Correcting Autonomous Driving Object Detection Misclassifications with Automated Commonsense Reasoning

TL;DR

This paper demonstrates how automated commonsense reasoning can correct object detection errors in autonomous vehicles, especially in scenarios with limited training data, thereby enhancing perception accuracy.

Contribution

It introduces a hybrid approach combining perception models with commonsense reasoning to improve object detection in abnormal scenarios for autonomous driving.

Findings

Commonsense reasoning corrects misclassifications in AV perception.

Hybrid models improve detection accuracy in rare scenarios.

Experiments in CARLA simulator validate the approach.

Abstract

Autonomous Vehicle (AV) technology has been heavily researched and sought after, yet there are no SAE Level 5 AVs available today in the marketplace. We contend that over-reliance on machine learning technology is the main reason. Use of automated commonsense reasoning technology, we believe, can help achieve SAE Level 5 autonomy. In this paper, we show how automated common-sense reasoning technology can be deployed in situations where there are not enough data samples available to train a deep learning-based AV model that can handle certain abnormal road scenarios. Specifically, we consider two situations where (i) a traffic signal is malfunctioning at an intersection and (ii) all the cars ahead are slowing down and steering away due to an unexpected obstruction (e.g., animals on the road). We show that in such situations, our commonsense reasoning-based solution accurately detects traffic light colors and obstacles not correctly captured by the AV's perception model. We also provide a pathway for efficiently invoking commonsense reasoning by measuring uncertainty in the computer vision model and using commonsense reasoning to handle uncertain scenarios. We describe our experiments conducted using the CARLA simulator and the results obtained. The main contribution of our research is to show that automated commonsense reasoning effectively corrects AV-based object detection misclassifications and that hybrid models provide an effective pathway to improving AV perception.