Motion Prediction for Autonomous Vehicles from Lyft Dataset using Deep Learning

TLDR

Autonomous vehicles are poised to transform global transportation, yet predicting the motion of surrounding traffic agents remains a key engineering challenge. The study evaluates the prediction accuracy of several deep‑learning models using root‑mean‑square error. The authors train deep‑learning models that, given the current state of surrounding agents, predict their future motion and assess performance via RMSE.

Abstract

Autonomous Vehicles are expected to change the future of worldwide transportation system. As self-driving cars are facing a lot of engineering challenges, it is one of the hottest topics in recent research. One such challenge is to build models to predict the movements of traffic agents such as cars, cyclists, pedestrians etc around the self-driving cars. The objective of this paper is to analyse the prediction efficiency of various deep learning models by calculating root mean square error score. This deep learning models takes a current state of the surrounding and depending on that predict the motion for the agents.