Balancing Efficiency and Comfort in Robot-Assisted Bite Transfer
This work addresses the problem of improving robot-assisted feeding for users in household environments, representing an incremental advance by combining existing heuristics with motion planning.
The paper tackled the challenge of robot-assisted feeding by balancing bite transfer efficiency and user comfort, formalizing them as heuristics for motion planning. Real-robot evaluations showed that optimizing both significantly outperformed fixed-pose methods, with users preferring it over comfort-only approaches.
Robot-assisted feeding in household environments is challenging because it requires robots to generate trajectories that effectively bring food items of varying shapes and sizes into the mouth while making sure the user is comfortable. Our key insight is that in order to solve this challenge, robots must balance the efficiency of feeding a food item with the comfort of each individual bite. We formalize comfort and efficiency as heuristics to incorporate in motion planning. We present an approach based on heuristics-guided bi-directional Rapidly-exploring Random Trees (h-BiRRT) that selects bite transfer trajectories of arbitrary food item geometries and shapes using our developed bite efficiency and comfort heuristics and a learned constraint model. Real-robot evaluations show that optimizing both comfort and efficiency significantly outperforms a fixed-pose based method, and users preferred our method significantly more than that of a method that maximizes only user comfort. Videos and Appendices are found on our website: https://sites.google.com/view/comfortbitetransfer-icra22/home.