Efficient Motion Prediction: A Lightweight & Accurate Trajectory Prediction Model With Fast Training and Inference Speed

TL;DR

This paper introduces a lightweight, efficient motion prediction model for autonomous driving that achieves high accuracy with fast training and inference, suitable for embedded systems.

Contribution

The paper presents a novel, resource-efficient motion prediction model that requires minimal training time and computational resources, enabling deployment on embedded hardware.

Findings

Achieves competitive benchmark results

Trains in only a few hours on a single GPU

Has low inference latency suitable for real-time applications

Abstract

For efficient and safe autonomous driving, it is essential that autonomous vehicles can predict the motion of other traffic agents. While highly accurate, current motion prediction models often impose significant challenges in terms of training resource requirements and deployment on embedded hardware. We propose a new efficient motion prediction model, which achieves highly competitive benchmark results while training only a few hours on a single GPU. Due to our lightweight architectural choices and the focus on reducing the required training resources, our model can easily be applied to custom datasets. Furthermore, its low inference latency makes it particularly suitable for deployment in autonomous applications with limited computing resources.