Improving User Experience in Preference-Based Optimization of Reward Functions for Assistive Robots
This work addresses the challenge of improving user experience in preference learning for assistive robots, representing an incremental advancement over existing methods.
The paper tackled the problem of assistive robots not reflecting user preferences over repeated interactions by developing CMA-ES-IG, an algorithm that prioritizes user experience in generating trajectories for ranking. The result showed that users found CMA-ES-IG more intuitive and easier to use than previous approaches across physical and social robot tasks.
Assistive robots interact with humans and must adapt to different users' preferences to be effective. An easy and effective technique to learn non-expert users' preferences is through rankings of robot behaviors, for example, robot movement trajectories or gestures. Existing techniques focus on generating trajectories for users to rank that maximize the outcome of the preference learning process. However, the generated trajectories do not appear to reflect the user's preference over repeated interactions. In this work, we design an algorithm to generate trajectories for users to rank that we call Covariance Matrix Adaptation Evolution Strategies with Information Gain (CMA-ES-IG). CMA-ES-IG prioritizes the user's experience of the preference learning process. We show that users find our algorithm more intuitive and easier to use than previous approaches across both physical and social robot tasks. This project's code is hosted at github.com/interaction-lab/CMA-ES-IG