Scaling Motion Forecasting Models with Ensemble Distillation

arXiv:2404.03843v1 Announce Type: cross
Abstract: Motion forecasting has become an increasingly critical component of autonomous robotic systems. Onboard compute budgets typically limit the accuracy of real-time systems. In this work we propose methods of improving motion forecasting systems subject to limited compute budgets by combining model ensemble and distillation techniques. The use of ensembles of deep neural networks has been shown to improve generalization accuracy in many application domains. We first demonstrate significant performance gains by creating a large ensemble …

abstract accuracy arxiv autonomous become budgets compute cs.lg cs.ro distillation ensemble forecasting improving real-time robotic scaling systems type work