Safe Nonlinear Control Using Robust Neural Lyapunov-Barrier Functions
This addresses safety and stability challenges in robotic control for applications like autonomous vehicles and satellites, though it appears incremental as it builds on existing Lyapunov and barrier function methods.
The paper tackles the problem of designing safe and stable controllers for nonlinear robotic systems with model uncertainty by developing a model-based learning approach that synthesizes robust feedback controllers with guarantees. The results show that their approach matches or exceeds robust MPC capabilities while reducing computational costs by an order of magnitude in simulations.
Safety and stability are common requirements for robotic control systems; however, designing safe, stable controllers remains difficult for nonlinear and uncertain models. We develop a model-based learning approach to synthesize robust feedback controllers with safety and stability guarantees. We take inspiration from robust convex optimization and Lyapunov theory to define robust control Lyapunov barrier functions that generalize despite model uncertainty. We demonstrate our approach in simulation on problems including car trajectory tracking, nonlinear control with obstacle avoidance, satellite rendezvous with safety constraints, and flight control with a learned ground effect model. Simulation results show that our approach yields controllers that match or exceed the capabilities of robust MPC while reducing computational costs by an order of magnitude.