Trajectory Prediction using Equivariant Continuous Convolution

Abstract

Trajectory prediction is a critical part of many AI applications, for example, the safe operation of autonomous vehicles. However, current methods are prone to making inconsistent and physically unrealistic predictions. We leverage insights from fluid dynamics to overcome this limitation by considering internal symmetry in real-world trajectories. We propose a novel model, Equivariant Continous COnvolution (ECCO) for improved trajectory prediction. ECCO uses rotationally-equivariant continuous convolutions to embed the symmetries of the system. On both vehicle and pedestrian trajectory datasets, ECCO attains competitive accuracy with significantly fewer parameters. It is also more sample efficient, generalizing automatically from few data points in any orientation. Lastly, ECCO improves generalization with equivariance, resulting in more physically consistent predictions. Our method provides a fresh perspective towards increasing trust and transparency in deep learning models.

Accepted to ICLR 2021, 17 pages

References in corpus (18)

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Group Equivariant Convolutional Networks
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• Learning to Simulate Complex Physics with Graph Networks
• SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks
• On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
• Equivariant flow-based sampling for lattice gauge theory
• Argoverse: 3D Tracking and Forecasting with Rich Maps
• Exploiting Cyclic Symmetry in Convolutional Neural Networks
• General $E(2)$-Equivariant Steerable CNNs
• Incorporating Symmetry into Deep Dynamics Models for Improved Generalization
• Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
• On Learning Sets of Symmetric Elements
• Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Driving
• Learning Lane Graph Representations for Motion Forecasting
• Applying Deep Learning to Basketball Trajectories
• Rotation Equivariance and Invariance in Convolutional Neural Networks
• Equivariant neural networks and equivarification