An adaptive system for autonomous driving
- PDF / 1,308,796 Bytes
- 24 Pages / 439.642 x 666.49 pts Page_size
- 86 Downloads / 261 Views
An adaptive system for autonomous driving Martin Zimmermann1 · Franz Wotawa1
© The Author(s) 2020
Abstract Having systems that can adapt themselves in case of faults or changing environmental conditions is of growing interest for industry and especially for the automotive industry considering autonomous driving. In autonomous driving, it is vital to have a system that is able to cope with faults in order to enable the system to reach a safe state. In this paper, we present an adaptive control method that can be used for this purpose. The method selects alternative actions so that given goal states can be reached, providing the availability of a certain degree of redundancy. The action selection is based on weight models that are adapted over time, capturing the success rate of certain actions. Besides the method, we present a Java implementation and its validation based on two case studies motivated by the requirements of the autonomous driving domain. We show that the presented approach is applicable both in case of environmental changes but also in case of faults occurring during operation. In the latter case, the methods provide an adaptive behavior very much close to the optimal selection. Keywords Self-adaptive systems · Validation using simulation · Adaptive control PACS 68T05
1 Introduction Our modern society relies more and more on various kinds of systems ranging from basic infrastructure like communication or power transmission networks to entertainment. Some of these systems are safety-critical like vehicles or airplanes where faults occurring at runtime may harm people, which has to be prevented by taking appropriate measures during development. In addition, there seems to be a trend for increased digitalization and automation for enabling new opportunities that capture almost all parts of our daily lives. For example, tight integration of product development and manufacturing considering user Franz Wotawa
[email protected] Martin Zimmermann [email protected] 1
Technische Universit¨at Graz, Institute for Software Technology, Christian Doppler Lab for Quality Assurance Methodologies for Cyber-Physical Systems, Inffeldgasse 16b, 8010 Graz, Austria
Software Quality Journal
requirements potentially lead to mass customization where people can order one specific product especially tailored to fit their needs. A challenge of increased pervasion of systems into our society is that we more and more depend on the correct functioning of these systems. Hence, it is of uttermost importance that the systems work as expected even in case of unexpected environmental changes or faults occurring during operation. In the automotive industry, there is the additional motivation of avoiding traffic accidents and, therefore, saving lives behind further information. Bringing truly autonomous driving into practice, there are at least two challenges to solve. First, we have to provide guarantees that the autonomous vehicle is trustworthy providing the expected behavior. This requires extensive testing and
Data Loading...
