← Back to Benchmarks
simmediumquadrupedmetric · varies
Safety-Aware Imitation Learning via MPC-Guided Disturbance Injection
Description
Imitation Learning has provided a promising approach to learning complex robot behaviors from expert demonstrations. However, learned policies can make errors that lead to safety violations, which limits their deployment in safety-critical applications. We propose MPC-SafeGIL, a design-time approach that enhances the safety of imitation learning by injecting adversarial disturbances during expert demonstrations. This exposes the expert to a broader range of safety-critical scenarios and allows t