Upper-limb robots better adapt to user intent and strength changes
Attribution-Gated Joint Estimation of Intention and Capability for Assist-as-Needed Upper-Limb Robots
Robotics
Summary
Helping robots better support people moving their arms can be tricky because it's hard to tell if a person wants to move differently or just can't apply as much force. The authors created a method that separately estimates both what a person intends to do and how much strength they currently have, so the robot can assist more accurately. They tested this with volunteers doing arm tasks, including when they were tired, and found the robot adjusted its help in sensible ways.
What this means in practice
- •For rehabilitation therapists: Use robotic assistance that adjusts separately to patient intent and muscle fatigue during upper-limb exercises to improve therapy effectiveness.
- •For industrial robot integrators: Implement arm-assist robots that distinguish operator movement intention from strength changes to provide safer, adaptive support in manual tasks.
Authors
Pengcheng Li, Shuxiang Guo, Hanze Wang, Jun Leng, Bin Wang, Mingchao Ding
Abstract
Assist-as-needed (AAN) control must distinguish between changes in intended motion and changes in effective voluntary torque capability, even though both can produce similar kinematic and interaction responses. A dual-measurand multimodal MHE-MPC architecture is developed as the base framework, in which the intended trajectory and the task-dependent effective voluntary torque capability are estimated online as distinct quantities, and both estimates are used to adapt robotic assistance. Building on this architecture, the ambiguity between the two update channels is formulated as a continuous credit-assignment problem and resolved by an attribution gate. A trajectory-change indicator is obtained from persistent corrective interaction, whereas a capability-change indicator is derived from the residual between normalized muscle activation and dynamics-reconstructed voluntary torque. Nine healthy participants completed factorial target-height-load trials and a pre-post fatigue cup-transport task. Without target-height input, the gated method generated correctly ordered Low-Middle-High references under every load: target changes were preferentially assigned to trajectory adaptation, whereas added load shifted adaptation toward the capability channel. It achieved the lowest RMSE in all nine conditions (0.017 rad versus 0.041 rad for ungated dual estimation and 0.127 rad for fixed-reference error-based AAN). Post-fatigue capability estimates decreased and assistance increased at all heights, supporting functional feasibility.