MR
M.C. Rozendaal
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
10 records found
1
Professional painting is a physically demanding job that frequently leads to long-term health issues. To reduce this physical strain, prior research developed a motorized robot cart assistant. However, this prototype lacked a defined behavioural repertoire, limiting its practical usability regarding control, feedback, and autonomy. This thesis addresses this gap by exploring how this robot can be transformed into a transparent and collaborative tool through appropriate autonomy design and multimodal interaction.
The research followed a Double Diamond design process, combining literature research, a benchmark of existing autonomous systems, and stakeholder input. These insights were subsequently explored in an exploratory field study with professional painters using a Wizard-of-Oz approach. The findings demonstrated a clear user preference for the robot to function as a responsive, predictable tool carrier rather than a proactive autonomous collaborator. Furthermore, the study highlighted the strict necessity for simple, physically grounded interaction over complex digital interfaces, as painters must maintain visual focus on their work. Based on these insights, the project scope was refined to focus specifically on the active work scenario within a constrained, one-dimensional workspace alongside a wall.
A functional motorized prototype was developed to evaluate the proposed interaction concepts in practice. The system incorporated a Time-of-Flight sensor for distance regulation, three distinct behavioural modes (Manual, Continuous Follow, and Segmented Follow), a wearable tactile remote, and a digital dashboard. A validation user study was then conducted, comparing the autonomous prototype against a manual cart baseline using abstract wall-based tasks and NASA-TLX workload assessments. The results showed that autonomous assistance successfully reduced physical effort but redistributed the workload by increasing cognitive demand, as users initially needed to monitor the robot's state. Additionally, the autonomous cart induced a shift in user workflow from sequential task execution to more efficient batch-processing strategies.
To address the observed increase in cognitive load, the interfaces were redesigned to include distinct tactile buttons, a physical mode slider, haptic vibration feedback, and a simplified dashboard. An extended familiarisation study was subsequently conducted to investigate interaction over repeated trials. This follow-up study revealed that the previously elevated mental workload was primarily a temporary learning effect. With repeated exposure, this participant's perceived mental demand dropped significantly, interaction efficiency improved, and they successfully adapted their workflow to naturally integrate the autonomous system. The thesis concludes that effective robotic assistance in this context depends on predictable robot behaviour, explicit state communication, and a shared-control approach that enables simple tactile interaction and immediate physical user override.
...
The research followed a Double Diamond design process, combining literature research, a benchmark of existing autonomous systems, and stakeholder input. These insights were subsequently explored in an exploratory field study with professional painters using a Wizard-of-Oz approach. The findings demonstrated a clear user preference for the robot to function as a responsive, predictable tool carrier rather than a proactive autonomous collaborator. Furthermore, the study highlighted the strict necessity for simple, physically grounded interaction over complex digital interfaces, as painters must maintain visual focus on their work. Based on these insights, the project scope was refined to focus specifically on the active work scenario within a constrained, one-dimensional workspace alongside a wall.
A functional motorized prototype was developed to evaluate the proposed interaction concepts in practice. The system incorporated a Time-of-Flight sensor for distance regulation, three distinct behavioural modes (Manual, Continuous Follow, and Segmented Follow), a wearable tactile remote, and a digital dashboard. A validation user study was then conducted, comparing the autonomous prototype against a manual cart baseline using abstract wall-based tasks and NASA-TLX workload assessments. The results showed that autonomous assistance successfully reduced physical effort but redistributed the workload by increasing cognitive demand, as users initially needed to monitor the robot's state. Additionally, the autonomous cart induced a shift in user workflow from sequential task execution to more efficient batch-processing strategies.
To address the observed increase in cognitive load, the interfaces were redesigned to include distinct tactile buttons, a physical mode slider, haptic vibration feedback, and a simplified dashboard. An extended familiarisation study was subsequently conducted to investigate interaction over repeated trials. This follow-up study revealed that the previously elevated mental workload was primarily a temporary learning effect. With repeated exposure, this participant's perceived mental demand dropped significantly, interaction efficiency improved, and they successfully adapted their workflow to naturally integrate the autonomous system. The thesis concludes that effective robotic assistance in this context depends on predictable robot behaviour, explicit state communication, and a shared-control approach that enables simple tactile interaction and immediate physical user override.
...
Professional painting is a physically demanding job that frequently leads to long-term health issues. To reduce this physical strain, prior research developed a motorized robot cart assistant. However, this prototype lacked a defined behavioural repertoire, limiting its practical usability regarding control, feedback, and autonomy. This thesis addresses this gap by exploring how this robot can be transformed into a transparent and collaborative tool through appropriate autonomy design and multimodal interaction.
The research followed a Double Diamond design process, combining literature research, a benchmark of existing autonomous systems, and stakeholder input. These insights were subsequently explored in an exploratory field study with professional painters using a Wizard-of-Oz approach. The findings demonstrated a clear user preference for the robot to function as a responsive, predictable tool carrier rather than a proactive autonomous collaborator. Furthermore, the study highlighted the strict necessity for simple, physically grounded interaction over complex digital interfaces, as painters must maintain visual focus on their work. Based on these insights, the project scope was refined to focus specifically on the active work scenario within a constrained, one-dimensional workspace alongside a wall.
A functional motorized prototype was developed to evaluate the proposed interaction concepts in practice. The system incorporated a Time-of-Flight sensor for distance regulation, three distinct behavioural modes (Manual, Continuous Follow, and Segmented Follow), a wearable tactile remote, and a digital dashboard. A validation user study was then conducted, comparing the autonomous prototype against a manual cart baseline using abstract wall-based tasks and NASA-TLX workload assessments. The results showed that autonomous assistance successfully reduced physical effort but redistributed the workload by increasing cognitive demand, as users initially needed to monitor the robot's state. Additionally, the autonomous cart induced a shift in user workflow from sequential task execution to more efficient batch-processing strategies.
To address the observed increase in cognitive load, the interfaces were redesigned to include distinct tactile buttons, a physical mode slider, haptic vibration feedback, and a simplified dashboard. An extended familiarisation study was subsequently conducted to investigate interaction over repeated trials. This follow-up study revealed that the previously elevated mental workload was primarily a temporary learning effect. With repeated exposure, this participant's perceived mental demand dropped significantly, interaction efficiency improved, and they successfully adapted their workflow to naturally integrate the autonomous system. The thesis concludes that effective robotic assistance in this context depends on predictable robot behaviour, explicit state communication, and a shared-control approach that enables simple tactile interaction and immediate physical user override.
The research followed a Double Diamond design process, combining literature research, a benchmark of existing autonomous systems, and stakeholder input. These insights were subsequently explored in an exploratory field study with professional painters using a Wizard-of-Oz approach. The findings demonstrated a clear user preference for the robot to function as a responsive, predictable tool carrier rather than a proactive autonomous collaborator. Furthermore, the study highlighted the strict necessity for simple, physically grounded interaction over complex digital interfaces, as painters must maintain visual focus on their work. Based on these insights, the project scope was refined to focus specifically on the active work scenario within a constrained, one-dimensional workspace alongside a wall.
A functional motorized prototype was developed to evaluate the proposed interaction concepts in practice. The system incorporated a Time-of-Flight sensor for distance regulation, three distinct behavioural modes (Manual, Continuous Follow, and Segmented Follow), a wearable tactile remote, and a digital dashboard. A validation user study was then conducted, comparing the autonomous prototype against a manual cart baseline using abstract wall-based tasks and NASA-TLX workload assessments. The results showed that autonomous assistance successfully reduced physical effort but redistributed the workload by increasing cognitive demand, as users initially needed to monitor the robot's state. Additionally, the autonomous cart induced a shift in user workflow from sequential task execution to more efficient batch-processing strategies.
To address the observed increase in cognitive load, the interfaces were redesigned to include distinct tactile buttons, a physical mode slider, haptic vibration feedback, and a simplified dashboard. An extended familiarisation study was subsequently conducted to investigate interaction over repeated trials. This follow-up study revealed that the previously elevated mental workload was primarily a temporary learning effect. With repeated exposure, this participant's perceived mental demand dropped significantly, interaction efficiency improved, and they successfully adapted their workflow to naturally integrate the autonomous system. The thesis concludes that effective robotic assistance in this context depends on predictable robot behaviour, explicit state communication, and a shared-control approach that enables simple tactile interaction and immediate physical user override.
The professional painting sector in the Netherlands faces several challenges: an ageing workforce, limited inflow of young workers, and a high number of occupational health disorders, particularly musculoskeletal disorders. These challenges contribute to existing labour shortages, increasing work pressure and forcing painters to prioritise speed over quality.
Building on the prior work of Hoogendijk (2023) and Jansen (2025), this thesis further develops the concept of a robot assistant for professional painters towards commercialisation, resulting in a high-fidelity prototype integrated with a dedicated robot platform developed by RoboHouse.
The project follows a double-diamond approach, combining a review of existing human-robot interaction (HRI) literature with the analysis of a value proposition and the technical constraints of the robot platform. These findings were used to inform the design process.
The initial research showed that scale is important for the feasibility and viability of the robot concept, as software development was identified as a major cost driver. Achieving scale would spread these costs, enabling the offering of an affordable product. This finding led to a shift from a painter-specific robot to a modular robot concept that can also serve similar applications, such as carpentry, plumbing, and installation. This allowed the broadening of the addressable market without abandoning the original user group.
This led to the concept of Oxen, a modular robot companion that follows workers on-site and can be summoned to keep tools and materials at hand. The robot concept consists of a base that handles uneven construction terrain through a skid-steer mechanism. The robot combines an RGB-D camera and LiDAR with a wearable tracking device to provide reliable following and quick controls. The robot has a detachable controller that houses the main interface and allows manual take-over.
The modular configurations facilitate tool organisation, material handling, and lifting to a comfortable working height. A direct-purchase model is proposed for early users, whilst a robotics-as-a-service is recommended to achieve wider adoption.
The prototype was received enthusiastically by potential customers from the painting industry. However, in evaluating the robot concept against market-adoption metrics, it showed that it addresses many of the sector's challenges but does not resolve any single one exceptionally well. This indicates a gap between initial enthusiasm for a single product and the conditions required for mass adoption. This is discussed alongside recommendations for further technical and commercial development. Oxen is introduced not as a replacement for artisans but as a collaborative teammate, offering a modular, scalable solution to address challenges in the construction finishing sector.
...
Building on the prior work of Hoogendijk (2023) and Jansen (2025), this thesis further develops the concept of a robot assistant for professional painters towards commercialisation, resulting in a high-fidelity prototype integrated with a dedicated robot platform developed by RoboHouse.
The project follows a double-diamond approach, combining a review of existing human-robot interaction (HRI) literature with the analysis of a value proposition and the technical constraints of the robot platform. These findings were used to inform the design process.
The initial research showed that scale is important for the feasibility and viability of the robot concept, as software development was identified as a major cost driver. Achieving scale would spread these costs, enabling the offering of an affordable product. This finding led to a shift from a painter-specific robot to a modular robot concept that can also serve similar applications, such as carpentry, plumbing, and installation. This allowed the broadening of the addressable market without abandoning the original user group.
This led to the concept of Oxen, a modular robot companion that follows workers on-site and can be summoned to keep tools and materials at hand. The robot concept consists of a base that handles uneven construction terrain through a skid-steer mechanism. The robot combines an RGB-D camera and LiDAR with a wearable tracking device to provide reliable following and quick controls. The robot has a detachable controller that houses the main interface and allows manual take-over.
The modular configurations facilitate tool organisation, material handling, and lifting to a comfortable working height. A direct-purchase model is proposed for early users, whilst a robotics-as-a-service is recommended to achieve wider adoption.
The prototype was received enthusiastically by potential customers from the painting industry. However, in evaluating the robot concept against market-adoption metrics, it showed that it addresses many of the sector's challenges but does not resolve any single one exceptionally well. This indicates a gap between initial enthusiasm for a single product and the conditions required for mass adoption. This is discussed alongside recommendations for further technical and commercial development. Oxen is introduced not as a replacement for artisans but as a collaborative teammate, offering a modular, scalable solution to address challenges in the construction finishing sector.
...
The professional painting sector in the Netherlands faces several challenges: an ageing workforce, limited inflow of young workers, and a high number of occupational health disorders, particularly musculoskeletal disorders. These challenges contribute to existing labour shortages, increasing work pressure and forcing painters to prioritise speed over quality.
Building on the prior work of Hoogendijk (2023) and Jansen (2025), this thesis further develops the concept of a robot assistant for professional painters towards commercialisation, resulting in a high-fidelity prototype integrated with a dedicated robot platform developed by RoboHouse.
The project follows a double-diamond approach, combining a review of existing human-robot interaction (HRI) literature with the analysis of a value proposition and the technical constraints of the robot platform. These findings were used to inform the design process.
The initial research showed that scale is important for the feasibility and viability of the robot concept, as software development was identified as a major cost driver. Achieving scale would spread these costs, enabling the offering of an affordable product. This finding led to a shift from a painter-specific robot to a modular robot concept that can also serve similar applications, such as carpentry, plumbing, and installation. This allowed the broadening of the addressable market without abandoning the original user group.
This led to the concept of Oxen, a modular robot companion that follows workers on-site and can be summoned to keep tools and materials at hand. The robot concept consists of a base that handles uneven construction terrain through a skid-steer mechanism. The robot combines an RGB-D camera and LiDAR with a wearable tracking device to provide reliable following and quick controls. The robot has a detachable controller that houses the main interface and allows manual take-over.
The modular configurations facilitate tool organisation, material handling, and lifting to a comfortable working height. A direct-purchase model is proposed for early users, whilst a robotics-as-a-service is recommended to achieve wider adoption.
The prototype was received enthusiastically by potential customers from the painting industry. However, in evaluating the robot concept against market-adoption metrics, it showed that it addresses many of the sector's challenges but does not resolve any single one exceptionally well. This indicates a gap between initial enthusiasm for a single product and the conditions required for mass adoption. This is discussed alongside recommendations for further technical and commercial development. Oxen is introduced not as a replacement for artisans but as a collaborative teammate, offering a modular, scalable solution to address challenges in the construction finishing sector.
Building on the prior work of Hoogendijk (2023) and Jansen (2025), this thesis further develops the concept of a robot assistant for professional painters towards commercialisation, resulting in a high-fidelity prototype integrated with a dedicated robot platform developed by RoboHouse.
The project follows a double-diamond approach, combining a review of existing human-robot interaction (HRI) literature with the analysis of a value proposition and the technical constraints of the robot platform. These findings were used to inform the design process.
The initial research showed that scale is important for the feasibility and viability of the robot concept, as software development was identified as a major cost driver. Achieving scale would spread these costs, enabling the offering of an affordable product. This finding led to a shift from a painter-specific robot to a modular robot concept that can also serve similar applications, such as carpentry, plumbing, and installation. This allowed the broadening of the addressable market without abandoning the original user group.
This led to the concept of Oxen, a modular robot companion that follows workers on-site and can be summoned to keep tools and materials at hand. The robot concept consists of a base that handles uneven construction terrain through a skid-steer mechanism. The robot combines an RGB-D camera and LiDAR with a wearable tracking device to provide reliable following and quick controls. The robot has a detachable controller that houses the main interface and allows manual take-over.
The modular configurations facilitate tool organisation, material handling, and lifting to a comfortable working height. A direct-purchase model is proposed for early users, whilst a robotics-as-a-service is recommended to achieve wider adoption.
The prototype was received enthusiastically by potential customers from the painting industry. However, in evaluating the robot concept against market-adoption metrics, it showed that it addresses many of the sector's challenges but does not resolve any single one exceptionally well. This indicates a gap between initial enthusiasm for a single product and the conditions required for mass adoption. This is discussed alongside recommendations for further technical and commercial development. Oxen is introduced not as a replacement for artisans but as a collaborative teammate, offering a modular, scalable solution to address challenges in the construction finishing sector.
This thesis explores the design and development of a bio-inspired robotic module that enhances intuitive human interaction within a swarm robotics context. The work addresses a research gap in Human-Swarm Interaction by focusing on how individual swarm robots can express emotions and respond to humans in meaningful, non-verbal ways, drawing inspiration from both domesticated animals, like dogs, and arthropods. The project integrates sensory and expressive components such as eyes, antennae, and body movement into a modular "symbiote" that can be mounted on existing robots. Through iterative prototyping, user studies, and expert consultations, the research identifies key emotional states and corresponding expressive behaviors, culminating in a module that communicates through movement of its appendages. The module supports real-time interaction and demonstrates the potential for robots to form more natural and intuitive relationships with human users, especially in exhibition environments like TU Delft’s Cyber Zoo. The findings contribute to the fields of bio-inspired design, swarm robotics, and human-robot interaction by offering a novel approach to enhancing emotional legibility and engagement in robotic swarms.
...
This thesis explores the design and development of a bio-inspired robotic module that enhances intuitive human interaction within a swarm robotics context. The work addresses a research gap in Human-Swarm Interaction by focusing on how individual swarm robots can express emotions and respond to humans in meaningful, non-verbal ways, drawing inspiration from both domesticated animals, like dogs, and arthropods. The project integrates sensory and expressive components such as eyes, antennae, and body movement into a modular "symbiote" that can be mounted on existing robots. Through iterative prototyping, user studies, and expert consultations, the research identifies key emotional states and corresponding expressive behaviors, culminating in a module that communicates through movement of its appendages. The module supports real-time interaction and demonstrates the potential for robots to form more natural and intuitive relationships with human users, especially in exhibition environments like TU Delft’s Cyber Zoo. The findings contribute to the fields of bio-inspired design, swarm robotics, and human-robot interaction by offering a novel approach to enhancing emotional legibility and engagement in robotic swarms.
Cognitive Companion
Designing a cognitive assistant for the bedside nursing practice at the Erasmus MC Sophia
Technological innovation can provide valuable solutions for the challenges facing the Dutch healthcare sector. However, the development of such innovations poses transdisciplinary challenges in aligning academic research, practice, and technology. This graduation project addresses those challenges by conducting exploratory design research for the bedside nursing practice at the Children’s Thorax Center at Erasmus MC Sophia Children’s Hospital.
The initial phase of the project focused on gaining familiarity with the bedside nursing practice to establish preliminary insights for desired changes. Two nurses were shadowed during their shifts at the aforementioned pediatric ward, employing a contextual inquiry research method to gather observational insights and enhance the understanding of bedside nursing. A reflective analysis of practice understanding, established through nurse feedback and observations, resulted in a list of desired transformations within the practice. These transformations were validated and further elaborated upon through a group feedback session with nurses, which culminated in primary design opportunities involving improved local accessibility of medical data for both input and retrieval, interpersonal communication, and memory support.
The second phase focused on further defining strategic opportunities for innovation development and bridging insights from current practice to a design direction for the desired future. The analysis of four practice dimensions relating to tangibility and relativity resulted in ‘personal cognitive support for nurses at the bedside’ being identified as the most valuable strategic focus for novel technology research and design development. Subsequently, a future perspective of bedside nursing practice was explored through a generative session with nurses, further highlighting the need for cognitive support and technology accessibility at the bedside. This led to a design direction pursuing the development of a cognitive assistant within a future perspective involving pervasive computing.
The third and final phase of the project involved Research through Design development, using a bridging concept for a cognitive assistant named the Cognitive Companion (Coco). Coco is developed as an AI-enabled wearable device, worn in the chest pocket of the nursing uniform, to provide nurses with always-accessible cognitive assistance wherever they go. It features the operational ease of voice control using AI speech recognition, suited for interactions at the bedside. The purpose of Coco as a bridging concept is to facilitate further research and design development in nursing practice toward the realization of the pervasive computing future perspective. To achieve this, a pretotype was built and used in real nursing practice. This revealed that current interventions force nurses to adjust their practice to accommodate technology interactions, which adds extra mental strain by demanding their focus and mental energy during bedside care.
Ultimately, this project concludes that future technological developments for bedside nursing should focus on human interactions and care, which are fundamental aspects that must be safeguarded. Interactions with technology interventions should be simple, easily accessible, and seamlessly integrated into the practice surroundings so that they support rather than distract from patient care. The proposal building on these findings follows a future perspective of pervasive computing in practice, which can be supported through the development of the Coco AI-enabled wearable. ...
The initial phase of the project focused on gaining familiarity with the bedside nursing practice to establish preliminary insights for desired changes. Two nurses were shadowed during their shifts at the aforementioned pediatric ward, employing a contextual inquiry research method to gather observational insights and enhance the understanding of bedside nursing. A reflective analysis of practice understanding, established through nurse feedback and observations, resulted in a list of desired transformations within the practice. These transformations were validated and further elaborated upon through a group feedback session with nurses, which culminated in primary design opportunities involving improved local accessibility of medical data for both input and retrieval, interpersonal communication, and memory support.
The second phase focused on further defining strategic opportunities for innovation development and bridging insights from current practice to a design direction for the desired future. The analysis of four practice dimensions relating to tangibility and relativity resulted in ‘personal cognitive support for nurses at the bedside’ being identified as the most valuable strategic focus for novel technology research and design development. Subsequently, a future perspective of bedside nursing practice was explored through a generative session with nurses, further highlighting the need for cognitive support and technology accessibility at the bedside. This led to a design direction pursuing the development of a cognitive assistant within a future perspective involving pervasive computing.
The third and final phase of the project involved Research through Design development, using a bridging concept for a cognitive assistant named the Cognitive Companion (Coco). Coco is developed as an AI-enabled wearable device, worn in the chest pocket of the nursing uniform, to provide nurses with always-accessible cognitive assistance wherever they go. It features the operational ease of voice control using AI speech recognition, suited for interactions at the bedside. The purpose of Coco as a bridging concept is to facilitate further research and design development in nursing practice toward the realization of the pervasive computing future perspective. To achieve this, a pretotype was built and used in real nursing practice. This revealed that current interventions force nurses to adjust their practice to accommodate technology interactions, which adds extra mental strain by demanding their focus and mental energy during bedside care.
Ultimately, this project concludes that future technological developments for bedside nursing should focus on human interactions and care, which are fundamental aspects that must be safeguarded. Interactions with technology interventions should be simple, easily accessible, and seamlessly integrated into the practice surroundings so that they support rather than distract from patient care. The proposal building on these findings follows a future perspective of pervasive computing in practice, which can be supported through the development of the Coco AI-enabled wearable. ...
Technological innovation can provide valuable solutions for the challenges facing the Dutch healthcare sector. However, the development of such innovations poses transdisciplinary challenges in aligning academic research, practice, and technology. This graduation project addresses those challenges by conducting exploratory design research for the bedside nursing practice at the Children’s Thorax Center at Erasmus MC Sophia Children’s Hospital.
The initial phase of the project focused on gaining familiarity with the bedside nursing practice to establish preliminary insights for desired changes. Two nurses were shadowed during their shifts at the aforementioned pediatric ward, employing a contextual inquiry research method to gather observational insights and enhance the understanding of bedside nursing. A reflective analysis of practice understanding, established through nurse feedback and observations, resulted in a list of desired transformations within the practice. These transformations were validated and further elaborated upon through a group feedback session with nurses, which culminated in primary design opportunities involving improved local accessibility of medical data for both input and retrieval, interpersonal communication, and memory support.
The second phase focused on further defining strategic opportunities for innovation development and bridging insights from current practice to a design direction for the desired future. The analysis of four practice dimensions relating to tangibility and relativity resulted in ‘personal cognitive support for nurses at the bedside’ being identified as the most valuable strategic focus for novel technology research and design development. Subsequently, a future perspective of bedside nursing practice was explored through a generative session with nurses, further highlighting the need for cognitive support and technology accessibility at the bedside. This led to a design direction pursuing the development of a cognitive assistant within a future perspective involving pervasive computing.
The third and final phase of the project involved Research through Design development, using a bridging concept for a cognitive assistant named the Cognitive Companion (Coco). Coco is developed as an AI-enabled wearable device, worn in the chest pocket of the nursing uniform, to provide nurses with always-accessible cognitive assistance wherever they go. It features the operational ease of voice control using AI speech recognition, suited for interactions at the bedside. The purpose of Coco as a bridging concept is to facilitate further research and design development in nursing practice toward the realization of the pervasive computing future perspective. To achieve this, a pretotype was built and used in real nursing practice. This revealed that current interventions force nurses to adjust their practice to accommodate technology interactions, which adds extra mental strain by demanding their focus and mental energy during bedside care.
Ultimately, this project concludes that future technological developments for bedside nursing should focus on human interactions and care, which are fundamental aspects that must be safeguarded. Interactions with technology interventions should be simple, easily accessible, and seamlessly integrated into the practice surroundings so that they support rather than distract from patient care. The proposal building on these findings follows a future perspective of pervasive computing in practice, which can be supported through the development of the Coco AI-enabled wearable.
The initial phase of the project focused on gaining familiarity with the bedside nursing practice to establish preliminary insights for desired changes. Two nurses were shadowed during their shifts at the aforementioned pediatric ward, employing a contextual inquiry research method to gather observational insights and enhance the understanding of bedside nursing. A reflective analysis of practice understanding, established through nurse feedback and observations, resulted in a list of desired transformations within the practice. These transformations were validated and further elaborated upon through a group feedback session with nurses, which culminated in primary design opportunities involving improved local accessibility of medical data for both input and retrieval, interpersonal communication, and memory support.
The second phase focused on further defining strategic opportunities for innovation development and bridging insights from current practice to a design direction for the desired future. The analysis of four practice dimensions relating to tangibility and relativity resulted in ‘personal cognitive support for nurses at the bedside’ being identified as the most valuable strategic focus for novel technology research and design development. Subsequently, a future perspective of bedside nursing practice was explored through a generative session with nurses, further highlighting the need for cognitive support and technology accessibility at the bedside. This led to a design direction pursuing the development of a cognitive assistant within a future perspective involving pervasive computing.
The third and final phase of the project involved Research through Design development, using a bridging concept for a cognitive assistant named the Cognitive Companion (Coco). Coco is developed as an AI-enabled wearable device, worn in the chest pocket of the nursing uniform, to provide nurses with always-accessible cognitive assistance wherever they go. It features the operational ease of voice control using AI speech recognition, suited for interactions at the bedside. The purpose of Coco as a bridging concept is to facilitate further research and design development in nursing practice toward the realization of the pervasive computing future perspective. To achieve this, a pretotype was built and used in real nursing practice. This revealed that current interventions force nurses to adjust their practice to accommodate technology interactions, which adds extra mental strain by demanding their focus and mental energy during bedside care.
Ultimately, this project concludes that future technological developments for bedside nursing should focus on human interactions and care, which are fundamental aspects that must be safeguarded. Interactions with technology interventions should be simple, easily accessible, and seamlessly integrated into the practice surroundings so that they support rather than distract from patient care. The proposal building on these findings follows a future perspective of pervasive computing in practice, which can be supported through the development of the Coco AI-enabled wearable.
This project focuses on improving computer keyboard interaction for people with Parkinson’s Disease (PD), specifically addressing the symptom of bradykinesia, which causes slowed movement and impairs fine motor skills. The objective is to explore the integration of cueing techniques—external stimuli such as auditory prompts, visual cues, and haptic feedback—to assist people with PD in initiating and executing movements more effectively.
Adopting a user-centered design approach and involving actual users throughout the research and testing phases, the project investigated various concepts to enhance the ergonomics and functionality of keyboards for people with Parkinson’s. Multiple prototypes were developed and tested through focus groups, providing valuable feedback that guided the refinement of the design.
The final design, called OnCue, features a modular system comprising an ergonomic keyboard specifically tailored to users’ needs, with integrated haptic feedback, visual cues, and haptic cuffs. A key feature of the design is its customizability, allowing the system to adapt to individual needs as symptoms fluctuate daily. The goal is to reduce frustration and improve the quality of life for people affected by Parkinson’s. This project demonstrates the potential of adaptive technologies to significantly enhance well-being and foster greater independence for users. ...
Adopting a user-centered design approach and involving actual users throughout the research and testing phases, the project investigated various concepts to enhance the ergonomics and functionality of keyboards for people with Parkinson’s. Multiple prototypes were developed and tested through focus groups, providing valuable feedback that guided the refinement of the design.
The final design, called OnCue, features a modular system comprising an ergonomic keyboard specifically tailored to users’ needs, with integrated haptic feedback, visual cues, and haptic cuffs. A key feature of the design is its customizability, allowing the system to adapt to individual needs as symptoms fluctuate daily. The goal is to reduce frustration and improve the quality of life for people affected by Parkinson’s. This project demonstrates the potential of adaptive technologies to significantly enhance well-being and foster greater independence for users. ...
This project focuses on improving computer keyboard interaction for people with Parkinson’s Disease (PD), specifically addressing the symptom of bradykinesia, which causes slowed movement and impairs fine motor skills. The objective is to explore the integration of cueing techniques—external stimuli such as auditory prompts, visual cues, and haptic feedback—to assist people with PD in initiating and executing movements more effectively.
Adopting a user-centered design approach and involving actual users throughout the research and testing phases, the project investigated various concepts to enhance the ergonomics and functionality of keyboards for people with Parkinson’s. Multiple prototypes were developed and tested through focus groups, providing valuable feedback that guided the refinement of the design.
The final design, called OnCue, features a modular system comprising an ergonomic keyboard specifically tailored to users’ needs, with integrated haptic feedback, visual cues, and haptic cuffs. A key feature of the design is its customizability, allowing the system to adapt to individual needs as symptoms fluctuate daily. The goal is to reduce frustration and improve the quality of life for people affected by Parkinson’s. This project demonstrates the potential of adaptive technologies to significantly enhance well-being and foster greater independence for users.
Adopting a user-centered design approach and involving actual users throughout the research and testing phases, the project investigated various concepts to enhance the ergonomics and functionality of keyboards for people with Parkinson’s. Multiple prototypes were developed and tested through focus groups, providing valuable feedback that guided the refinement of the design.
The final design, called OnCue, features a modular system comprising an ergonomic keyboard specifically tailored to users’ needs, with integrated haptic feedback, visual cues, and haptic cuffs. A key feature of the design is its customizability, allowing the system to adapt to individual needs as symptoms fluctuate daily. The goal is to reduce frustration and improve the quality of life for people affected by Parkinson’s. This project demonstrates the potential of adaptive technologies to significantly enhance well-being and foster greater independence for users.
Design Guidelines for Human-Agent Collaboration in a Painting Context
Authority, Autonomy, and Delegation
This project focuses on developing design guidelines for Human-Agent Collaboration around Authority, Autonomy, and Control in the outdoor painting context. While painting as an activity is something most of us have done and understand, working professionals have a sense of pride and skill in their motions that would be difficult to replace with agents. Painters are generally conservative and wary of innovation, as they deeply enjoy the restoration process. Still, they are also a profession that finds it difficult to recruit as many people as before. This project explored how agents could support painters to work sustainably to see what possibilities exist for collaboration. Through a combination of design and research activities, a Design Fiction grounded in painting practice and focused on Authority, Autonomy, and Control was developed. The Design Fiction facilitated discussions with painters around the three themes. From these discussions, design guidelines were developed for each theme.
The guidelines contributed to the project's overall goal: understanding how agentic technology could facilitate the sustainable employment of painters. ...
The guidelines contributed to the project's overall goal: understanding how agentic technology could facilitate the sustainable employment of painters. ...
This project focuses on developing design guidelines for Human-Agent Collaboration around Authority, Autonomy, and Control in the outdoor painting context. While painting as an activity is something most of us have done and understand, working professionals have a sense of pride and skill in their motions that would be difficult to replace with agents. Painters are generally conservative and wary of innovation, as they deeply enjoy the restoration process. Still, they are also a profession that finds it difficult to recruit as many people as before. This project explored how agents could support painters to work sustainably to see what possibilities exist for collaboration. Through a combination of design and research activities, a Design Fiction grounded in painting practice and focused on Authority, Autonomy, and Control was developed. The Design Fiction facilitated discussions with painters around the three themes. From these discussions, design guidelines were developed for each theme.
The guidelines contributed to the project's overall goal: understanding how agentic technology could facilitate the sustainable employment of painters.
The guidelines contributed to the project's overall goal: understanding how agentic technology could facilitate the sustainable employment of painters.
This thesis investigates the behavior of an elastomer spherical structure compressed by a small object compared to the cross-section of the structure. The study is based on the situation in which a child catches a ball multiple times with two hands. This was simplified to a situation where a hemisphere was cyclically compressed by a small object. The elastomer chosen was the cured resin Elastic 50A, which is manufactured by Formlabs. Stereo lithography was used to print the investigated structures. Layer-by-layer printing introduced the ability to print the same structure with different layering. Elastomers and rubbers cannot be described by a linear material model. Therefore, the non-linear behavior of the elastomer was obtained experimentally. Material behavior was described by performing a uni-axial tensile test with dumbbell specimens printed in three different directions according to ASTM D412. The dumbbell specimens were printed in the x-, y- and z-directions, representing upright, lateral and supine positions. A comparison between the specimen force-deflection responses and the finite-element analysis(FEA) responses showed that different models performed best for different print directions. Ansys Mechanical was used to calibrate the hyper-elastic material models available to describe a material with a single uni-axial test. The curve fitting tool of Ansys was used to acquire the Arruda-Boyce, Gent and Yeoh model constants. The 2nd-order Yeoh model performed best for the x-direction printed specimen. The 1st-order Yeoh model performed best for the y- and z-direction printed specimen. These models were used in the finite-element analysis on the elastomer hemispheres. The hemispheres were printed in the y- and z- direction, representing the upright and lateral positions. The experimentally obtained peak forces for the z-direction printed hemisphere were 19.61 and 17.76 N for the velocities of 50 and 500mm/min, respectively. The peak forces for the y-direction printed hemisphere were 19.40 and 17.51 N for the velocities of 50 and 500mm/min, respectively. The prediction of the finite- element analysis showed a higher peak force at 50mm/min of 33.78, 29 and 36.27 N for the x-, y- and z-direction models used, respectively. The prediction of the finite-element analysis showed a higher peak force at 500 mm/min of 33.62, 28.91 and 36.1 N for the x-, y- and z-direction models used, respectively. The hysteresis found during the compression test did not match the hysteresis found in the FEA. The experimentally obtained hysteresis was larger than the hysteresis predicted by finite-element analysis. Both hemispheres were able to support the loads without damage for ten cycles.
...
This thesis investigates the behavior of an elastomer spherical structure compressed by a small object compared to the cross-section of the structure. The study is based on the situation in which a child catches a ball multiple times with two hands. This was simplified to a situation where a hemisphere was cyclically compressed by a small object. The elastomer chosen was the cured resin Elastic 50A, which is manufactured by Formlabs. Stereo lithography was used to print the investigated structures. Layer-by-layer printing introduced the ability to print the same structure with different layering. Elastomers and rubbers cannot be described by a linear material model. Therefore, the non-linear behavior of the elastomer was obtained experimentally. Material behavior was described by performing a uni-axial tensile test with dumbbell specimens printed in three different directions according to ASTM D412. The dumbbell specimens were printed in the x-, y- and z-directions, representing upright, lateral and supine positions. A comparison between the specimen force-deflection responses and the finite-element analysis(FEA) responses showed that different models performed best for different print directions. Ansys Mechanical was used to calibrate the hyper-elastic material models available to describe a material with a single uni-axial test. The curve fitting tool of Ansys was used to acquire the Arruda-Boyce, Gent and Yeoh model constants. The 2nd-order Yeoh model performed best for the x-direction printed specimen. The 1st-order Yeoh model performed best for the y- and z-direction printed specimen. These models were used in the finite-element analysis on the elastomer hemispheres. The hemispheres were printed in the y- and z- direction, representing the upright and lateral positions. The experimentally obtained peak forces for the z-direction printed hemisphere were 19.61 and 17.76 N for the velocities of 50 and 500mm/min, respectively. The peak forces for the y-direction printed hemisphere were 19.40 and 17.51 N for the velocities of 50 and 500mm/min, respectively. The prediction of the finite- element analysis showed a higher peak force at 50mm/min of 33.78, 29 and 36.27 N for the x-, y- and z-direction models used, respectively. The prediction of the finite-element analysis showed a higher peak force at 500 mm/min of 33.62, 28.91 and 36.1 N for the x-, y- and z-direction models used, respectively. The hysteresis found during the compression test did not match the hysteresis found in the FEA. The experimentally obtained hysteresis was larger than the hysteresis predicted by finite-element analysis. Both hemispheres were able to support the loads without damage for ten cycles.
As robots become increasingly popular and co-inhabit spaces with people, there is a need for designing robots that people are comfortable interacting with. For robots to successfully integrate into human society, it is important to design robots in a way that enhances the quality of the human-robot interaction. While the human-robot relationship typically exists to serve people, there will be instances when robots require human assistance. This project aims to investigate people’s interactions with robots that need their assistance. It employs a robot designed to test people’s willingness to help it achieve a goal under various scenarios.
The project in its entirety was quite an ambitious one given the limited scope of a graduation project. A literature review carried at the beginning helped identify key features a robot and an interaction should have, in order for it to be perceived positively by humans interacting with it. This review culminated in a list of design considerations which informed the design and the interaction. These design considerations were referred to throughout the project, while choosing ideas for the interaction and while detailing the chosen scenario. A state machine was used to explain the general behavioural states of the robot, and the electronic components that facilitated the desired interaction were chosen. These components were coded to reflect the desired behaviour of the robot during the interaction. Alongside this process, the robot was embodied as sub-assemblies incorporating these components. Once the robot was given a form, the components were designed to fit within a modular body that accounted for zoomorphic and anthropomorphic features, while retaining functionality of the components inside. During its embodiment, the robot was given the ability to express itself through displayed speech, sounds, facial expressions and body language. Additional structures like "nests" were also designed to support the robot's interaction. Once the interaction was designed and embodied, the robot was then plot tested, before being used as a research probe to conduct human-robot interaction (HRI) experiments to address the research questions outlined at the start of the project. Data was gathered through data logging via the robot, user observations and interviews. The results of the experiments indicate that people's willingness to help a robot is influenced by the narrative of a human-robot interaction, the effort level of the task required to help the robot, as well as individuals' attitudes towards robots. Increasing the effort level reduced people's willingness to help the robot, but only when the narrative of the interaction was simple and functional, demonstrating that a narrative which tries to engage emotionally with participants has a positive effect on their altruistic response. The experiments were also able to shed some light on the social dynamics that emerge when a robot co-inhabits a space with people, as more people informed others about the robot.
...
The project in its entirety was quite an ambitious one given the limited scope of a graduation project. A literature review carried at the beginning helped identify key features a robot and an interaction should have, in order for it to be perceived positively by humans interacting with it. This review culminated in a list of design considerations which informed the design and the interaction. These design considerations were referred to throughout the project, while choosing ideas for the interaction and while detailing the chosen scenario. A state machine was used to explain the general behavioural states of the robot, and the electronic components that facilitated the desired interaction were chosen. These components were coded to reflect the desired behaviour of the robot during the interaction. Alongside this process, the robot was embodied as sub-assemblies incorporating these components. Once the robot was given a form, the components were designed to fit within a modular body that accounted for zoomorphic and anthropomorphic features, while retaining functionality of the components inside. During its embodiment, the robot was given the ability to express itself through displayed speech, sounds, facial expressions and body language. Additional structures like "nests" were also designed to support the robot's interaction. Once the interaction was designed and embodied, the robot was then plot tested, before being used as a research probe to conduct human-robot interaction (HRI) experiments to address the research questions outlined at the start of the project. Data was gathered through data logging via the robot, user observations and interviews. The results of the experiments indicate that people's willingness to help a robot is influenced by the narrative of a human-robot interaction, the effort level of the task required to help the robot, as well as individuals' attitudes towards robots. Increasing the effort level reduced people's willingness to help the robot, but only when the narrative of the interaction was simple and functional, demonstrating that a narrative which tries to engage emotionally with participants has a positive effect on their altruistic response. The experiments were also able to shed some light on the social dynamics that emerge when a robot co-inhabits a space with people, as more people informed others about the robot.
...
As robots become increasingly popular and co-inhabit spaces with people, there is a need for designing robots that people are comfortable interacting with. For robots to successfully integrate into human society, it is important to design robots in a way that enhances the quality of the human-robot interaction. While the human-robot relationship typically exists to serve people, there will be instances when robots require human assistance. This project aims to investigate people’s interactions with robots that need their assistance. It employs a robot designed to test people’s willingness to help it achieve a goal under various scenarios.
The project in its entirety was quite an ambitious one given the limited scope of a graduation project. A literature review carried at the beginning helped identify key features a robot and an interaction should have, in order for it to be perceived positively by humans interacting with it. This review culminated in a list of design considerations which informed the design and the interaction. These design considerations were referred to throughout the project, while choosing ideas for the interaction and while detailing the chosen scenario. A state machine was used to explain the general behavioural states of the robot, and the electronic components that facilitated the desired interaction were chosen. These components were coded to reflect the desired behaviour of the robot during the interaction. Alongside this process, the robot was embodied as sub-assemblies incorporating these components. Once the robot was given a form, the components were designed to fit within a modular body that accounted for zoomorphic and anthropomorphic features, while retaining functionality of the components inside. During its embodiment, the robot was given the ability to express itself through displayed speech, sounds, facial expressions and body language. Additional structures like "nests" were also designed to support the robot's interaction. Once the interaction was designed and embodied, the robot was then plot tested, before being used as a research probe to conduct human-robot interaction (HRI) experiments to address the research questions outlined at the start of the project. Data was gathered through data logging via the robot, user observations and interviews. The results of the experiments indicate that people's willingness to help a robot is influenced by the narrative of a human-robot interaction, the effort level of the task required to help the robot, as well as individuals' attitudes towards robots. Increasing the effort level reduced people's willingness to help the robot, but only when the narrative of the interaction was simple and functional, demonstrating that a narrative which tries to engage emotionally with participants has a positive effect on their altruistic response. The experiments were also able to shed some light on the social dynamics that emerge when a robot co-inhabits a space with people, as more people informed others about the robot.
The project in its entirety was quite an ambitious one given the limited scope of a graduation project. A literature review carried at the beginning helped identify key features a robot and an interaction should have, in order for it to be perceived positively by humans interacting with it. This review culminated in a list of design considerations which informed the design and the interaction. These design considerations were referred to throughout the project, while choosing ideas for the interaction and while detailing the chosen scenario. A state machine was used to explain the general behavioural states of the robot, and the electronic components that facilitated the desired interaction were chosen. These components were coded to reflect the desired behaviour of the robot during the interaction. Alongside this process, the robot was embodied as sub-assemblies incorporating these components. Once the robot was given a form, the components were designed to fit within a modular body that accounted for zoomorphic and anthropomorphic features, while retaining functionality of the components inside. During its embodiment, the robot was given the ability to express itself through displayed speech, sounds, facial expressions and body language. Additional structures like "nests" were also designed to support the robot's interaction. Once the interaction was designed and embodied, the robot was then plot tested, before being used as a research probe to conduct human-robot interaction (HRI) experiments to address the research questions outlined at the start of the project. Data was gathered through data logging via the robot, user observations and interviews. The results of the experiments indicate that people's willingness to help a robot is influenced by the narrative of a human-robot interaction, the effort level of the task required to help the robot, as well as individuals' attitudes towards robots. Increasing the effort level reduced people's willingness to help the robot, but only when the narrative of the interaction was simple and functional, demonstrating that a narrative which tries to engage emotionally with participants has a positive effect on their altruistic response. The experiments were also able to shed some light on the social dynamics that emerge when a robot co-inhabits a space with people, as more people informed others about the robot.
A Cleaner Public Space Through Robots
An exploratory research into the introduction of a cleaning robot in the Amsterdam Schoon department
The Dutch metropolis of Amsterdam deals with a waste problem. Both the inhabitants and tourists in Amsterdam experience nuisance from litter. The future growth of Amsterdam will only amplify this problem. To address this, the municipality needs to increase the productivity of the Schoon department, the department tasked with keeping the public space of Amsterdam clean. Therefore, the responsible and effective introduction of a cleaning robot is researched. During a series of walk-along days, interviews, experiments and observations, I identified multiple themes, important for the job satisfaction of the Schoon employees. This knowledge, combined with observed knowledge on practical challenges caused by the design of the Amsterdam public space on the cleaning activities, translates into a number of design qualities for a future cleaning robot. The results of this research seem to indicate that this cleaning robot could best be deployed during the shifts tasked with brooming the streets and emptying the trash bins, the Veegshift and Vuilnisbakkenshift respectively. During those shifts it can potentially assist in cleaning the street using the RAVO mechanical streetsweeper and emptying trash bins respectively. Assisting during those two tasks frees up manpower that can be utilized to increase the productivity of those shifts. The findings further highlight that this future robot should not compromise the freedom experienced by the Schoon employees in how they carry out their work. Nor should this robot replace the Schoon employees, as this would remove the human interaction with bystanders, an aspect of the work greatly appreciated by the employees. The loss of human interaction might also lead to a more monotonous situation, which is the opposite of the variety enjoyed by the Schoon employees during their work. The future robot should also be user friendly, allowing everyone in the department to operate the robot. Furthermore, the robot must be able to communicate its status, intentions and possible help requests and offers to its Schoon colleagues. Overall, the introduction of a cleaning robot can improve the cleanliness of the city of Amsterdam when the design incorporates the themes important for the job satisfaction of the Schoon employees, aims at an efficient human-robot collaboration through clear communication and combines the right type of autonomy with the challenging Amsterdam environment.
...
The Dutch metropolis of Amsterdam deals with a waste problem. Both the inhabitants and tourists in Amsterdam experience nuisance from litter. The future growth of Amsterdam will only amplify this problem. To address this, the municipality needs to increase the productivity of the Schoon department, the department tasked with keeping the public space of Amsterdam clean. Therefore, the responsible and effective introduction of a cleaning robot is researched. During a series of walk-along days, interviews, experiments and observations, I identified multiple themes, important for the job satisfaction of the Schoon employees. This knowledge, combined with observed knowledge on practical challenges caused by the design of the Amsterdam public space on the cleaning activities, translates into a number of design qualities for a future cleaning robot. The results of this research seem to indicate that this cleaning robot could best be deployed during the shifts tasked with brooming the streets and emptying the trash bins, the Veegshift and Vuilnisbakkenshift respectively. During those shifts it can potentially assist in cleaning the street using the RAVO mechanical streetsweeper and emptying trash bins respectively. Assisting during those two tasks frees up manpower that can be utilized to increase the productivity of those shifts. The findings further highlight that this future robot should not compromise the freedom experienced by the Schoon employees in how they carry out their work. Nor should this robot replace the Schoon employees, as this would remove the human interaction with bystanders, an aspect of the work greatly appreciated by the employees. The loss of human interaction might also lead to a more monotonous situation, which is the opposite of the variety enjoyed by the Schoon employees during their work. The future robot should also be user friendly, allowing everyone in the department to operate the robot. Furthermore, the robot must be able to communicate its status, intentions and possible help requests and offers to its Schoon colleagues. Overall, the introduction of a cleaning robot can improve the cleanliness of the city of Amsterdam when the design incorporates the themes important for the job satisfaction of the Schoon employees, aims at an efficient human-robot collaboration through clear communication and combines the right type of autonomy with the challenging Amsterdam environment.
Robot Code of Conduct for Automated Dairy Farming
Steering the Design of Pleasurable, Cohesive and Appropriate Behaviours for Lely Automated Portfolio
Robot systems are essentially a new species spreading around us, one that we willingly designed and introduced. Neither a natural species nor a mere human artefact. We have limited information about these smart agents. What do they want, what do you need from us, and how can we find a common ground of understanding to enhance each other through collaboration. Lely took a step into exploring these questions.
As a dutch-based company with a diverse portfolio of robot solutions, Lely thrives to bring dairy farming to the future. They cover many tasks assisting farmers and cows in barns worldwide. These increasingly capable entities are no longer tools but partners so we must take the next step into carefully designing our coexistence and collaboration with these robotic systems.
After extensive literature on Human-Robot Interaction (HRI) and research activities with a variety of stakeholders, I developed a Robot Code of Conduct. This code guides developers into designing robotic systems delivering pleasurable, fitting and cohesive interactions. It provides intermediate-level knowledge on robot behavioural design by carrying the reader through three sets of guidelines differing in abstraction and actionability.
This project contributes to the field of HRI while spreading awareness of its relevance in practice. The document contains many influential factors that are applied and tailored to designing automated solutions in dairy farming. This document sets a direction and gives concrete guidelines to steer the development of the portfolio towards a vision where all Lely systems work and communicate desirably. Where they communicate as one. I obtained positive results from assessing the content and direction of this document with developers and farmers, however, further tests would be necessary for a more precise validation of this Robot Code of Conduct. Future research would be essential to transition from bringing awareness to relevant factors, to defining more recommendations and appropriate solutions. ...
As a dutch-based company with a diverse portfolio of robot solutions, Lely thrives to bring dairy farming to the future. They cover many tasks assisting farmers and cows in barns worldwide. These increasingly capable entities are no longer tools but partners so we must take the next step into carefully designing our coexistence and collaboration with these robotic systems.
After extensive literature on Human-Robot Interaction (HRI) and research activities with a variety of stakeholders, I developed a Robot Code of Conduct. This code guides developers into designing robotic systems delivering pleasurable, fitting and cohesive interactions. It provides intermediate-level knowledge on robot behavioural design by carrying the reader through three sets of guidelines differing in abstraction and actionability.
This project contributes to the field of HRI while spreading awareness of its relevance in practice. The document contains many influential factors that are applied and tailored to designing automated solutions in dairy farming. This document sets a direction and gives concrete guidelines to steer the development of the portfolio towards a vision where all Lely systems work and communicate desirably. Where they communicate as one. I obtained positive results from assessing the content and direction of this document with developers and farmers, however, further tests would be necessary for a more precise validation of this Robot Code of Conduct. Future research would be essential to transition from bringing awareness to relevant factors, to defining more recommendations and appropriate solutions. ...
Robot systems are essentially a new species spreading around us, one that we willingly designed and introduced. Neither a natural species nor a mere human artefact. We have limited information about these smart agents. What do they want, what do you need from us, and how can we find a common ground of understanding to enhance each other through collaboration. Lely took a step into exploring these questions.
As a dutch-based company with a diverse portfolio of robot solutions, Lely thrives to bring dairy farming to the future. They cover many tasks assisting farmers and cows in barns worldwide. These increasingly capable entities are no longer tools but partners so we must take the next step into carefully designing our coexistence and collaboration with these robotic systems.
After extensive literature on Human-Robot Interaction (HRI) and research activities with a variety of stakeholders, I developed a Robot Code of Conduct. This code guides developers into designing robotic systems delivering pleasurable, fitting and cohesive interactions. It provides intermediate-level knowledge on robot behavioural design by carrying the reader through three sets of guidelines differing in abstraction and actionability.
This project contributes to the field of HRI while spreading awareness of its relevance in practice. The document contains many influential factors that are applied and tailored to designing automated solutions in dairy farming. This document sets a direction and gives concrete guidelines to steer the development of the portfolio towards a vision where all Lely systems work and communicate desirably. Where they communicate as one. I obtained positive results from assessing the content and direction of this document with developers and farmers, however, further tests would be necessary for a more precise validation of this Robot Code of Conduct. Future research would be essential to transition from bringing awareness to relevant factors, to defining more recommendations and appropriate solutions.
As a dutch-based company with a diverse portfolio of robot solutions, Lely thrives to bring dairy farming to the future. They cover many tasks assisting farmers and cows in barns worldwide. These increasingly capable entities are no longer tools but partners so we must take the next step into carefully designing our coexistence and collaboration with these robotic systems.
After extensive literature on Human-Robot Interaction (HRI) and research activities with a variety of stakeholders, I developed a Robot Code of Conduct. This code guides developers into designing robotic systems delivering pleasurable, fitting and cohesive interactions. It provides intermediate-level knowledge on robot behavioural design by carrying the reader through three sets of guidelines differing in abstraction and actionability.
This project contributes to the field of HRI while spreading awareness of its relevance in practice. The document contains many influential factors that are applied and tailored to designing automated solutions in dairy farming. This document sets a direction and gives concrete guidelines to steer the development of the portfolio towards a vision where all Lely systems work and communicate desirably. Where they communicate as one. I obtained positive results from assessing the content and direction of this document with developers and farmers, however, further tests would be necessary for a more precise validation of this Robot Code of Conduct. Future research would be essential to transition from bringing awareness to relevant factors, to defining more recommendations and appropriate solutions.