Learning to Drive (Efficiently)

被引：1

作者：

Dominka, Sven ^{[1
]}

Doppler, Joerg ^{[1
]}

Smith, Henrik ^{[1
]}

Litschauer, Teresa ^{[1
]}

Laflamme, Catherine ^{[2
]}

机构：

[1] Robert Bosch AG, Bosch Engn GmbH, Vienna, Austria

[2] Fraunhofer Austria Res GmbH, Wattens, Austria

来源：

2024 IEEE INTERNATIONAL CONFERENCE ON ELECTRO INFORMATION TECHNOLOGY, EIT 2024 | 2024年

关键词：

reinforcement learning; embedded software; automotive; powertrain; control unit software; REINFORCEMENT; OPTIMIZATION; FRAMEWORK; VEHICLES;

D O I：

10.1109/eIT60633.2024.10609861

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The development of modern automotive powertrain control software is subject to various requirements ranging from safety, comfort, emission reduction, performance to efficiency. Consequently, the software engineering process is both complex and time consuming. To reduce these efforts, we explore the usage of reinforcement learning within the powertrain control software engineering process. We aim to automate parts of the software engineering process, especially the parameterization of embedded software. We will introduce the overall concept and current state of our evaluation based on an (initial) use-case and will discuss the associated limits and boundaries.

引用

页码：111 / 116

页数：6

共 25 条

[1]

Chen IM, 2019, IEEE INT C INTELL TR, P2620, DOI 10.1109/ITSC.2019.8917076

[2]

Dominka Sven, 2018, 2018 IEEE Industrial Cyber-Physical Systems (ICPS). Proceedings, P324, DOI 10.1109/ICPHYS.2018.8387679

[3] Automotive Feature Coordination based on a Machine-Learning Approach [J].

Dominka, Sven ;

Tabrizi, Sarah ;

Mandl, Michael ;

Duebner, Michael .

2021 IEEE 11TH ANNUAL COMPUTING AND COMMUNICATION WORKSHOP AND CONFERENCE (CCWC), 2021, :726-731

[4] Deep Q-Learning Based Energy Management Strategy for a Series Hybrid Electric Tracked Vehicle and Its Adaptability Validation [J].

He, Dingbo ;

Zou, Yuan ;

Wu, Jinlong ;

Zhang, Xudong ;

Zhang, Zhigang ;

Wang, Ruizhi .

2019 IEEE TRANSPORTATION ELECTRIFICATION CONFERENCE AND EXPO (ITEC), 2019,

[5] An Edge Computing Framework for Powertrain Control System Optimization of Intelligent and Connected Vehicles Based on Curiosity-Driven Deep Reinforcement Learning [J].

Hu, Bo ;

Li, Jiaxi .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2021, 68 (08) :7652-7661

[6]

Hu S., 2021, 2021 5 CAA INT C VEH, P1, DOI [10.1109/CVCI54083.2021.9661213, DOI 10.1109/CVCI54083.2021.9661213]

[7]

Jia X, 2020, IEEE SYS MAN CYBERN, P2432, DOI [10.1109/SMC42975.2020.9283452, 10.1109/smc42975.2020.9283452]

[8] A Decentralized Multi-agent Energy Management Strategy Based on a Look-Ahead Reinforcement Learning Approach [J].

Khalatbarisoltani A. ;

Kandidayeni M. ;

Boulon L. ;

Hu X. .

SAE International Journal of Electrified Vehicles, 2021, 11 (02)

[9]

Lee W., 2021, SAE WCX DIG SUMM, DOI [10.4271/2021-01-0434, DOI 10.4271/2021-01-0434]

[10]

Liessner R., 2018, ICAART (2), P61, DOI DOI 10.5220/0006573000610072

← 1 2 3 →