Case Study: Verifying the Safety of an Autonomous Racing Car with a Neural Network Controller

Loading...
Thumbnail Image
Penn collection
Departmental Papers (CIS)
Degree type
Discipline
Subject
CPS Safe Autonomy
Neural Network Verification
Learning for Control
F1/10 Racing
Computer Engineering
Computer Sciences
Funder
Grant number
License
Copyright date
Distributor
Related resources
Contributor
Abstract

This paper describes a verification case study on an autonomous racing car with a neural network (NN) controller. Although several verification approaches have been recently proposed, they have only been evaluated on low-dimensional systems or systems with constrained environments. To explore the limits of existing approaches, we present a challenging benchmark in which the NN takes raw LiDAR measurements as input and outputs steering for the car. We train a dozen NNs using reinforcement learning (RL) and show that the state of the art in verification can handle systems with around 40 LiDAR rays. Furthermore, we perform real experiments to investigate the benefits and limitations of verification with respect to the sim2real gap, i.e., the difference between a system’s modeled and real performance. We identify cases, similar to the modeled environment, in which verification is strongly correlated with safe behavior. Finally, we illustrate LiDAR fault patterns that can be used to develop robust and safe RL algorithms.

Advisor
Date of presentation
2020-04-01
Conference name
Departmental Papers (CIS)
Conference dates
2023-05-17T23:32:14.000
Conference location
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
23rd ACM International Conference on Hybrid Systems: Computation and Control (HSCC 2020)(https://berkeleylearnverify.github.io/HSCC_2020/), Sydney, Australia, April 21-24, 2020
Recommended citation
Collection