Trajectory Prediction using Equivariant Continuous Convolution
This addresses trajectory prediction for autonomous vehicles and pedestrians, offering a novel approach to improve physical consistency, though it appears incremental in applying equivariance to an existing problem.
The paper tackles the problem of inconsistent and physically unrealistic trajectory predictions in autonomous systems by proposing ECCO, an equivariant continuous convolution model that leverages rotational symmetries. On vehicle and pedestrian datasets, ECCO achieves competitive accuracy with fewer parameters and better sample efficiency.
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.