Uncertainty-Aware Diffusion Model for Multimodal Highway Trajectory Prediction via DDIM Sampling

TL;DR

This paper introduces cVMDx, a diffusion-based model for autonomous vehicle trajectory prediction that significantly improves efficiency, robustness, and multimodal prediction accuracy using DDIM sampling and Gaussian Mixture Models.

Contribution

cVMDx enhances diffusion-based trajectory prediction by reducing inference time, improving diversity, and enabling practical uncertainty estimation in autonomous driving scenarios.

Findings

Achieves up to 100x faster inference than previous models

Provides more accurate and diverse multimodal trajectory predictions

Demonstrates superior performance on the highD dataset

Abstract

Accurate and uncertainty-aware trajectory prediction remains a core challenge for autonomous driving, driven by complex multi-agent interactions, diverse scene contexts and the inherently stochastic nature of future motion. Diffusion-based generative models have recently shown strong potential for capturing multimodal futures, yet existing approaches such as cVMD suffer from slow sampling, limited exploitation of generative diversity and brittle scenario encodings. This work introduces cVMDx, an enhanced diffusion-based trajectory prediction framework that improves efficiency, robustness and multimodal predictive capability. Through DDIM sampling, cVMDx achieves up to a 100x reduction in inference time, enabling practical multi-sample generation for uncertainty estimation. A fitted Gaussian Mixture Model further provides tractable multimodal predictions from the generated trajectories. In addition, a CVQ-VAE variant is evaluated for scenario encoding. Experiments on the publicly available highD dataset show that cVMDx achieves higher accuracy and significantly improved efficiency over cVMD, enabling fully stochastic, multimodal trajectory prediction.