Traffic Agent Trajectory Prediction Using Social Convolution and Attention Mechanism

TL;DR

This paper introduces a novel traffic agent trajectory prediction model that combines social convolution and attention mechanisms, effectively capturing agent interactions and history to improve accuracy and real-time performance in autonomous driving scenarios.

Contribution

The proposed model uniquely integrates social convolution with attention-based encoding of agent trajectories, handling dynamic agent numbers with a variable-length LSTM, and demonstrates significant accuracy improvements.

Findings

Achieved 20% reduction in prediction error on a public dataset.

Operates at 32 frames per second, meeting real-time requirements.

Effectively models dynamic agent interactions in traffic scenes.

Abstract

The trajectory prediction is significant for the decision-making of autonomous driving vehicles. In this paper, we propose a model to predict the trajectories of target agents around an autonomous vehicle. The main idea of our method is considering the history trajectories of the target agent and the influence of surrounding agents on the target agent. To this end, we encode the target agent history trajectories as an attention mask and construct a social map to encode the interactive relationship between the target agent and its surrounding agents. Given a trajectory sequence, the LSTM networks are firstly utilized to extract the features for all agents, based on which the attention mask and social map are formed. Then, the attention mask and social map are fused to get the fusion feature map, which is processed by the social convolution to obtain a fusion feature representation. Finally, this fusion feature is taken as the input of a variable-length LSTM to predict the trajectory of the target agent. We note that the variable-length LSTM enables our model to handle the case that the number of agents in the sensing scope is highly dynamic in traffic scenes. To verify the effectiveness of our method, we widely compare with several methods on a public dataset, achieving a 20% error decrease. In addition, the model satisfies the real-time requirement with the 32 fps.