IEEE

MaTVT: A Transformer-Based Approach for Multi-Agent Prediction in Complex Traffic Scenarios

Abstract: The future trajectories of surrounding agents are critical for the motion planning and control of autonomous vehicles. Thus, this study employs Transformer to develop a multi-agent ...
IEEE

Rotation-Invariant Feature Learning via Convolutional Neural Network With Cyclic Polar Coordinates Convolutional Layer

Abstract: Convolutional neural networks (CNNs) have been demonstrated to be powerful tools to automatically learn effective features from large datasets. Though features learned in CNNs are ...