Adv-BMT: Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation
Yuxin Liu* 1 , Zhenghao Peng* 1 , Xuanhao Cui 1 , Bolei Zhou 1
1 University of California, Los Angeles
TL; DR
Adv-BMT augments diverse and realistic collision interactions from a input real-world driving log.
Adv-BMT generates collision interactions through adversarial initializations + reverse motion predictions.
Adv-BMT can be leveraged as a closed-loop generator for reinforcement adversarial learnings.
Adv-BMT
Adv-BMT is a two-staged pipeline: first, it initializes diverse collision states between a new adversary agent and ego vehicle; then, it reconstructs the adversarial trajectories via BMT’s reverse predictions. A rule-based rejection sampling mechanism is used to filter candidate trajectories from unsatisfactory adversarial initializations, and maintain realistic collision interactions. In the output, the new agent maintains realistic interactions with surrounding traffic.
BMT Architecture
BMT is a transformer-based motion prediction model, and is able to predict both future and history trajectories for vehicles, bicycles, and pedestrain agents.
Diverse Adversarial Behaviors
Safer Agent via Adversarial Learnings
Adversarial RL Evaluations
Prior Works
CAT (CoRL 2022): Closed-loop adversarial training for safe end-to-end driving.
MetaDrive (TPAMI 2021): An open-source platform for large-scale traffic scenario simulation and modeling