Safe Motion Planning against Multimodal Distributions based on a Scenario Approach
This addresses safety-critical motion planning for autonomous vehicles in complex, uncertain environments, representing an incremental improvement over existing scenario-based methods.
The paper tackles the problem of ensuring safety in autonomous vehicle motion planning under multimodal uncertainty, such as predicting surrounding vehicles' discrete decisions at intersections, by developing a computationally efficient scenario-based method that clusters samples and uses bounding polytopes to formulate a mixed-integer problem. The result demonstrates high-probability safety, with improved computational efficiency and reduced conservatism compared to conventional approaches, as validated on the nuScenes dataset.
We present the design of a motion planning algorithm that ensures safety for an autonomous vehicle. In particular, we consider a multimodal distribution over uncertainties; for example, the uncertain predictions of future trajectories of surrounding vehicles reflect discrete decisions, such as turning or going straight at intersections. We develop a computationally efficient, scenario-based approach that solves the motion planning problem with high confidence given a quantifiable number of samples from the multimodal distribution. Our approach is based on two preprocessing steps, which 1) separate the samples into distinct clusters and 2) compute a bounding polytope for each cluster. Then, we rewrite the motion planning problem approximately as a mixed-integer problem using the polytopes. We demonstrate via simulation on the nuScenes dataset that our approach ensures safety with high probability in the presence of multimodal uncertainties, and is computationally more efficient and less conservative than a conventional scenario approach.