Speed Control Optimization for Autonomous Vehicles with Metaheuristics
The development of speed controllers under execution in autonomous vehicles within their dynamic driving task (DDT) is a traditional research area from the point of view of control techniques. In this regard, Proportional − Integral − Derivative (PID) controllers are the most wid...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-03-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/9/4/551 |
id |
doaj-d6cb7e69edbe4c74b3e8e78ec1001011 |
---|---|
record_format |
Article |
spelling |
doaj-d6cb7e69edbe4c74b3e8e78ec10010112020-11-25T01:44:35ZengMDPI AGElectronics2079-92922020-03-019455110.3390/electronics9040551electronics9040551Speed Control Optimization for Autonomous Vehicles with MetaheuristicsJosé Eugenio Naranjo0Francisco Serradilla1Fawzi Nashashibi2INSIA, Artificial Intelligence Department, Universidad Politécnica de Madrid, 28031 Madrid, SpainINSIA, Artificial Intelligence Department, Universidad Politécnica de Madrid, 28031 Madrid, SpainNational Institute for Research in Computer Science and Automation (INRIA), 75012 Paris, FranceThe development of speed controllers under execution in autonomous vehicles within their dynamic driving task (DDT) is a traditional research area from the point of view of control techniques. In this regard, Proportional − Integral − Derivative (PID) controllers are the most widely used in order to meet the requirements of cruise control. However, fine tuning of the parameters associated with this type of controller can be complex, especially if it is intended to optimize them and reduce their characteristic errors. The objective of the work described in this paper is to evaluate the capacity of several metaheuristics for the adjustment of the parameters Kp, 1/Ti, and 1/Td of a PID controller to regulate the speed of a vehicle. To do this, an adjustment error function has been established from a linear combination of classic estimators of the goodness of the controller, such as overshoot, settling time (ts), steady-state error (ess), and the number of changes of sign of the signal (d). The error obtained when applying the controller has also been compared to a computational model of the vehicle after estimating the parameters Kp, Ki, and Kd, both for a setpoint sequence used in the adjustment of the system parameters and for a sequence not used during the adjustment, and therefore unknown by the system. The main novelty of the paper is to propose a new global error function, a function that enables the use of heuristic optimization methods for PID tuning. This optimization has been carried out by using three methods: genetic algorithms (GA), memetics algorithms (MA), and mesh adaptive direct search (MADS). The results of the application of the optimization methods using the proposed metric show that the accuracy of the PID controller is improved, compared with the classical optimization based on classical methods like the integral absolute error (IAE) or similar metrics, reducing oscillatory behaviours as well as minimizing the analysed performance indexes.https://www.mdpi.com/2079-9292/9/4/551autonomous vehiclesgenetic algorithmsintelligent controlcruise control |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
José Eugenio Naranjo Francisco Serradilla Fawzi Nashashibi |
spellingShingle |
José Eugenio Naranjo Francisco Serradilla Fawzi Nashashibi Speed Control Optimization for Autonomous Vehicles with Metaheuristics Electronics autonomous vehicles genetic algorithms intelligent control cruise control |
author_facet |
José Eugenio Naranjo Francisco Serradilla Fawzi Nashashibi |
author_sort |
José Eugenio Naranjo |
title |
Speed Control Optimization for Autonomous Vehicles with Metaheuristics |
title_short |
Speed Control Optimization for Autonomous Vehicles with Metaheuristics |
title_full |
Speed Control Optimization for Autonomous Vehicles with Metaheuristics |
title_fullStr |
Speed Control Optimization for Autonomous Vehicles with Metaheuristics |
title_full_unstemmed |
Speed Control Optimization for Autonomous Vehicles with Metaheuristics |
title_sort |
speed control optimization for autonomous vehicles with metaheuristics |
publisher |
MDPI AG |
series |
Electronics |
issn |
2079-9292 |
publishDate |
2020-03-01 |
description |
The development of speed controllers under execution in autonomous vehicles within their dynamic driving task (DDT) is a traditional research area from the point of view of control techniques. In this regard, Proportional − Integral − Derivative (PID) controllers are the most widely used in order to meet the requirements of cruise control. However, fine tuning of the parameters associated with this type of controller can be complex, especially if it is intended to optimize them and reduce their characteristic errors. The objective of the work described in this paper is to evaluate the capacity of several metaheuristics for the adjustment of the parameters Kp, 1/Ti, and 1/Td of a PID controller to regulate the speed of a vehicle. To do this, an adjustment error function has been established from a linear combination of classic estimators of the goodness of the controller, such as overshoot, settling time (ts), steady-state error (ess), and the number of changes of sign of the signal (d). The error obtained when applying the controller has also been compared to a computational model of the vehicle after estimating the parameters Kp, Ki, and Kd, both for a setpoint sequence used in the adjustment of the system parameters and for a sequence not used during the adjustment, and therefore unknown by the system. The main novelty of the paper is to propose a new global error function, a function that enables the use of heuristic optimization methods for PID tuning. This optimization has been carried out by using three methods: genetic algorithms (GA), memetics algorithms (MA), and mesh adaptive direct search (MADS). The results of the application of the optimization methods using the proposed metric show that the accuracy of the PID controller is improved, compared with the classical optimization based on classical methods like the integral absolute error (IAE) or similar metrics, reducing oscillatory behaviours as well as minimizing the analysed performance indexes. |
topic |
autonomous vehicles genetic algorithms intelligent control cruise control |
url |
https://www.mdpi.com/2079-9292/9/4/551 |
work_keys_str_mv |
AT joseeugenionaranjo speedcontroloptimizationforautonomousvehicleswithmetaheuristics AT franciscoserradilla speedcontroloptimizationforautonomousvehicleswithmetaheuristics AT fawzinashashibi speedcontroloptimizationforautonomousvehicleswithmetaheuristics |
_version_ |
1725027723488788480 |