Neural Certificates for Safe Control Policies

Abstract

This paper develops an approach to learn a policy of a dynamical system that is guaranteed to be both provably safe and goal-reaching. Here, the safety means that a policy must not drive the state of the system to any unsafe region, while the goal-reaching requires the trajectory of the controlled system asymptotically converges to a goal region (a generalization of stability). We obtain the safe and goal-reaching policy by jointly learning two additional certificate functions: a barrier function that guarantees the safety and a developed Lyapunov-like function to fulfill the goal-reaching requirement, both of which are represented by neural networks. We show the effectiveness of the method to learn both safe and goal-reaching policies on various systems, including pendulums, cart-poles, and UAVs.

References in corpus (4)

• Playing Atari with Deep Reinforcement Learning
• Control of Memory, Active Perception, and Action in Minecraft
• Learning for Safety-Critical Control with Control Barrier Functions
• End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks

Cited by in corpus (7)

• Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates
• Learning Stability Certificates from Data
• Learning Hybrid Control Barrier Functions from Data
• Actor-Critic Physics-informed Neural Lyapunov Control
• Promoting global stability in data-driven models of quadratic nonlinear dynamics
• BarrierNet: A Safety-Guaranteed Layer for Neural Networks
• Verification in the Loop: Correct-by-Construction Control Learning with Reach-avoid Guarantees