Residual Policy Learning for Shared Autonomy
This work addresses the challenge of human-robot collaboration in continuous control settings with minimal assumptions about goals or dynamics, offering a practical solution for real-world applications.
The paper tackled the problem of scaling shared autonomy to complex real-world environments by proposing a model-free residual policy learning algorithm that minimally adjusts human actions to satisfy goal-agnostic constraints, resulting in significant performance improvements in continuous control tasks like Lunar Lander and a 6-DOF quadrotor.
Shared autonomy provides an effective framework for human-robot collaboration that takes advantage of the complementary strengths of humans and robots to achieve common goals. Many existing approaches to shared autonomy make restrictive assumptions that the goal space, environment dynamics, or human policy are known a priori, or are limited to discrete action spaces, preventing those methods from scaling to complicated real world environments. We propose a model-free, residual policy learning algorithm for shared autonomy that alleviates the need for these assumptions. Our agents are trained to minimally adjust the human's actions such that a set of goal-agnostic constraints are satisfied. We test our method in two continuous control environments: Lunar Lander, a 2D flight control domain, and a 6-DOF quadrotor reaching task. In experiments with human and surrogate pilots, our method significantly improves task performance without any knowledge of the human's goal beyond the constraints. These results highlight the ability of model-free deep reinforcement learning to realize assistive agents suited to continuous control settings with little knowledge of user intent.