Distributionally Robust and Safe Imitation Learning
Provides a unified approach to safe imitation learning under distribution shifts for safety-critical autonomous systems like UAVs.
Imitation learning suffers from distribution shifts that cause safety risks. The authors propose a framework combining Taylor Series Imitation Learning and distributionally robust control to handle both policy- and uncertainty-induced shifts, demonstrating effectiveness on a UAV task with safety constraints.
Imitation learning (IL) has achieved remarkable success in complex decision-making tasks. However, its performance is highly sensitive to distribution shifts, which can pose significant safety risks. We propose a distributionally robust and safe IL framework that explicitly addresses both policy-induced and uncertainty-induced distribution shifts. Our approach develops a unified framework leveraging Taylor Series Imitation Learning (TaSIL) to mitigate policy-induced shifts and distributionally robust adaptive control to handle uncertainty-induced shifts. This architecture enables the formulation of an IL problem that optimizes performance under distributional uncertainty while systematically accounting for safety constraints. We demonstrate the effectiveness of the proposed approach on an unmanned aerial vehicle (UAV) case study where the UAV performs a task in an uncertain environment while avoiding unsafe regions.