Self-Supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Map

TL;DR

This paper presents a self-supervised architecture for predicting road dynamics and cost maps over multiple steps, improving autonomous driving safety without manual data labeling.

Contribution

A novel self-supervised model that jointly predicts interpretable cost maps and road dynamics, eliminating the need for manual labeling and enhancing scalability.

Findings

Lower collisions and violations in long-term predictions

Effective integration of contextual information without labels

Demonstrated feasibility of fully self-supervised prediction

Abstract

While supervised learning is widely used for perception modules in conventional autonomous driving solutions, scalability is hindered by the huge amount of data labeling needed. In contrast, while end-to-end architectures do not require labeled data and are potentially more scalable, interpretability is sacrificed. We introduce a novel architecture that is trained in a fully self-supervised fashion for simultaneous multi-step prediction of space-time cost map and road dynamics. Our solution replaces the manually designed cost function for motion planning with a learned high dimensional cost map that is naturally interpretable and allows diverse contextual information to be integrated without manual data labeling. Experiments on real world driving data show that our solution leads to lower number of collisions and road violations in long planning horizons in comparison to baselines, demonstrating the feasibility of fully self-supervised prediction without sacrificing either scalability or interpretability.