Shengfan Cao

Yuxiang Liu, Shengfan Cao

We study visual domain transfer for end-to-end imitation learning in a realistic and challenging setting where target-domain data are strictly off-policy, expert-free, and scarce. We first provide a theoretical analysis showing that the target-domain imitation loss can be upper bounded by the source-domain loss plus a state-conditional latent KL divergence between source and target observation models. Guided by this result, we propose State- Conditional Adversarial Learning, an off-policy adversarial framework that aligns latent distributions conditioned on system state using a discriminator-based estimator of the conditional KL term. Experiments on visually diverse autonomous driving environments built on the BARC-CARLA simulator demonstrate that SCAL achieves robust transfer and strong sample efficiency.

Shengfan Cao, Francesco Borrelli

Safety-critical learning requires policies that improve performance without leaving the safe operating regime. We study constrained policy learning where model parameters must satisfy unknown, rollout-based safety constraints. We propose SCPO, a sampling-based weight-space projection method that enforces safety directly in parameter space without requiring gradient access to the constraint functions. Our approach constructs a local safe region by combining trajectory rollouts with smoothness bounds that relate parameter changes to shifts in safety metrics. Each gradient update is then projected via a convex SOCP, producing a safe first-order step. We establish a safe-by-induction guarantee: starting from any safe initialization, all intermediate policies remain safe given feasible projections. In constrained control settings with a stabilizing backup policy, our approach further ensures closed-loop stability and enables safe adaptation beyond the conservative backup. On regression with harmful supervision and a constrained double-integrator task with malicious expert, our approach consistently rejects unsafe updates, maintains feasibility throughout training, and achieves meaningful primal objective improvement.

Shengfan Cao, Eunhyek Joa, Francesco Borrelli

Guaranteeing constraint satisfaction is challenging in imitation learning (IL), particularly in tasks that require operating near a system's handling limits. Traditional IL methods, such as Behavior Cloning (BC), often struggle to enforce constraints, leading to suboptimal performance in high-precision tasks. In this paper, we present a simple approach to incorporating safety into the IL objective. Through simulations, we empirically validate our approach on an autonomous racing task with both full-state and image feedback, demonstrating improved constraint satisfaction and greater consistency in task performance compared to BC.