CRIL: Continual Robot Imitation Learning via Generative and Prediction Model
This addresses the challenge of reducing the burden of multi-task imitation learning for robots in real-world applications, though it appears incremental as it builds on existing imitation learning techniques.
The paper tackles the problem of robots needing to learn multiple tasks sequentially without forgetting previous ones, proposing a method that generates pseudo trajectories from learned tasks to enable continual imitation learning, achieving effective results in both simulation and real-world manipulation tasks.
Imitation learning (IL) algorithms have shown promising results for robots to learn skills from expert demonstrations. However, they need multi-task demonstrations to be provided at once for acquiring diverse skills, which is difficult in real world. In this work we study how to realize continual imitation learning ability that empowers robots to continually learn new tasks one by one, thus reducing the burden of multi-task IL and accelerating the process of new task learning at the same time. We propose a novel trajectory generation model that employs both a generative adversarial network and a dynamics-aware prediction model to generate pseudo trajectories from all learned tasks in the new task learning process. Our experiments on both simulation and real-world manipulation tasks demonstrate the effectiveness of our method.