Collaborative Motion Prediction via Neural Motion Message Passing

Abstract

Motion prediction is essential and challenging for autonomous vehicles and social robots. One challenge of motion prediction is to model the interaction among traffic actors, which could cooperate with each other to avoid collisions or form groups. To address this challenge, we propose neural motion message passing (NMMP) to explicitly model the interaction and learn representations for directed interactions between actors. Based on the proposed NMMP, we design the motion prediction systems for two settings: the pedestrian setting and the joint pedestrian and vehicle setting. Both systems share a common pattern: we use an individual branch to model the behavior of a single actor and an interactive branch to model the interaction between actors, while with different wrappers to handle the varied input formats and characteristics. The experimental results show that both systems outperform the previous state-of-the-art methods on several existing benchmarks. Besides, we provide interpretability for interaction learning.

arXiv commentAccepted by CVPR 2020 Oral

References in corpus (8)

• Sequence to Sequence Learning with Neural Networks
• Social Force Model for Pedestrian Dynamics
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Gated Graph Sequence Neural Networks
• IntentNet: Learning to Predict Intention from Raw Sensor Data
• Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Driving
• Generalized Value Iteration Networks: Life Beyond Lattices

Cited by in corpus (4)

• Scene Gated Social Graph: Pedestrian Trajectory Prediction Based on Dynamic Social Graphs and Scene Constraints
• SRA-LSTM: Social Relationship Attention LSTM for Human Trajectory Prediction
• AVGCN: Trajectory Prediction using Graph Convolutional Networks Guided by Human Attention
• HGCN-GJS: Hierarchical Graph Convolutional Network with Groupwise Joint Sampling for Trajectory Prediction