DeepAI AI Chat
Log In Sign Up

TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction

by   Zhejun Zhang, et al.
Max Planck Society

Data-driven simulation has become a favorable way to train and test autonomous driving algorithms. The idea of replacing the actual environment with a learned simulator has also been explored in model-based reinforcement learning in the context of world models. In this work, we show data-driven traffic simulation can be formulated as a world model. We present TrafficBots, a multi-agent policy built upon motion prediction and end-to-end driving, and based on TrafficBots we obtain a world model tailored for the planning module of autonomous vehicles. Existing data-driven traffic simulators are lacking configurability and scalability. To generate configurable behaviors, for each agent we introduce a destination as navigational information, and a time-invariant latent personality that specifies the behavioral style. To improve the scalability, we present a new scheme of positional encoding for angles, allowing all agents to share the same vectorized context and the use of an architecture based on dot-product attention. As a result, we can simulate all traffic participants seen in dense urban scenarios. Experiments on the Waymo open motion dataset show TrafficBots can simulate realistic multi-agent behaviors and achieve good performance on the motion prediction task.


page 1

page 2

page 3

page 4

page 6


Simulating Autonomous Driving in Massive Mixed Urban Traffic

Autonomous driving in an unregulated urban crowd is an outstanding chall...

SUMMIT: A Simulator for Urban Driving in Massive Mixed Traffic

Autonomous driving in an unregulated urban crowd is an outstanding chall...

From Model-Based to Data-Driven Simulation: Challenges and Trends in Autonomous Driving

Simulation is an integral part in the process of developing autonomous v...

TraInterSim: Adaptive and Planning-Aware Hybrid-Driven Traffic Intersection Simulation

Traffic intersections are important scenes that can be seen almost every...

Deep Occupancy-Predictive Representations for Autonomous Driving

Manually specifying features that capture the diversity in traffic envir...

Gradient Optimization for Single-State RMDPs

As modern problems such as autonomous driving, control of robotic compon...

Data-driven Analysis for Understanding Team Sports Behaviors

Understanding the principles of real-world biological multi-agent behavi...