Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies

TL;DR

This paper introduces a Bayesian variational inference framework for imitation learning that learns flexible multi-action policies and enhances robustness by incorporating disturbances, improving generalization and safety in robotic tasks.

Contribution

It presents the first Bayesian non-parametric imitation learning method that combines policy flexibility with robustness through disturbance injection.

Findings

Improved policy flexibility and robustness in simulations and real robot experiments.

Enhanced learning performance and control safety over comparison methods.

Effective handling of multi-action decision scenarios in robotic manipulation.

Abstract

Scenarios requiring humans to choose from multiple seemingly optimal actions are commonplace, however standard imitation learning often fails to capture this behavior. Instead, an over-reliance on replicating expert actions induces inflexible and unstable policies, leading to poor generalizability in an application. To address the problem, this paper presents the first imitation learning framework that incorporates Bayesian variational inference for learning flexible non-parametric multi-action policies, while simultaneously robustifying the policies against sources of error, by introducing and optimizing disturbances to create a richer demonstration dataset. This combinatorial approach forces the policy to adapt to challenging situations, enabling stable multi-action policies to be learned efficiently. The effectiveness of our proposed method is evaluated through simulations and real-robot experiments for a table-sweep task using the UR3 6-DOF robotic arm. Results show that, through improved flexibility and robustness, the learning performance and control safety are better than comparison methods.