A Classification-based Approach for Approximate Reachability
This work addresses efficiency and applicability issues in safety verification for nonlinear systems, though it is incremental as it builds on existing reachability methods.
The authors tackled the computational complexity of Hamilton-Jacobi reachability analysis for control-affine systems by developing a method that learns controllers as binary classifiers instead of storing value functions, demonstrating its utility on examples like a quadrotor navigation task.
Hamilton-Jacobi (HJ) reachability analysis has been developed over the past decades into a widely-applicable tool for determining goal satisfaction and safety verification in nonlinear systems. While HJ reachability can be formulated very generally, computational complexity can be a serious impediment for many systems of practical interest. Much prior work has been devoted to computing approximate solutions to large reachability problems, yet many of these methods may only apply to very restrictive problem classes, do not generate controllers, and/or can be extremely conservative. In this paper, we present a new method for approximating the optimal controller of the HJ reachability problem for control-affine systems. While also a specific problem class, many dynamical systems of interest are, or can be well approximated, by control-affine models. We explicitly avoid storing a representation of the reachability value function, and instead learn a controller as a sequence of simple binary classifiers. We compare our approach to existing grid-based methodologies in HJ reachability and demonstrate its utility on several examples, including a physical quadrotor navigation task.