Collision Avoidance Detour for Multi-Agent Trajectory Forecasting
This work addresses simulation realism for autonomous driving systems, but it is incremental as it builds on existing factorization and resampling techniques.
The paper tackled multi-agent trajectory forecasting for autonomous driving by partitioning objects into three sets and using independent motion models, achieving 3rd place in the 2023 Waymo Open Dataset Challenge.
We present our approach, Collision Avoidance Detour (CAD), which won the 3rd place award in the 2023 Waymo Open Dataset Challenge - Sim Agents, held at the 2023 CVPR Workshop on Autonomous Driving. To satisfy the motion prediction factorization requirement, we partition all the valid objects into three mutually exclusive sets: Autonomous Driving Vehicle (ADV), World-tracks-to-predict, and World-others. We use different motion models to forecast their future trajectories independently. Furthermore, we also apply collision avoidance detour resampling, additive Gaussian noise, and velocity-based heading estimation to improve the realism of our simulation result.