Scaling Motion Forecasting Models with Ensemble Distillation

Scott Ettinger,Kratarth Goel,Avikalp Srivastava,Rami Al-Rfou,Scott Ettinger,Kratarth Goel,Avikalp Srivastava,Rami Al-Rfou

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 im...