Longitudinal and lateral motion planning method for avoidance of multi-obstacles in urban environments based on inverse collision probability

This paper presents a longitudinal and lateral motion planning method for driver assistance systems in urban scenarios. We proposed a Bayesian network based motion planner to generate the trajectory, including the positions and velocities to path through multiple traffic participants. To design the probabilistic models which represent a lane keeping maneuver and an obstacle avoidance maneuver, we collect and analyze natural driving data. Then, it is difficult to collect collision data in the real world. Therefore, we analyze the inverse collision probability from safety driving trajectories of expert drivers. The proposed method generates the optimal trajectory plan by using the global optimization algorithm named Belief Propagation. Finally, we show the evaluation experiment that compares the difference between the trajectories generated by the proposed method and natural driving data.