Generating and Explaining Corner Cases Using Learnt Probabilistic Lane Graphs

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Maci, Enrik, Howard, Rhys, Kunze, Lars
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913262863384576
author Maci, Enrik
Howard, Rhys
Kunze, Lars
author_facet Maci, Enrik
Howard, Rhys
Kunze, Lars
contents Validating the safety of Autonomous Vehicles (AVs) operating in open-ended, dynamic environments is challenging as vehicles will eventually encounter safety-critical situations for which there is not representative training data. By increasing the coverage of different road and traffic conditions and by including corner cases in simulation-based scenario testing, the safety of AVs can be improved. However, the creation of corner case scenarios including multiple agents is non-trivial. Our approach allows engineers to generate novel, realistic corner cases based on historic traffic data and to explain why situations were safety-critical. In this paper, we introduce Probabilistic Lane Graphs (PLGs) to describe a finite set of lane positions and directions in which vehicles might travel. The structure of PLGs is learnt directly from spatio-temporal traffic data. The graph model represents the actions of the drivers in response to a given state in the form of a probabilistic policy. We use reinforcement learning techniques to modify this policy and to generate realistic and explainable corner case scenarios which can be used for assessing the safety of AVs.
format Preprint
id arxiv_https___arxiv_org_abs_2308_13658
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Generating and Explaining Corner Cases Using Learnt Probabilistic Lane Graphs
Maci, Enrik
Howard, Rhys
Kunze, Lars
Artificial Intelligence
Robotics
E.1; G.1.1; G.3; I.2.6; I.2.9; I.6.0
Validating the safety of Autonomous Vehicles (AVs) operating in open-ended, dynamic environments is challenging as vehicles will eventually encounter safety-critical situations for which there is not representative training data. By increasing the coverage of different road and traffic conditions and by including corner cases in simulation-based scenario testing, the safety of AVs can be improved. However, the creation of corner case scenarios including multiple agents is non-trivial. Our approach allows engineers to generate novel, realistic corner cases based on historic traffic data and to explain why situations were safety-critical. In this paper, we introduce Probabilistic Lane Graphs (PLGs) to describe a finite set of lane positions and directions in which vehicles might travel. The structure of PLGs is learnt directly from spatio-temporal traffic data. The graph model represents the actions of the drivers in response to a given state in the form of a probabilistic policy. We use reinforcement learning techniques to modify this policy and to generate realistic and explainable corner case scenarios which can be used for assessing the safety of AVs.
title Generating and Explaining Corner Cases Using Learnt Probabilistic Lane Graphs
topic Artificial Intelligence
Robotics
E.1; G.1.1; G.3; I.2.6; I.2.9; I.6.0
url https://arxiv.org/abs/2308.13658