ITSC 2024 Paper Abstract

Close

Paper ThBT1.1

Li, Jiahui (Sichuan University), shen, tianle (South China University of Technology), Gu, Zekai (National University of Singapore), SUN, JIAWEI (National University of Singapore), YUAN, CHENGRAN (National University of Singapore), Han, Yuhang (National University of Singapore), SUN, Shuo (National University of Singapore), Ang Jr, Marcelo H (National University of Singapore)

ADM: Accelerated Diffusion Model Via Estimated Priors for Robust Motion Prediction under Uncertainties

Scheduled for presentation during the Invited Session "Learning-powered and Knowledge-driven Autonomous Driving II" (ThBT1), Thursday, September 26, 2024, 14:30−14:50, Salon 1

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on December 26, 2024

Keywords Sensing, Vision, and Perception, Multi-autonomous Vehicle Studies, Models, Techniques and Simulations

Abstract

Motion prediction is a challenging problem in autonomous driving as it demands the system to comprehend stochastic dynamics and the multi-modal nature of real-world agent interactions. Diffusion models have recently risen to prominence, and have proven particularly effective in pedestrian motion prediction tasks. However, the significant time consumption and sensitivity to noise have limited the real-time predictive capability of diffusion models. In response to these impediments, we propose a novel diffusion-based, acceleratable framework that adeptly predicts future trajectories of agents with enhanced resistance to noise. The core idea of our model is to learn a coarse-grained prior distribution of trajectory, which can skip a large number of denoise steps. This advancement not only boosts sampling efficiency but also maintains the fidelity of prediction accuracy. Our method meets the rigorous real-time operational standards essential for autonomous vehicles, enabling prompt trajectory generation that is vital for secure and efficient navigation. Through extensive experiments, our method speeds up the inference time to 136ms compared to standard diffusion model, and achieves significant improvement in multi-agent motion prediction on the Argoverse 1 motion forecasting dataset.

 

 

All Content © PaperCept, Inc.


This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2024 PaperCept, Inc.
Page generated 2024-12-26  06:35:08 PST  Terms of use