The WayHome: Long-term Motion Prediction on Dynamically Scaled

TL;DR

This paper introduces a neural network-based motion prediction method for autonomous vehicles that uses heatmaps and a novel grid-scaling technique, significantly improving short-term prediction accuracy on the Waymo dataset.

Contribution

A new motion forecasting approach utilizing heatmaps, a sampling algorithm, and grid-scaling, advancing state-of-the-art in short-term autonomous vehicle motion prediction.

Findings

Improved miss rate performance for 3-second predictions

Competitive accuracy up to 8 seconds

Effective grid-scaling technique enhances results

Abstract

One of the key challenges for autonomous vehicles is the ability to accurately predict the motion of other objects in the surrounding environment, such as pedestrians or other vehicles. In this contribution, a novel motion forecasting approach for autonomous vehicles is developed, inspired by the work of Gilles et al. [1]. We predict multiple heatmaps with a neuralnetwork-based model for every traffic participant in the vicinity of the autonomous vehicle; with one heatmap per timestep. The heatmaps are used as input to a novel sampling algorithm that extracts coordinates corresponding to the most likely future positions. We experiment with different encoders and decoders, as well as a comparison of two loss functions. Additionally, a new grid-scaling technique is introduced, showing further improved performance. Overall, our approach improves stateof-the-art miss rate performance for the function-relevant prediction interval of 3 seconds while being competitive in longer prediction intervals (up to eight seconds). The evaluation is done on the public 2022 Waymo motion challenge.