Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies for Robot Manipulation

TL;DR

This paper introduces Bayesian Disturbance Injection, a novel imitation learning framework that captures human-like behavioral variability, improves robustness, and enhances demonstration feasibility for robot manipulation tasks.

Contribution

It presents the first imitation learning method incorporating human behavioral characteristics through Bayesian inference and disturbance injection for flexible, robust policies.

Findings

Enhanced task performance in simulations and real robot experiments.

Improved flexibility and robustness of learned policies.

Increased demonstration feasibility for complex manipulation tasks.

Abstract

Humans demonstrate a variety of interesting behavioral characteristics when performing tasks, such as selecting between seemingly equivalent optimal actions, performing recovery actions when deviating from the optimal trajectory, or moderating actions in response to sensed risks. However, imitation learning, which attempts to teach robots to perform these same tasks from observations of human demonstrations, often fails to capture such behavior. Specifically, commonly used learning algorithms embody inherent contradictions between the learning assumptions (e.g., single optimal action) and actual human behavior (e.g., multiple optimal actions), thereby limiting robot generalizability, applicability, and demonstration feasibility. To address this, this paper proposes designing imitation learning algorithms with a focus on utilizing human behavioral characteristics, thereby embodying principles for capturing and exploiting actual demonstrator behavioral characteristics. This paper presents the first imitation learning framework, Bayesian Disturbance Injection (BDI), that typifies human behavioral characteristics by incorporating model flexibility, robustification, and risk sensitivity. Bayesian inference is used to learn flexible non-parametric multi-action policies, while simultaneously robustifying policies by injecting risk-sensitive disturbances to induce human recovery action and ensuring demonstration feasibility. Our method is evaluated through risk-sensitive simulations and real-robot experiments (e.g., table-sweep task, shaft-reach task and shaft-insertion task) using the UR5e 6-DOF robotic arm, to demonstrate the improved characterisation of behavior. Results show significant improvement in task performance, through improved flexibility, robustness as well as demonstration feasibility.