TrajGen: Generating Realistic and Diverse Trajectories with Reactive and Feasible Agent Behaviors for Autonomous Driving

TL;DR

TrajGen is a two-stage framework that generates realistic, diverse, and feasible vehicle trajectories for autonomous driving simulation by combining multi-modal prediction and reinforcement learning, trained on naturalistic data.

Contribution

The paper introduces TrajGen, a novel two-stage trajectory generation method with a new auxiliary RouteLoss and a data-driven simulator, improving realism and diversity over existing models.

Findings

TrajGen outperforms existing methods in fidelity, reactivity, feasibility, and diversity.

The auxiliary RouteLoss enhances multi-modal trajectory prediction.

The data-driven simulator enables effective reinforcement learning training.

Abstract

Realistic and diverse simulation scenarios with reactive and feasible agent behaviors can be used for validation and verification of self-driving system performance without relying on expensive and time-consuming real-world testing. Existing simulators rely on heuristic-based behavior models for background vehicles, which cannot capture the complex interactive behaviors in real-world scenarios. To bridge the gap between simulation and the real world, we propose TrajGen, a two-stage trajectory generation framework, which can capture more realistic behaviors directly from human demonstration. In particular, TrajGen consists of the multi-modal trajectory prediction stage and the reinforcement learning based trajectory modification stage. In the first stage, we propose a novel auxiliary RouteLoss for the trajectory prediction model to generate multi-modal diverse trajectories in the drivable area. In the second stage, reinforcement learning is used to track the predicted trajectories while avoiding collisions, which can improve the feasibility of generated trajectories. In addition, we develop a data-driven simulator I-Sim that can be used to train reinforcement learning models in parallel based on naturalistic driving data. The vehicle model in I-Sim can guarantee that the generated trajectories by TrajGen satisfy vehicle kinematic constraints. Finally, we give comprehensive metrics to evaluate generated trajectories for simulation scenarios, which shows that TrajGen outperforms either trajectory prediction or inverse reinforcement learning in terms of fidelity, reactivity, feasibility, and diversity.