ABNet: Attention BarrierNet for Safe and Scalable Robot Learning
This addresses safety challenges for AI-enabled robots, offering a scalable solution with proven guarantees, though it is incremental in its approach.
The paper tackled the scalability and instability issues of barrier-based methods in safe robot learning by proposing Attention BarrierNet (ABNet), which incrementally builds safe models with multiple heads for different features, resulting in improved robustness and formal safety guarantees in tasks like obstacle avoidance and autonomous driving.
Safe learning is central to AI-enabled robots where a single failure may lead to catastrophic results. Barrier-based method is one of the dominant approaches for safe robot learning. However, this method is not scalable, hard to train, and tends to generate unstable signals under noisy inputs that are challenging to be deployed for robots. To address these challenges, we propose a novel Attention BarrierNet (ABNet) that is scalable to build larger foundational safe models in an incremental manner. Each head of BarrierNet in the ABNet could learn safe robot control policies from different features and focus on specific part of the observation. In this way, we do not need to one-shotly construct a large model for complex tasks, which significantly facilitates the training of the model while ensuring its stable output. Most importantly, we can still formally prove the safety guarantees of the ABNet. We demonstrate the strength of ABNet in 2D robot obstacle avoidance, safe robot manipulation, and vision-based end-to-end autonomous driving, with results showing much better robustness and guarantees over existing models.