The development of the automotive industry toward autonomous vehicles creates a new set of requirements for real-time scheduling, due to the rocketing complexity. To start with, while scheduling theories for simple task models and uniprocessors have been well established, multiprocessors are being deployed and dependencies between tasks need to be considered. In addition, reliability is a safety-related issue, especially when there is large-scale resource sharing. On communication, the in-vehicle backbone network is migrating to Ethernet. Eventually, scheduling/controller co-design from the cyber-physical systems (CPS) perspective is desired. In this chapter, we present three interconnected fundamental works along the above directions. First, we introduce a concurrent provider and consumer (CPC) model and a novel scheduling method that orders the nodes. Second, we present the first fault-tolerant multiprocessor resource sharing protocol (namely MSRP-FT) and a system execution model that supports the application of MSRP-FT in mixed-criticality systems (MCS). Third, we present the first fixed-priority scheduling (FPS) approach for TSN and a finer-grained frame-level response time analysis. Moreover, we formulate a co-design optimization problem to decide the sampling periods and poles of real-time controllers with settling time as the objective to minimize, whilst satisfying the schedulability constraint.
Evolvement of Scheduling Theories for Autonomous Vehicles
Machine Learning and Optimization Techniques for Automotive Cyber-Physical Systems ; Kapitel : 2 ; 43-80
2023-03-27
38 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Distributed traffic scheduling for autonomous self-driving vehicles
Europäisches Patentamt | 2021
|Centralized scheduling system for operating autonomous driving vehicles
Europäisches Patentamt | 2020
|Communication scheduling for CAN bus autonomous underwater vehicles
Tema Archiv | 2006
|DISTRIBUTED TRAFFIC SCHEDULING FOR AUTONOMOUS SELF-DRIVING VEHICLES
Europäisches Patentamt | 2020
|Lane change scheduling for connected and autonomous vehicles
Elsevier | 2022
|