StarNet: Pedestrian Trajectory Prediction using Deep Neural Network in Star Topology

Abstract

Pedestrian trajectory prediction is crucial for many important applications. This problem is a great challenge because of complicated interactions among pedestrians. Previous methods model only the pairwise interactions between pedestrians, which not only oversimplifies the interactions among pedestrians but also is computationally inefficient. In this paper, we propose a novel model StarNet to deal with these issues. StarNet has a star topology which includes a unique hub network and multiple host networks. The hub network takes observed trajectories of all pedestrians to produce a comprehensive description of the interpersonal interactions. Then the host networks, each of which corresponds to one pedestrian, consult the description and predict future trajectories. The star topology gives StarNet two advantages over conventional models. First, StarNet is able to consider the collective influence among all pedestrians in the hub network, making more accurate predictions. Second, StarNet is computationally efficient since the number of host network is linear to the number of pedestrians. Experiments on multiple public datasets demonstrate that StarNet outperforms multiple state-of-the-arts by a large margin in terms of both accuracy and efficiency.

arXiv commentAccepted by the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019)

References in corpus (4)

• Social Force Model for Pedestrian Dynamics
• A Neural Representation of Sketch Drawings
• Human Trajectory Prediction using Spatially aware Deep Attention Models
• Soft + Hardwired Attention: An LSTM Framework for Human Trajectory Prediction and Abnormal Event Detection

Cited by in corpus (10)

• GRIP++: Enhanced Graph-based Interaction-aware Trajectory Prediction for Autonomous Driving
• A Novel Graph based Trajectory Predictor with Pseudo Oracle
• Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies
• Probabilistic Multi-modal Trajectory Prediction with Lane Attention for Autonomous Vehicles
• TPNet: Trajectory Proposal Network for Motion Prediction
• TPPO: A Novel Trajectory Predictor with Pseudo Oracle
• VisionNet: A Drivable-space-based Interactive Motion Prediction Network for Autonomous Driving
• DsMCL: Dual-Level Stochastic Multiple Choice Learning for Multi-Modal Trajectory Prediction
• UST: Unifying Spatio-Temporal Context for Trajectory Prediction in Autonomous Driving
• Phase Space Reconstruction Network for Lane Intrusion Action Recognition