Towards Defensive Autonomous Driving: Collecting and Probing Driving Demonstrations of Mixed Qualities

09/16/2021
by   Jeongwoo Oh, et al.
0

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.

READ FULL TEXT

page 1

page 4

research
08/04/2023

Synthetic outlier generation for anomaly detection in autonomous driving

Anomaly detection, or outlier detection, is a crucial task in various do...
research
02/25/2019

Towards Corner Case Detection for Autonomous Driving

The progress in autonomous driving is also due to the increased availabi...
research
02/11/2021

Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approaches

Automated driving has become a major topic of interest not only in the a...
research
04/27/2020

Multi-IF : An Approach to Anomaly Detection in Self-Driving Systems

Autonomous driving vehicles (ADVs) are implemented with rich software fu...
research
05/16/2018

ChoiceNet: Robust Learning by Revealing Output Correlations

In this paper, we focus on the supervised learning problem with corrupte...
research
05/28/2021

Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving

In this paper, we show how uncertainty estimation can be leveraged to en...
research
12/07/2021

Causal Imitative Model for Autonomous Driving

Imitation learning is a powerful approach for learning autonomous drivin...

Please sign up or login with your details

Forgot password? Click here to reset