Bachelor and Master Theses

Title: A Method for Optimised Allocation of System Architectures with Real-time Constraints
Subject: Computer Science
Level: Advanced
Description: There is currently a strong automation trend in the vehicle industry and many vehicle manufactur- ers are working in this field to build knowledge and develop products. An autonomous vehicle is typically capable of sensing its environment and navigating without human input. As a result, the autonomous system must be designed to handle unexpected situations and failures, without posing any hazards to people and other objects, while at the same time meeting demands on efficiency and safety. In this regard, the system architecture plays an important role and its structure has a significant impact on the facilitation and allocation of functions on the system. As such, attention must be given to the system architecture, both in regards to hardware and software.

Although developing a system on a single hardware platform is fast and efficient, it leaves the system vulnerable as it is inherently susceptible to a single-point-of-failure. The same problem is prevalent in every area of vehicular automation in which a centralised computer system is in use, and, wherein safety is of great concern. Decentralisation in the system architecture considers cooperative operation when distributing a set of functionalities across multiple discrete hardware platforms. The means of communication and load distribution are two main focal points in this. Decentralisation within automation systems should, however, not infringe on the productivity of the system. There should not be a noticeable decrease in productivity in a decentralised system compared to a centralised one. Although performance and operational speed make up for a large portion of such metrics, they may both be sacrificed for increased up-time, which, in turn, accounts for another major portion of the productivity metric.

Safety-critical aspects of the system need to be identified and given special attention while discussing decentralisation. They generally have very strict requirements on redundancy and tim- ing. The safety-critical parts of a machine automation system may also need to be certified by a third party, in order to verify compliance to relevant industry standards and the requirements and guarantees on safety.

Distributing a system’s functionality across multiple discrete hardware platforms can generally help to reduce the risk of a single-point-of-failure. In the vehicular domain, knowing the implications of decentralisation in an automation system would be beneficial for future vehicular automation development. Deciding on an optimal system architecture would, by extension, likely result in safer products. Another major benefit of decentralised systems is the induced executional independence and ease of continuous development. A new, or updated, subsystem can be verified and tested independently from the remainder of the system, reducing the complexity and scope. Certifying safety-critical parts of the system is a costly process, and therefore, the implementational independence of safety-critical functionality is also important in this regard, especially considering cost. Therefore, it is of worth investigating the implications of such concepts in the case of autonomous vehicles and assessing different levels of decentralisation.
Company: Volvo Construction Equipment, kontaktperson: Jimmie Wiklander
Prel. end date: 2018-05-31
Presentation date: 2018-05-31
Student: Arman Hasanbegovic ahc16002@student.mdh.se
Student: Marcus Ventovaara mva13001@student.mdh.se
IDT supervisors:
Saad Mubeen
saad.mubeen@mdh.se, +4621103191
     Mikael Ekström
mikael.ekstrom@mdh.se, +46-21-101671
Examinator: Mikael Sjödin
Mikael Sjödin
mikael.sjodin@mdh.se, +46 70 288 2829

Rapport och bilagor

Size

Senaste uppdatering

TR2174.pdf

996012

2018-06-12, 16:55


  • Mälardalen University |
  • Box 883 |
  • 721 23 Västerås/Eskilstuna |
  • 021-101300, 016-153600 |
  • webmaster |
  • Latest update: 2018.05.24