Efficient and Accurate Digital Twins for Lane-Wise and Topology-Invariant Intersection Traffic Simulation
Graph Attention Neural Networks are leveraged to build efficient and accurate digital twins that can simultaneously estimate lane-wise traffic waveforms for vehicles approaching and exiting any intersection, while accounting for various influential factors such as signal timing, driving behavior, and turning-movement counts.
Versatile and Controllable Traffic Scenario Generation using Diffusion-based Optimization
The proposed Versatile Behavior Diffusion (VBD) model leverages diffusion-based generative modeling to efficiently generate realistic and controllable traffic scenarios by integrating joint multi-agent diffusion policy and marginal multi-modal behavior prediction.
LitSim: Long-term Interactive Traffic Simulation with Conflict-aware Policy
LitSim proposes a conflict-aware policy for long-term interactive traffic simulation to enhance realism and reactivity.
LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation
Addressing the covariate shift problem in multi-agent imitation learning for realistic traffic simulation.
LitSim: Long-term Interactive Traffic Simulation with Conflict-aware Policy
LitSim proposes a conflict-aware policy for long-term interactive traffic simulation to enhance realism and reactivity.
LitSim: Long-term Interactive Traffic Simulation with Conflict-aware Policy
LitSim proposes a long-term interactive simulation approach that maximizes realism while avoiding unrealistic collisions by utilizing conflict-aware policies. The method outperforms existing approaches in terms of realism and reactivity.
© 2024 by Linnk AI