A Soft-Rigid Hybrid Robot-Assisted Feeding System with a Tendon-Driven Continuum Robot
Jingyi Chen, Quecheng Qiu, Jianmin Ji
AI summary
Problem
Existing robot-assisted feeding systems struggle to balance the speed and accuracy of rigid manipulators with the safety and compliance of soft robots, while controlling soft robots for food acquisition remains difficult due to complex interactions and discontinuous imitation learning outputs.
Approach
The authors pair a fast 6-DoF rigid arm with a compliant, tendon-driven continuum robot to balance safety and reach, and train a hybrid pose-torque imitation learning policy on human demonstrations to synchronize their movements for smooth food acquisition.
Key results
- Novel soft-rigid hybrid RAFS architecture balancing speed, reach, and passive safety
- Pose-torque imitation learning framework enabling continuous, synchronized control
- 76.7% food acquisition success rate in real-world trials
- Strong user preference over traditional rigid-only systems in volunteer tests
Why it matters
Provides a practical, safe, and efficient robotic feeding solution for assisted living, advancing the application of soft robotics and imitation learning in human-robot interaction.
Abstract
Active delivery of food to a human mouth in a controlled and safe manner remains a key challenge for robot-assisted feeding systems (RAFSs). Existing RAFS designs struggle to simultaneously achieve efficiency and safety: rigid manipulators offer fast and accurate motion but risk hazardous contact, while soft robots provide passive compliance at the cost of limited speed or workspace. To meet the specific demands of feeding tasks, we design a tendon-driven continuum robot that allows precise orientation control of the utensil while exhibiting strong passive compliance in position. Integrating it with a 6- DoF rigid robot for fast and long-range positioning, we propose a hybrid RAFS architecture that achieves safe, efficient, and accurate food delivery. Controlling a passive-compliant RAFS to acquire various food is non-trivial: physical modeling struggles with complex interactions between soft robot and food, while typical imitation learning methods lead to discontinuous or distorted movements out of the passive deformation. To handle this, we design a pose-torque learning policy that enables the soft and rigid robots to generate coherent and synchronized movements, offering a case-specific solution to the long-standing challenge of soft robot imitation learning. Experiments show that our method achieve a food acquisition success rate of 76.7%, while user tests with 14 volunteers confirm user preference, marking our RAFS as a practical step toward safe and efficient robotic feeding.