Assistive robot arms can help to provide care for those with disabilities. A recent paper on arXiv.org looks into robot-assisted feeding. A bite transfer strategy must optimize its trajectories on the fly by bringing food into a mouth without sacrificing user comfort.
In order to achieve that, the researchers present a bite transfer algorithm for selecting trajectories in a continuous space of mouth sizes, food geometries, and poses. The approach takes as input a food mesh and an acquisition pose on the fork from the real world and generates an analogous simulation environment. A constraint model is learned to sample goal food poses near the mouth. Motion planning is performed to shape the perceived comfort and bite volume efficiency of each transfer.
A user study shows that the proposed approach of blending comfort and efficiency is the only method to outperform a fixed pose baseline with statistical significance.
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: this https URL.
Research paper: Belkhale, S., Gordon, E. K., Chen, Y., Srinivasa, S., Bhattacharjee, T., and Sadigh, D., “Balancing Efficiency and Comfort in Robot-Assisted Bite Transfer”, 2021. Link: https://arxiv.org/abs/2111.11401