Graph-Based Interaction-Aware Multimodal 2D Vehicle Trajectory Prediction using Diffusion Graph Convolutional Networks

no code implementations • 5 Sep 2023 • Keshu Wu, Yang Zhou, Haotian Shi, Xiaopeng Li, Bin Ran

Within this framework, vehicles' motions are conceptualized as nodes in a time-varying graph, and the traffic interactions are represented by a dynamic adjacency matrix.

Graph Embedding Intent Detection +1

Partially Connected Automated Vehicle Cooperative Control Strategy with a Deep Reinforcement Learning Approach

no code implementations • 3 Dec 2020 • Haotian Shi, Yang Zhou, Keshu Wu, Xin Wang, Yangxin Lin, Bin Ran

This paper proposes a cooperative strategy of connected and automated vehicles (CAVs) longitudinal control for partially connected and automated traffic environment based on deep reinforcement learning (DRL) algorithm, which enhances the string stability of mixed traffic, car following efficiency, and energy efficiency.

reinforcement-learning Reinforcement Learning (RL)