Simulation provides a fast, cost-effective, and secure environment for developing autonomous driving systems. However, mitigating the gap between simulation and reality is a challenging task as it demands a behavior simulation method that is human-like, diverse, controllable, socially consistent, and scalable. This work proposes a data-driven traffic agent simulation method to address the aforementioned challenges. Our approach centers around a graph-based scene representation and an encoding method, dividing the simulation into two stages: Multi-Agent Goal assignment (MAG) and Goal-Directed Planning (GDP). Firstly, we create joint goal sets for all agents involved in the scenario. Subsequently, we assign target centerlines (TCLs) to each agent based on their predicted goals. To account for any potential mismatch between the predicted joint goal sets and the road structure, we further align the goals of each agent with their respective assigned TCLs. These on-TCL goals serve as inputs for our interactive autoregressive Goal-Directed Planner (AR-GDP), constituting the second stage of our method that generates roll-outs for simulations. Evaluation results on the leaderboard of the Waymo Open Sim Agents Challenge (WOSAC) 2023 show the competitiveness of the proposed method.
Scalable Traffic Simulation for Autonomous Driving via Multi-Agent Goal Assignment and Autoregressive Goal-Directed Planning
2024-06-02
2408610 byte
Conference paper
Electronic Resource
English
Goal-directed occupancy prediction for autonomous driving
European Patent Office | 2022
|Goal-Directed Occupancy Prediction for Autonomous Driving
European Patent Office | 2021
|Goal Directed Approach to Autonomous Motion Planning for Unmanned Vehicles
BASE | 2016
|A goal-directed transportation planning model
Elsevier | 1970