Towards Defensive Autonomous Driving: Collecting and Probing Driving Demonstrations of Mixed Qualities
This work addresses the need for diverse driving data to improve safety in autonomous vehicles, but it is incremental as it builds on existing OOD detection methods with a new dataset.
The authors tackled the problem of ensuring safety in autonomous driving by creating the R3 Driving Dataset, which includes abnormal driving behaviors categorized into eight types and 369 situations, and found that combining uncertainty estimation and anomaly detection methods can discriminate most abnormal cases.
Designing or learning an autonomous driving policy is undoubtedly a challenging task as the policy has to maintain its safety in all corner cases. In order to secure safety in autonomous driving, the ability to detect hazardous situations, which can be seen as an out-of-distribution (OOD) detection problem, becomes crucial. However, most conventional datasets only provide expert driving demonstrations, although some non-expert or uncommon driving behavior data are needed to implement a safety guaranteed autonomous driving platform. To this end, we present a novel dataset called the R3 Driving Dataset, composed of driving data with different qualities. The dataset categorizes abnormal driving behaviors into eight categories and 369 different detailed situations. The situations include dangerous lane changes and near-collision situations. To further enlighten how these abnormal driving behaviors can be detected, we utilize different uncertainty estimation and anomaly detection methods to the proposed dataset. From the results of the proposed experiment, it can be inferred that by using both uncertainty estimation and anomaly detection, most of the abnormal cases in the proposed dataset can be discriminated. The dataset of this paper can be downloaded from https://rllab-snu.github.io/projects/R3-Driving-Dataset/doc.html.