Using control synthesis to generate corner cases: A case study on autonomous driving
This addresses safety verification for autonomous vehicles by providing a method to identify critical failure scenarios, though it is incremental as it builds on existing control synthesis techniques.
The paper tackles the problem of generating corner cases for autonomous driving control designs by using control synthesis, specifically controlled invariant set computations, to sample initial conditions and inputs that lead to safety violations. It demonstrates the technique on adaptive cruise control and lane keeping, finding falsifying trajectories for various controllers including classical designs and an open-source autonomous driving package.
This paper employs correct-by-construction control synthesis, in particular controlled invariant set computations, for falsification. Our hypothesis is that if it is possible to compute a "large enough" controlled invariant set either for the actual system model or some simplification of the system model, interesting corner cases for other control designs can be generated by sampling initial conditions from the boundary of this controlled invariant set. Moreover, if falsifying trajectories for a given control design can be found through such sampling, then the controlled invariant set can be used as a supervisor to ensure safe operation of the control design under consideration. In addition to interesting initial conditions, which are mostly related to safety violations in transients, we use solutions from a dual game, a reachability game for the safety specification, to find falsifying inputs. We also propose optimization-based heuristics for input generation for cases when the state is outside the winning set of the dual game. To demonstrate the proposed ideas, we consider case studies from basic autonomous driving functionality, in particular, adaptive cruise control and lane keeping. We show how the proposed technique can be used to find interesting falsifying trajectories for classical control designs like proportional controllers, proportional integral controllers and model predictive controllers, as well as an open source real-world autonomous driving package.