Detecting What Matters: A Novel Approach for Out-of-Distribution 3D Object Detection in Autonomous Vehicles

TL;DR

This paper introduces a new approach for autonomous vehicle object detection that focuses on identifying potentially harmful objects regardless of their class, improving safety by detecting out-of-distribution objects and assessing their danger.

Contribution

The paper presents a novel method that shifts from class-based detection to harm-based detection, enabling AVs to recognize and evaluate unseen objects for safety.

Findings

Effective detection of OOD objects

Accurate assessment of object harmfulness

Enhanced decision-making in dynamic environments

Abstract

Autonomous vehicles (AVs) use object detection models to recognize their surroundings and make driving decisions accordingly. Conventional object detection approaches classify objects into known classes, which limits the AV's ability to detect and appropriately respond to Out-of-Distribution (OOD) objects. This problem is a significant safety concern since the AV may fail to detect objects or misclassify them, which can potentially lead to hazardous situations such as accidents. Consequently, we propose a novel object detection approach that shifts the emphasis from conventional class-based classification to object harmfulness determination. Instead of object detection by their specific class, our method identifies them as either 'harmful' or 'harmless' based on whether they pose a danger to the AV. This is done based on the object position relative to the AV and its trajectory. With this metric, our model can effectively detect previously unseen objects to enable the AV to make safer real-time decisions. Our results demonstrate that the proposed model effectively detects OOD objects, evaluates their harmfulness, and classifies them accordingly, thus enhancing the AV decision-making effectiveness in dynamic environments.