TrafficBots V1.5: Traffic Simulation via Conditional VAEs and Transformers with Relative Pose Encoding

TL;DR

TrafficBots V1.5 introduces a traffic simulation method combining CVAE-based policies and transformers with relative pose encoding, achieving competitive performance in the WOSAC 2024 challenge.

Contribution

It presents a simple yet effective baseline for traffic agent simulation using conditional VAEs and transformers, with improvements like scheduled teacher-forcing and scenario filtering.

Findings

Achieved 3rd place in WOSAC 2024

Baseline-level performance on traffic simulation

Effective combination of CVAE and transformer architectures

Abstract

In this technical report we present TrafficBots V1.5, a baseline method for the closed-loop simulation of traffic agents. TrafficBots V1.5 achieves baseline-level performance and a 3rd place ranking in the Waymo Open Sim Agents Challenge (WOSAC) 2024. It is a simple baseline that combines TrafficBots, a CVAE-based multi-agent policy conditioned on each agent's individual destination and personality, and HPTR, the heterogeneous polyline transformer with relative pose encoding. To improve the performance on the WOSAC leaderboard, we apply scheduled teacher-forcing at the training time and we filter the sampled scenarios at the inference time. The code is available at https://github.com/zhejz/TrafficBotsV1.5.