Research on Lane-Changing Trajectory Planning for Autonomous Driving Considering Longitudinal Interaction

Autonomous driving in real-world urban traffic must cope with dynamic environments. This presents a challenging decision-making problem, e.g. deciding when to perform an overtaking maneuver or how to safely merge into traffic. The traditional autonomous driving algorithm framework decouples prediction and decision-making, which means that the decision-making and planning tasks will be carried out after the prediction task is over. The disadvantage of this approach is that it does not consider the possible impact of ego vehicle decisions on the future states of other agents. In this article, a decision-making and planning method which considers longitudinal interaction is represented. The method’s architecture is mainly composed of the following parts: trajectory sampling, forward simulation, trajectory scoring and trajectory selection. For trajectory sampling, a lattice planner is used to sample three-dimensionally in both the time horizon and the space horizon. Three sampling modes which include car following, cruising and lane changing are set up to satisfy different driving requirements. For each trajectory sampled, a forward simulation is used to capture the potential future states of other agents under the ego vehicle’s policy. We then score the trajectory outcomes using a user-defined cost function which has considered comfort, driving efficiency, etc … And the results of the forward simulation in the previous process will also be taken into account in the cost function. Finally, we select the optimal trajectory based on the score. In the simulation process, we simulate the overtaking by lane changing scenario. The result shows that the proposed method can effectively handle multi-agents’ dynamic interaction scenario.