Human intention detection with hand motion prediction is critical to drive the upper-extremity assistive robots in neurorehabilitation applications. However, the traditional methods relying on physiological signal measurement are restrictive and often lack environmental context. We propose a novel approach that predicts future sequences of both hand poses and joint positions. This method integrates gaze information, historical hand motion sequences, and environmental object data, adapting dynamically to the assistive needs of the patient without prior knowledge of the intended object for grasping. Specifically, we use a vector-quantized variational autoencoder for robust hand pose encoding with an autoregressive generative transformer for effective hand motion sequence prediction. We demonstrate the usability of these novel techniques in a pilot study with healthy subjects. To train and evaluate the proposed method, we collect a dataset consisting of various types of grasp actions on different objects from multiple subjects. Through extensive experiments, we demonstrate that the proposed method can successfully predict sequential hand movement. Especially, the gaze information shows significant enhancements in prediction capabilities, particularly with fewer input frames, highlighting the potential of the proposed method for real-world applications.

Haptic interaction is critical in physical human–robot Interaction (pHRI), given its wide applications in manufacturing, medical and healthcare, and various industry tasks. A stable haptic interface is always needed while the human operator interacts with the robot. Passivity-based approaches have been widely utilized in the control design as a sufficient condition for stability. However, it is a conservative approach which therefore sacrifices performance to maintain stability. This article proposes a novel concept to characterize an ultimately passive system, which can achieve the boundedness of the energy in the steady-state. A so-called ultimately passive controller (UPC) is then proposed. This algorithm switches the system between a nominal mode for keeping desired performance and a conservative mode when needed to remain stable. An experimental evaluation on two robotic systems, one admittance-based and one impedance-based, demonstrates the potential interest of the proposed framework compared to existing approaches. The results demonstrate the possibility of UPC in finding a more aggressive tradeoff between haptic performance and system stability, while still providing a stability guarantee.

Rehabilitation robots are useful tools to objectively quantify and treat post-stroke impairments. The SCRIPT Passive Orthosis (SPO) is an passively actuated hand orthosis that can be used for interactive therapy at home. In the last year the SPO was used independently by 24 patients in three EU countries. In this paper we report on the technical challenges this has presented and the feedback we were given by therapists and patients. This includes the range-of-motion of the device, the assistive characteristics, the potential for grasp detection, and the user acceptance.

To automatically align exoskeleton axes to human anatomical axes, we propose to decouple the joint rotations from the joint translations. Decoupling can reduce setup times and painful misalignment forces, at the cost of increased mechanical complexity and movement inertia. The decoupling approach was applied to the Dampace and Limpact exoskeletons.