Object criticality for safer navigation

TL;DR

This paper explores how prioritizing relevant objects detected in autonomous driving can enhance safety and trajectory planning, proposing a strategy to filter objects based on relevance to reduce risks.

Contribution

It introduces a method to configure object detectors to extract relevance information and demonstrates how this improves trajectory safety and quality in autonomous driving.

Findings

Filtering by relevance reduces missed relevant objects.

Relevance-based filtering decreases dangerous trajectories.

Trajectory quality improves with relevance-aware detection.

Abstract

Object detection in autonomous driving consists in perceiving and locating instances of objects in multi-dimensional data, such as images or lidar scans. Very recently, multiple works are proposing to evaluate object detectors by measuring their ability to detect the objects that are most likely to interfere with the driving task. Detectors are then ranked according to their ability to detect the most relevant objects, rather than the highest number of objects. However there is little evidence so far that the relevance of predicted object may contribute to the safety and reliability improvement of the driving task. This position paper elaborates on a strategy, together with partial results, to i) configure and deploy object detectors that successfully extract knowledge on object relevance, and ii) use such knowledge to improve the trajectory planning task. We show that, given an object detector, filtering objects based on their relevance, in combination with the traditional confidence threshold, reduces the risk of missing relevant objects, decreases the likelihood of dangerous trajectories, and improves the quality of trajectories in general.