DA
D. Aschenbrenner
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>
3 records found
1
Context & Problem
Humans are entering the age of the 4th industrial revolution: improving factories by applying smart sensors, artificial intelligence, and other emerging technologies, such as AGVs: Autonomous Ground Vehicles. these are fully automated driverless vehicles that can transport goods and machinery. The newest generation AGVs moves efficiently and flexibly without guiding rails or fixed paths.
All of these extra ingredients are causing the factory to become more complex and less transparent in the face of high demands for safety and efficiency. Humans and their robotic colleagues are in dire need of enhanced methods for information exchange. Augmented Reality (AR) is an excellent tool to provide this exchange because of its inert ability to curate visual information and untangle complexity. The goal is to improve situation awareness and safety in the factory.
Analysis
The Magna Steyr factory in Graz was visited so to better understand the context. Literature research provided the necessary insights into the state of the art of the smart factory and AGVs as well as the human factors involved.
Design & iteration
To work towards the design of a solution an explorative approach was first adopted by matching different AR methodologies to different roles within the factory. This created a matrix of possible solutions. The following idea was selected: to place a projector on top of the AGV to provide visual cues to the factory worker by projecting the intention of the robot on the factory floor. An iterative approach was then adopted to develop a solution that could be mounted on top of an AGV.
Validation
In order to validate the presumed positive effects of this design, a between-groups study was conducted. A questionnaire research was devised in which a test-group and a control-group were shown videos of an AGV approaching the participant. The test-group videos included projected arrows while the control-group videos included no indication of the direction the AGV would take. Multiple realistic scenarios were tested to measure the response of the participants. Apart from the response of the participants, the experienced task load and situation awareness were also measured.
Results & conclusion
It was concluded that the projection of arrows in front of an AGV improves the perceived safety of workers as well as their assessment of the robot's future actions. Participants that were shown the projected arrows had a far greater chance of executing the desired response toward the robot. Improvement with regards to the situation awareness was measured in some scenarios. Additional research and design opportunities are identified and presented in chapters 12 and 13.
This project proposes a framework for future AR projects in the smart factory environment and also provides insights into the merits of using (spatial) augmented reality to facilitate communication between robots and people in the smart factory. It shows that the use of Spatial Augmented Reality can make factories safer and more efficient, paving the way for more industries to adopt AGV systems and take the next step toward the factory 4.0 paradigm.
...
Context & Problem
Humans are entering the age of the 4th industrial revolution: improving factories by applying smart sensors, artificial intelligence, and other emerging technologies, such as AGVs: Autonomous Ground Vehicles. these are fully automated driverless vehicles that can transport goods and machinery. The newest generation AGVs moves efficiently and flexibly without guiding rails or fixed paths.
All of these extra ingredients are causing the factory to become more complex and less transparent in the face of high demands for safety and efficiency. Humans and their robotic colleagues are in dire need of enhanced methods for information exchange. Augmented Reality (AR) is an excellent tool to provide this exchange because of its inert ability to curate visual information and untangle complexity. The goal is to improve situation awareness and safety in the factory.
Analysis
The Magna Steyr factory in Graz was visited so to better understand the context. Literature research provided the necessary insights into the state of the art of the smart factory and AGVs as well as the human factors involved.
Design & iteration
To work towards the design of a solution an explorative approach was first adopted by matching different AR methodologies to different roles within the factory. This created a matrix of possible solutions. The following idea was selected: to place a projector on top of the AGV to provide visual cues to the factory worker by projecting the intention of the robot on the factory floor. An iterative approach was then adopted to develop a solution that could be mounted on top of an AGV.
Validation
In order to validate the presumed positive effects of this design, a between-groups study was conducted. A questionnaire research was devised in which a test-group and a control-group were shown videos of an AGV approaching the participant. The test-group videos included projected arrows while the control-group videos included no indication of the direction the AGV would take. Multiple realistic scenarios were tested to measure the response of the participants. Apart from the response of the participants, the experienced task load and situation awareness were also measured.
Results & conclusion
It was concluded that the projection of arrows in front of an AGV improves the perceived safety of workers as well as their assessment of the robot's future actions. Participants that were shown the projected arrows had a far greater chance of executing the desired response toward the robot. Improvement with regards to the situation awareness was measured in some scenarios. Additional research and design opportunities are identified and presented in chapters 12 and 13.
This project proposes a framework for future AR projects in the smart factory environment and also provides insights into the merits of using (spatial) augmented reality to facilitate communication between robots and people in the smart factory. It shows that the use of Spatial Augmented Reality can make factories safer and more efficient, paving the way for more industries to adopt AGV systems and take the next step toward the factory 4.0 paradigm.
This project is an exploration of potential applications of Conversational AI Agents (CAIA) for industrial maintenance. Specifically, it involves the scientific validation and development of a CAIA for a promising application: the automatic creation of information-rich maintenance reports by conversing with a technician while they perform industrial maintenance. The choice for this application was based on literature research, (in-situ) context analyses and a review of CAIA frameworks and design guidelines. These revealed that maintenance workers rely heavily on their own experience and intuition when solving problems but mechanisms for capturing and accessing this were non-existent. This knowledge is highly valuable and can represent a significant part of a company’s worth. Furthermore, maintenance technicians reported that the existing reporting mechanisms were a nuisance. Lastly, audits revealed that maintenance reports were frequently incomplete or of poor quality. In turn, CAIAs (Conversational AI Agents), have various affordances that make them well-suited to the context of industrial maintenance. They are (1) hands and gaze-free, (2) highly efficient (faster than writing or typing, facilitate multitasking and they provide faster access to specific information), (3) they can adapt to the skill level of the user and (4) impose a minimal cognitive load.
A between-subjects experiment with 24 participants, which involved changing a bicycle inner tube, was used to test three hypotheses regarding the potential value of the application. All three hypotheses compare using a CAIA for reporting whilst performing maintenance, as opposed to writing the reports on paper afterwards. They posited that using the CAIA would result in (1) reports of higher quality (more information relevant to the understanding of the task), (2) time saving, and (3) a lower perceived workload (NASA TLX). T-tests confirmed that all three hypotheses were true. These results indicate that using a CAIA for live-reporting has a clear value proposition for the industrial maintenance domain. Critically, it demonstrated that it could facilitate the capture of valuable “expert knowledge”. Future research could explore integrating multi-modal information capture (e.g. through smart-glasses), identify additional uses for the captured data (e.g. for prescriptive maintenance or providing tips to maintenance technicians) and improve the functionality and usability of the existing application. A prototype was built using the open-source frameworks, Rasa and Mycroft, to demonstrate the technical feasibility of the functional requirements. These requirements include (1) uttering “continuers” in response to the user describing their work, (2) tracking conversational context, (3) asking for clarifications when there is a lack of mutual understanding and (4) asking for status updates when the user is silent for more than a set amount of time. The main challenges for the future development of the prototype are (1) reducing the response time of the CAIA, (2) the accuracy of the intent classifier and entity extractor and (3) improving the handling of fragmented/lengthy user input. Some of the prototype’s features rely on inflexible, hard-coded logic, therefore, future work should collect more conversational data and explore the use of machine learning algorithms. ...
A between-subjects experiment with 24 participants, which involved changing a bicycle inner tube, was used to test three hypotheses regarding the potential value of the application. All three hypotheses compare using a CAIA for reporting whilst performing maintenance, as opposed to writing the reports on paper afterwards. They posited that using the CAIA would result in (1) reports of higher quality (more information relevant to the understanding of the task), (2) time saving, and (3) a lower perceived workload (NASA TLX). T-tests confirmed that all three hypotheses were true. These results indicate that using a CAIA for live-reporting has a clear value proposition for the industrial maintenance domain. Critically, it demonstrated that it could facilitate the capture of valuable “expert knowledge”. Future research could explore integrating multi-modal information capture (e.g. through smart-glasses), identify additional uses for the captured data (e.g. for prescriptive maintenance or providing tips to maintenance technicians) and improve the functionality and usability of the existing application. A prototype was built using the open-source frameworks, Rasa and Mycroft, to demonstrate the technical feasibility of the functional requirements. These requirements include (1) uttering “continuers” in response to the user describing their work, (2) tracking conversational context, (3) asking for clarifications when there is a lack of mutual understanding and (4) asking for status updates when the user is silent for more than a set amount of time. The main challenges for the future development of the prototype are (1) reducing the response time of the CAIA, (2) the accuracy of the intent classifier and entity extractor and (3) improving the handling of fragmented/lengthy user input. Some of the prototype’s features rely on inflexible, hard-coded logic, therefore, future work should collect more conversational data and explore the use of machine learning algorithms. ...
This project is an exploration of potential applications of Conversational AI Agents (CAIA) for industrial maintenance. Specifically, it involves the scientific validation and development of a CAIA for a promising application: the automatic creation of information-rich maintenance reports by conversing with a technician while they perform industrial maintenance. The choice for this application was based on literature research, (in-situ) context analyses and a review of CAIA frameworks and design guidelines. These revealed that maintenance workers rely heavily on their own experience and intuition when solving problems but mechanisms for capturing and accessing this were non-existent. This knowledge is highly valuable and can represent a significant part of a company’s worth. Furthermore, maintenance technicians reported that the existing reporting mechanisms were a nuisance. Lastly, audits revealed that maintenance reports were frequently incomplete or of poor quality. In turn, CAIAs (Conversational AI Agents), have various affordances that make them well-suited to the context of industrial maintenance. They are (1) hands and gaze-free, (2) highly efficient (faster than writing or typing, facilitate multitasking and they provide faster access to specific information), (3) they can adapt to the skill level of the user and (4) impose a minimal cognitive load.
A between-subjects experiment with 24 participants, which involved changing a bicycle inner tube, was used to test three hypotheses regarding the potential value of the application. All three hypotheses compare using a CAIA for reporting whilst performing maintenance, as opposed to writing the reports on paper afterwards. They posited that using the CAIA would result in (1) reports of higher quality (more information relevant to the understanding of the task), (2) time saving, and (3) a lower perceived workload (NASA TLX). T-tests confirmed that all three hypotheses were true. These results indicate that using a CAIA for live-reporting has a clear value proposition for the industrial maintenance domain. Critically, it demonstrated that it could facilitate the capture of valuable “expert knowledge”. Future research could explore integrating multi-modal information capture (e.g. through smart-glasses), identify additional uses for the captured data (e.g. for prescriptive maintenance or providing tips to maintenance technicians) and improve the functionality and usability of the existing application. A prototype was built using the open-source frameworks, Rasa and Mycroft, to demonstrate the technical feasibility of the functional requirements. These requirements include (1) uttering “continuers” in response to the user describing their work, (2) tracking conversational context, (3) asking for clarifications when there is a lack of mutual understanding and (4) asking for status updates when the user is silent for more than a set amount of time. The main challenges for the future development of the prototype are (1) reducing the response time of the CAIA, (2) the accuracy of the intent classifier and entity extractor and (3) improving the handling of fragmented/lengthy user input. Some of the prototype’s features rely on inflexible, hard-coded logic, therefore, future work should collect more conversational data and explore the use of machine learning algorithms.
A between-subjects experiment with 24 participants, which involved changing a bicycle inner tube, was used to test three hypotheses regarding the potential value of the application. All three hypotheses compare using a CAIA for reporting whilst performing maintenance, as opposed to writing the reports on paper afterwards. They posited that using the CAIA would result in (1) reports of higher quality (more information relevant to the understanding of the task), (2) time saving, and (3) a lower perceived workload (NASA TLX). T-tests confirmed that all three hypotheses were true. These results indicate that using a CAIA for live-reporting has a clear value proposition for the industrial maintenance domain. Critically, it demonstrated that it could facilitate the capture of valuable “expert knowledge”. Future research could explore integrating multi-modal information capture (e.g. through smart-glasses), identify additional uses for the captured data (e.g. for prescriptive maintenance or providing tips to maintenance technicians) and improve the functionality and usability of the existing application. A prototype was built using the open-source frameworks, Rasa and Mycroft, to demonstrate the technical feasibility of the functional requirements. These requirements include (1) uttering “continuers” in response to the user describing their work, (2) tracking conversational context, (3) asking for clarifications when there is a lack of mutual understanding and (4) asking for status updates when the user is silent for more than a set amount of time. The main challenges for the future development of the prototype are (1) reducing the response time of the CAIA, (2) the accuracy of the intent classifier and entity extractor and (3) improving the handling of fragmented/lengthy user input. Some of the prototype’s features rely on inflexible, hard-coded logic, therefore, future work should collect more conversational data and explore the use of machine learning algorithms.
The worldwide company named Royal IHC proposed this graduation project. Royal IHC is a reliable supplier of dredge vessels. Trailing suction hopper dredger (TSHD) is one of the company’s main products for port maintenance. A dredge operator is doing all the dredge control task in the dredge operator cockpit. The human-machine interface (HMI) of the dredge operator cockpit is developed on a perpetual basis. The system become more and more complex. Therefore, novice operators need to spend longer time in training in order to be fully efficient. The latest interface technology augmented reality has attracted attention. Royal IHC is interested in head-mounted devices, especially HoloLens. Royal IHC sees the potential of HoloLens in terms of supporting the control tasks of dredge operators, but this assumption still needs to be proven by operational research. Therefore, the essence of this project is an explorative study, which is targeted to discover if there are possibilities of HoloLens to support dredge control work of novice operators. After technology research and user research, some tasks are selected and concpets are created.The core of the concepts is to extract this information and provide it in a more user-friendly way. The operator can then directly see the essential information through the HoloLens and will not be disturbed by other information, which is not relevant at the moment. The operator does not need to switch attention between screens and real world either. However, there are two different perspective for this concept: the first person’s perspective and the third person’s perspective.The concepts were tested with IHC employees and students. It is found that: Compared with the current system, HoloLens applications can give the information in a more straightforward way. Compared with the current system, simplified signals with its spatial property in HoloLens applications are easier to understand. Thus, compared with the current system, HoloLens applications require less workload. With the third person’s perspective, operators could have a more transparent overview of the situation than with the first person’s perspective. It is more easily for novice operators to learn the use of HoloLens applications than people without any dredge knowledge.
...
The worldwide company named Royal IHC proposed this graduation project. Royal IHC is a reliable supplier of dredge vessels. Trailing suction hopper dredger (TSHD) is one of the company’s main products for port maintenance. A dredge operator is doing all the dredge control task in the dredge operator cockpit. The human-machine interface (HMI) of the dredge operator cockpit is developed on a perpetual basis. The system become more and more complex. Therefore, novice operators need to spend longer time in training in order to be fully efficient. The latest interface technology augmented reality has attracted attention. Royal IHC is interested in head-mounted devices, especially HoloLens. Royal IHC sees the potential of HoloLens in terms of supporting the control tasks of dredge operators, but this assumption still needs to be proven by operational research. Therefore, the essence of this project is an explorative study, which is targeted to discover if there are possibilities of HoloLens to support dredge control work of novice operators. After technology research and user research, some tasks are selected and concpets are created.The core of the concepts is to extract this information and provide it in a more user-friendly way. The operator can then directly see the essential information through the HoloLens and will not be disturbed by other information, which is not relevant at the moment. The operator does not need to switch attention between screens and real world either. However, there are two different perspective for this concept: the first person’s perspective and the third person’s perspective.The concepts were tested with IHC employees and students. It is found that: Compared with the current system, HoloLens applications can give the information in a more straightforward way. Compared with the current system, simplified signals with its spatial property in HoloLens applications are easier to understand. Thus, compared with the current system, HoloLens applications require less workload. With the third person’s perspective, operators could have a more transparent overview of the situation than with the first person’s perspective. It is more easily for novice operators to learn the use of HoloLens applications than people without any dredge knowledge.