ScenarioNet: Open-source platform for large-scale traffic scenario simulation and modeling
Large-scale driving datasets such as Waymo Open Dataset and nuScenes substantially
accelerate autonomous driving research, especially for perception tasks such as 3D …
accelerate autonomous driving research, especially for perception tasks such as 3D …
SMART: Scalable Multi-agent Real-time Simulation via Next-token Prediction
W Wu, X Feng, Z Gao, Y Kan - arXiv preprint arXiv:2405.15677, 2024 - arxiv.org
Data-driven autonomous driving motion generation tasks are frequently impacted by the
limitations of dataset size and the domain gap between datasets, which precludes their …
limitations of dataset size and the domain gap between datasets, which precludes their …
Human-compatible driving partners through data-regularized self-play reinforcement learning
D Cornelisse, E Vinitsky - arXiv preprint arXiv:2403.19648, 2024 - arxiv.org
A central challenge for autonomous vehicles is coordinating with humans. Therefore,
incorporating realistic human agents is essential for scalable training and evaluation of …
incorporating realistic human agents is essential for scalable training and evaluation of …
Versatile Scene-Consistent Traffic Scenario Generation as Optimization with Diffusion
Generating realistic and controllable agent behaviors in traffic simulation is crucial for the
development of autonomous vehicles. This problem is often formulated as imitation learning …
development of autonomous vehicles. This problem is often formulated as imitation learning …
BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction
Simulating realistic interactions among traffic agents is crucial for efficiently validating the
safety of autonomous driving systems. Existing leading simulators primarily use an encoder …
safety of autonomous driving systems. Existing leading simulators primarily use an encoder …
SceneDM: Scene-level multi-agent trajectory generation with consistent diffusion models
Realistic scene-level multi-agent motion simulations are crucial for developing and
evaluating self-driving algorithms. However, most existing works focus on generating …
evaluating self-driving algorithms. However, most existing works focus on generating …
Differentiable constrained imitation learning for robot motion planning and control
Motion planning and control are crucial components of robotics applications like automated
driving. Here, spatio-temporal hard constraints like system dynamics and safety boundaries …
driving. Here, spatio-temporal hard constraints like system dynamics and safety boundaries …
A Hierarchical Forecasting Model of Pedestrian Crossing Behaviour for Autonomous Vehicle
Simulation of pedestrians in shared spaces poses a significant challenge in autonomous
driving virtual testing. The simulation pedestrian model can respond to autonomous vehicle …
driving virtual testing. The simulation pedestrian model can respond to autonomous vehicle …
UniGen: Unified Modeling of Initial Agent States and Trajectories for Generating Autonomous Driving Scenarios
R Mahjourian, R Mu, V Likhosherstov, P Mougin… - arXiv preprint arXiv …, 2024 - arxiv.org
This paper introduces UniGen, a novel approach to generating new traffic scenarios for
evaluating and improving autonomous driving software through simulation. Our approach …
evaluating and improving autonomous driving software through simulation. Our approach …
TrafficBots V1. 5: Traffic Simulation via Conditional VAEs and Transformers with Relative Pose Encoding
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 …
simulation of traffic agents. TrafficBots V1. 5 achieves baseline-level performance and a 3rd …