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

arXiv:2405.00797v1 Announce Type: cross
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 …

abstract agent arxiv autonomous autonomous driving cs.cv cs.ro diffusion diffusion model diffusion models driving dynamics interactions modal multi-modal nature pedestrian prediction robust stochastic type via world