Gradient-based Trajectory Optimization with Parallelized Differentiable Traffic Simulation
This work addresses scalable and physically-constrained trajectory optimization for autonomous vehicles and traffic analysis, representing an incremental improvement through differentiable simulation.
The authors developed a parallelized differentiable traffic simulator based on the Intelligent Driver Model to optimize vehicle trajectories using gradient-based methods, achieving real-time simulation of up to 2 million vehicles and demonstrating applications in trajectory filtering, reconstruction, and prediction on datasets like NGSIM and Waymo.
We present a parallelized differentiable traffic simulator based on the Intelligent Driver Model (IDM), a car-following framework that incorporates driver behavior as key variables. Our vehicle simulator efficiently models vehicle motion, generating trajectories that can be supervised to fit real-world data. By leveraging its differentiable nature, IDM parameters are optimized using gradient-based methods. With the capability to simulate up to 2 million vehicles in real time, the system is scalable for large-scale trajectory optimization. We show that we can use the simulator to filter noise in the input trajectories (trajectory filtering), reconstruct dense trajectories from sparse ones (trajectory reconstruction), and predict future trajectories (trajectory prediction), with all generated trajectories adhering to physical laws. We validate our simulator and algorithm on several datasets including NGSIM and Waymo Open Dataset. The code is publicly available at: https://github.com/SonSang/diffidm.