Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation

TL;DR

This paper introduces novel methods, OGD and ECM Guidance, to improve the efficiency of diffusion models for joint trajectory prediction and controllable generation in autonomous driving, reducing computational costs while maintaining high quality.

Contribution

The paper proposes two new techniques, OGD and ECM Guidance, that optimize diffusion processes for faster, more efficient joint trajectory prediction and controllable generation.

Findings

Outperforms existing methods on Argoverse 2 dataset

Reduces computational overhead significantly

Maintains high prediction accuracy

Abstract

Diffusion models are promising for joint trajectory prediction and controllable generation in autonomous driving, but they face challenges of inefficient inference steps and high computational demands. To tackle these challenges, we introduce Optimal Gaussian Diffusion (OGD) and Estimated Clean Manifold (ECM) Guidance. OGD optimizes the prior distribution for a small diffusion time $T$ and starts the reverse diffusion process from it. ECM directly injects guidance gradients to the estimated clean manifold, eliminating extensive gradient backpropagation throughout the network. Our methodology streamlines the generative process, enabling practical applications with reduced computational overhead. Experimental validation on the large-scale Argoverse 2 dataset demonstrates our approach's superior performance, offering a viable solution for computationally efficient, high-quality joint trajectory prediction and controllable generation for autonomous driving. Our project webpage is at https://yixiaowang7.github.io/OptTrajDiff_Page/.