3 papers
cs.CV2024
AMEND: A Mixture of Experts Framework for Long-tailed Trajectory Prediction
Ray Coden Mercurius, Ehsan Ahmadi, Soheil Mohamad Alizadeh Shabestary +1
Accurate prediction of pedestrians' future motions is critical for intelligent driving systems. Developing models for this task requires rich datasets containing diverse sets of sa…
cs.CV2023
DICE: Diverse Diffusion Model with Scoring for Trajectory Prediction
Younwoo Choi, Ray Coden Mercurius, Soheil Mohamad Alizadeh Shabestary +1
Road user trajectory prediction in dynamic environments is a challenging but crucial task for various applications, such as autonomous driving. One of the main challenges in this d…
cs.LG2023
Perimeter Control Using Deep Reinforcement Learning: A Model-free Approach towards Homogeneous Flow Rate Optimization
Xiaocan Li, Ray Coden Mercurius, Ayal Taitler +4
Perimeter control maintains high traffic efficiency within protected regions by controlling transfer flows among regions to ensure that their traffic densities are below critical v…