E. ShahabiShalghouni
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>
5 records found
1
Soft climbing robots are promising for inspection tasks in hazardous pipe-like and truss-like environments, as their compliant limbs can adapt well to unforeseen obstacles. However, their deformable and underactuated bodies make contact difficult to control, particularly when contact information is not available. This paper presents TETRASCEND, a four-limbed tendon-driven soft climbing robot with distributed tactile sensing embedded in its arms. Each sensorized arm contains eight force-sensing resistors positioned along the gripping surface, allowing contact location and load distribution to be estimated during grasping and climbing. The sensors were first characterized through loading and unloading experiments, showing repeatable but nonlinear behavior suitable for relative pressure estimation after normalization. A single-arm climbing setup was then used to evaluate grasping across different pipe positions: the center of pressure shifted consistently along the arm as the pipe distance increased, and failure events could be detected by the tactile sensors. Combining tactile sensing with tendon displacement further allowed real pipe contact to be distinguished from free-space arm curling. Finally, the complete robot was validated in a truss-like climbing cage, where the tactile sensors captured sequential contact events during repeated cycles of a climbing gait. These results demonstrate that distributed tactile sensing provides useful information about contact state, grip location, and anchoring stability. Therefore, the TETRASCEND platform is a step toward contact-aware autonomous soft climbing robots
...
Soft climbing robots are promising for inspection tasks in hazardous pipe-like and truss-like environments, as their compliant limbs can adapt well to unforeseen obstacles. However, their deformable and underactuated bodies make contact difficult to control, particularly when contact information is not available. This paper presents TETRASCEND, a four-limbed tendon-driven soft climbing robot with distributed tactile sensing embedded in its arms. Each sensorized arm contains eight force-sensing resistors positioned along the gripping surface, allowing contact location and load distribution to be estimated during grasping and climbing. The sensors were first characterized through loading and unloading experiments, showing repeatable but nonlinear behavior suitable for relative pressure estimation after normalization. A single-arm climbing setup was then used to evaluate grasping across different pipe positions: the center of pressure shifted consistently along the arm as the pipe distance increased, and failure events could be detected by the tactile sensors. Combining tactile sensing with tendon displacement further allowed real pipe contact to be distinguished from free-space arm curling. Finally, the complete robot was validated in a truss-like climbing cage, where the tactile sensors captured sequential contact events during repeated cycles of a climbing gait. These results demonstrate that distributed tactile sensing provides useful information about contact state, grip location, and anchoring stability. Therefore, the TETRASCEND platform is a step toward contact-aware autonomous soft climbing robots
Rising environmental pressures in aquatic ecosystems due to climate change require robotic systems capable of safe and non-invasive operation. Conventional underwater robots are typically rigid and rely on noisy, high-power actuators, limiting their suitability for sensitive environments such as coral reefs, seagrass meadows, and freshwater lakes and rivers. Here, we present an octopus-inspired robot integrating a hybrid rigid-soft body with compliant tentacle actuation and closed-loop navigation control. Central to the design is an experimental characterization of the actuator force–angle relationship, which enables a model-based feedforward strategy that exploits a locally linear operating regime, avoiding the computational burden of full nonlinear modeling. This feedforward component is combined with proportional–derivative (PD) feedback control to reject disturbances and compensate for model mismatch. The robot achieves an average forward velocity of 0.072 m/s under open-loop operation. Turning experiments show that maneuverability is governed by torque generation, achieving a minimum turning radius of 0.221 m using two-arm actuation. Closed-loop target tracking demonstrates robust navigation under disturbances through integrated vision- and inertial-based state estimation and task-level actuation allocation. Together, these results demonstrate that bio-inspired morphology combined with experimentally grounded hybrid control can yield efficient, adaptive platforms for underwater operation in ecologically sensitive environments.
...
...
Rising environmental pressures in aquatic ecosystems due to climate change require robotic systems capable of safe and non-invasive operation. Conventional underwater robots are typically rigid and rely on noisy, high-power actuators, limiting their suitability for sensitive environments such as coral reefs, seagrass meadows, and freshwater lakes and rivers. Here, we present an octopus-inspired robot integrating a hybrid rigid-soft body with compliant tentacle actuation and closed-loop navigation control. Central to the design is an experimental characterization of the actuator force–angle relationship, which enables a model-based feedforward strategy that exploits a locally linear operating regime, avoiding the computational burden of full nonlinear modeling. This feedforward component is combined with proportional–derivative (PD) feedback control to reject disturbances and compensate for model mismatch. The robot achieves an average forward velocity of 0.072 m/s under open-loop operation. Turning experiments show that maneuverability is governed by torque generation, achieving a minimum turning radius of 0.221 m using two-arm actuation. Closed-loop target tracking demonstrates robust navigation under disturbances through integrated vision- and inertial-based state estimation and task-level actuation allocation. Together, these results demonstrate that bio-inspired morphology combined with experimentally grounded hybrid control can yield efficient, adaptive platforms for underwater operation in ecologically sensitive environments.
Continuum soft manipulators (CSMs) offer key advantages over rigid robots for on-orbit servicing (OOS), but their deployment requires realistic ground-based testing environments. To emulate microgravity conditions for CSMs, this paper proposes tendon antagonism as a model based gravity compensation method. It is shown that a tendon layout design consisting of one linear tendon and two tendons shaped as five-segment piecewise-linear approximations of sinusoids is sufficient to counteract planar bending moment by gravitational loading. Dynamic simulations compare a gravity-loaded plant model, a gravity free reference model, and an uncompensated baseline using a geometric variable strain formulation. Results show accurate tracking on bending DOFs with negligible (10−5 rad/m) tracking errors in steady-state conditions and remain small during motion (10−2 rad/m), increasing moderately at higher actuation levels. Small errors in task space (18 mm) stem from uncontrolled elongation DOF, as tendon actuation is limited to tension only. The design is further validated experimentally, using machine vision for pose estimation. Results show high accuracy of the simulation, and demonstrate that tendon antagonism reduces gravitational sagging and enables tracking of the reference configuration across actuation values. Average positional error reduces by 80%, from 103 mm to 18 mm when using the compensation mechanism. At high actuation values, results show overcompensation for the gravity load, hinting to possible improvements in the tendon control scheme. Future research could implement real-time control or control of the remaining free DOFs.
...
Continuum soft manipulators (CSMs) offer key advantages over rigid robots for on-orbit servicing (OOS), but their deployment requires realistic ground-based testing environments. To emulate microgravity conditions for CSMs, this paper proposes tendon antagonism as a model based gravity compensation method. It is shown that a tendon layout design consisting of one linear tendon and two tendons shaped as five-segment piecewise-linear approximations of sinusoids is sufficient to counteract planar bending moment by gravitational loading. Dynamic simulations compare a gravity-loaded plant model, a gravity free reference model, and an uncompensated baseline using a geometric variable strain formulation. Results show accurate tracking on bending DOFs with negligible (10−5 rad/m) tracking errors in steady-state conditions and remain small during motion (10−2 rad/m), increasing moderately at higher actuation levels. Small errors in task space (18 mm) stem from uncontrolled elongation DOF, as tendon actuation is limited to tension only. The design is further validated experimentally, using machine vision for pose estimation. Results show high accuracy of the simulation, and demonstrate that tendon antagonism reduces gravitational sagging and enables tracking of the reference configuration across actuation values. Average positional error reduces by 80%, from 103 mm to 18 mm when using the compensation mechanism. At high actuation values, results show overcompensation for the gravity load, hinting to possible improvements in the tendon control scheme. Future research could implement real-time control or control of the remaining free DOFs.
This paper presents a robotic grasping system that integrates soft robotic fingers, a reconfigurable gripper, and a YOLOv11-OBB-based object detection to enable intelligent adaptive, grasping. The system addresses the challenge of handling fragile and geometrically diverse objects common in agricultural and food-handling applications by dynamically adjusting its gripper configuration in response to object characteristics. A novel soft finger, selected through finite element modeling and experimental validation, provides compliant contact. The object detection model not only localizes and orients objects but also infers the optimal finger configuration, encoded via class ID. Experimental results demonstrate significant performance improvements: grasp success rates increased from 70% to 84,67% for fruits and from 66% to 84,67% for abstract objects, with only a modest 3-second increase in cycle time due to reconfiguration.
...
This paper presents a robotic grasping system that integrates soft robotic fingers, a reconfigurable gripper, and a YOLOv11-OBB-based object detection to enable intelligent adaptive, grasping. The system addresses the challenge of handling fragile and geometrically diverse objects common in agricultural and food-handling applications by dynamically adjusting its gripper configuration in response to object characteristics. A novel soft finger, selected through finite element modeling and experimental validation, provides compliant contact. The object detection model not only localizes and orients objects but also infers the optimal finger configuration, encoded via class ID. Experimental results demonstrate significant performance improvements: grasp success rates increased from 70% to 84,67% for fruits and from 66% to 84,67% for abstract objects, with only a modest 3-second increase in cycle time due to reconfiguration.
Master thesis
(2025)
-
S.P.W. de Kam, C. Della Santina, E. ShahabiShalghouni, J. Kober, D. Farhadi Machekposhti
This thesis presents the design and control of the TActile Soft Quadruped (TASQ), a pneumatically actuated soft robot equipped with integrated tactile sensing for adaptive locomotion. Two core contributions are introduced. First, a novel tactile suction cup sensor is developed, capable of simultaneously providing foot contact information and generating suction-based adhesion. The sensor combines embedded magnets and magnetometers to estimate ground reaction forces via a learned calibration model, enabling lightweight, compliant, and robust tactile feedback essential for closed-loop control in soft robotics. Second, a learning-based control framework is proposed that integrates behavior cloning with domain-randomized reinforcement learning to achieve adaptive and robust locomotion. The approach first imitates a reference gait to initialize a stable walking policy and then refines it in simulation using the Soft Actor–Critic algorithm. The learned policy exploits proprioceptive and tactile feedback to enable goal-directed, stable motion and transfers effectively from simulation to real hardware. Experimental validation demonstrates that the learned closed-loop controller outperforms open-loop control on the physical robot, improving forward speed by 41\% on flat terrain and by 91\% on a $2.5^{\circ}$ incline. Ablation studies further confirm the importance of tactile and inertial feedback for stability and performance. Overall, this work establishes a unified sensing and learning framework for a soft legged robot, paving the way toward adaptive, environment-aware locomotion without reliance on vision.
...
This thesis presents the design and control of the TActile Soft Quadruped (TASQ), a pneumatically actuated soft robot equipped with integrated tactile sensing for adaptive locomotion. Two core contributions are introduced. First, a novel tactile suction cup sensor is developed, capable of simultaneously providing foot contact information and generating suction-based adhesion. The sensor combines embedded magnets and magnetometers to estimate ground reaction forces via a learned calibration model, enabling lightweight, compliant, and robust tactile feedback essential for closed-loop control in soft robotics. Second, a learning-based control framework is proposed that integrates behavior cloning with domain-randomized reinforcement learning to achieve adaptive and robust locomotion. The approach first imitates a reference gait to initialize a stable walking policy and then refines it in simulation using the Soft Actor–Critic algorithm. The learned policy exploits proprioceptive and tactile feedback to enable goal-directed, stable motion and transfers effectively from simulation to real hardware. Experimental validation demonstrates that the learned closed-loop controller outperforms open-loop control on the physical robot, improving forward speed by 41\% on flat terrain and by 91\% on a $2.5^{\circ}$ incline. Ablation studies further confirm the importance of tactile and inertial feedback for stability and performance. Overall, this work establishes a unified sensing and learning framework for a soft legged robot, paving the way toward adaptive, environment-aware locomotion without reliance on vision.