TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions

Abstract

We present a new algorithm for predicting the near-term trajectories of road-agents in dense traffic videos. Our approach is designed for heterogeneous traffic, where the road-agents may correspond to buses, cars, scooters, bicycles, or pedestrians. We model the interactions between different road-agents using a novel LSTM-CNN hybrid network for trajectory prediction. In particular, we take into account heterogeneous interactions that implicitly accounts for the varying shapes, dynamics, and behaviors of different road agents. In addition, we model horizon-based interactions which are used to implicitly model the driving behavior of each road-agent. We evaluate the performance of our prediction algorithm, TraPHic, on the standard datasets and also introduce a new dense, heterogeneous traffic dataset corresponding to urban Asian videos and agent trajectories. We outperform state-of-the-art methods on dense traffic datasets by 30%.

arXiv comment10 pages, 5 figures, 3 tables

References in corpus (2)

• Social Force Model for Pedestrian Dynamics
• How would surround vehicles move? A Unified Framework for Maneuver Classification and Motion Prediction

Cited by in corpus (15)

• A Review of Tracking, Prediction and Decision Making Methods for Autonomous Driving
• PiP: Planning-informed Trajectory Prediction for Autonomous Driving
• Social Interactions for Autonomous Driving: A Review and Perspectives
• SocialVAE: Human Trajectory Prediction using Timewise Latents
• Pedestrian Trajectory Prediction in Pedestrian-Vehicle Mixed Environments: A Systematic Review
• Probabilistic Crowd GAN: Multimodal Pedestrian Trajectory Prediction using a Graph Vehicle-Pedestrian Attention Network
• ROAD: The ROad event Awareness Dataset for Autonomous Driving
• Heterogeneous Trajectory Forecasting via Risk and Scene Graph Learning
• Social-IWSTCNN: A Social Interaction-Weighted Spatio-Temporal Convolutional Neural Network for Pedestrian Trajectory Prediction in Urban Traffic Scenarios
• Egocentric Human Trajectory Forecasting with a Wearable Camera and Multi-Modal Fusion
• The Magni Human Motion Dataset: Accurate, Complex, Multi-Modal, Natural, Semantically-Rich and Contextualized
• Learning the Pedestrian-Vehicle Interaction for Pedestrian Trajectory Prediction
• Spatiotemporal Receding Horizon Control with Proactive Interaction Towards Autonomous Driving in Dense Traffic
• Trajectory prediction for heterogeneous agents: A performance analysis on small and imbalanced datasets
• Characterizing Structured versus Unstructured Environments based on Pedestrians' and Vehicles' Motion Trajectories