Long-Tail Prediction Uncertainty Aware Trajectory Planning for Self-driving Vehicles

TL;DR

This paper introduces a trajectory planning method for autonomous vehicles that accounts for prediction uncertainty caused by sparse data, enhancing safety without being overly conservative when data is sufficient.

Contribution

It proposes an ensemble-based uncertainty estimation and a worst-case trajectory planning approach to improve safety in long-tail driving scenarios.

Findings

Improves safety under prediction uncertainty.

Maintains efficiency with sufficient data.

Reduces planner failures in rare scenarios.

Abstract

A typical trajectory planner of autonomous driving commonly relies on predicting the future behavior of surrounding obstacles. Recently, deep learning technology has been widely adopted to design prediction models due to their impressive performance. However, such models may fail in the "long-tail" driving cases where the training data is sparse or unavailable, leading to planner failures. To this end, this work proposes a trajectory planner to consider the prediction model uncertainty arising from insufficient data for safer performance. Firstly, an ensemble network structure estimates the prediction model's uncertainty due to insufficient training data. Then a trajectory planner is designed to consider the worst-case arising from prediction uncertainty. The results show that the proposed method can improve the safety of trajectory planning under the prediction uncertainty caused by insufficient data. At the same time, with sufficient data, the framework will not lead to overly conservative results. This technology helps to improve the safety and reliability of autonomous vehicles under the long-tail data distribution of the real world.