Data-based reachability analysis for movement prediction of pedestrians and motion planning

Abstract

It is a challenge to find safe trajectories for automated vehicles. Especially in urban environments with pedestrians there are many different situations. The prediction of future movements with 100% certainty is impossible, if the intention of the pedestrian is unknown. In this paper, reachability analysis is used based on historical movement data. A state of the art motion planning approach with Mixed-Integer Linear optimization (MILP) is used for the trajectory planning of the vehicle. This approach can also be used for cooperative vehicle systems, with historical movement data in a fixed urban environment (e.g. intersection). The advantage of this approach is that prior knowledge can be incorporated in the reachability analysis, and the computional load is scalable.