5 accepted papers
Planning contact-rich interactions for multi-finger manipulation is challenging due to the high-dimensionality and hybrid nature of dynamics. Recent advances in data-driven methods have shown promise, but are sensitive to the quality of training data. Combining learning with classical methods like t
Parameterizing finger rolling and finger-object contacts in a differentiable manner is important for formulating dexterous manipulation as a trajectory optimization problem. In contrast to previous methods which often assume simplified geometries of the robot and object or do not explicitly model fi
Robots that can physically interact with humans in a safe manner have the potential to revolutionize application domains like home assistance and nursing care. However, to become long-term companions, such robots must learn user-specific preferences and adapt their behaviors in real time. We propose
Algorithms used for controlling upper limb rehabilitation exoskeletons need to promote active participation of patients in the training while preventing incorrect hand motion and arm posture. Any such framework should also be systematically customizable for individual users. Our work is motivated by
This letter presents the electromechanical design, system architecture, baseline control development, and the preliminary evaluation of a novel upper-limb exoskeleton, named CLEVERarm. The developed system can support the motions of inner shoulder, glenohumeral joint, elbow and wrist’s pronation/sup