ML-MAS: a Hybrid AI Framework for Self-Driving Vehicles

Rafael C. Cardoso

ML-MAS: a Hybrid AI Framework for Self-Driving Vehicles

Rafael C. Cardoso^* (Corresponding Author)

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

Abstract

Machine Learning (ML) techniques have been shown to be widely successful in environments that require processing a large amount of perception data, such as in fully autonomous self-driving vehicles. Nevertheless, in such a complex domain, ML-only approaches have several limitations. In this paper, we propose a hybrid Artificial Intelligence (AI) framework for fully autonomous self-driving vehicles that uses rule-based agents from symbolic AI to supplement the ML models in their decision-making. Our framework is evaluated using routes from the CARLA simulation environment, and has been shown to improve the driving score of the ML models.

Original language	English
Title of host publication	Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023)
Place of Publication	London
Publisher	International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Number of pages	9
Publication status	Accepted/In press - 3 Jan 2023
Event	22nd International Conference on Autonomous Agents and Multiagent Systems - London ExCeL conference centre, London, United Kingdom Duration: 29 May 2023 → 2 Jun 2023 https://aamas2023.soton.ac.uk/

Conference

Conference	22nd International Conference on Autonomous Agents and Multiagent Systems
Abbreviated title	AAMAS 2023
Country/Territory	United Kingdom
City	London
Period	29/05/23 → 2/06/23
Internet address	https://aamas2023.soton.ac.uk/

Keywords

Hybrid AI
BDI
deep learning
self-driving vehicles
CARLA

Cite this

ML-MAS: a Hybrid AI Framework for Self-Driving Vehicles. / Cardoso, Rafael C. (Corresponding Author).

Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023). London : International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2023.

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

Cardoso, RC 2023, ML-MAS: a Hybrid AI Framework for Self-Driving Vehicles. in Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023). International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), London, 22nd International Conference on Autonomous Agents and Multiagent Systems, London, United Kingdom, 29/05/23.

@inproceedings{6cc46808aefb4464a0167562e29cc888,

title = "ML-MAS: a Hybrid AI Framework for Self-Driving Vehicles",

abstract = "Machine Learning (ML) techniques have been shown to be widely successful in environments that require processing a large amount of perception data, such as in fully autonomous self-driving vehicles. Nevertheless, in such a complex domain, ML-only approaches have several limitations. In this paper, we propose a hybrid Artificial Intelligence (AI) framework for fully autonomous self-driving vehicles that uses rule-based agents from symbolic AI to supplement the ML models in their decision-making. Our framework is evaluated using routes from the CARLA simulation environment, and has been shown to improve the driving score of the ML models.",

keywords = "Hybrid AI, BDI, deep learning, self-driving vehicles, CARLA",

author = "Cardoso, {Rafael C.}",

year = "2023",

month = jan,

day = "3",

language = "English",

booktitle = "Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023)",

publisher = "International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)",

note = "22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023 ; Conference date: 29-05-2023 Through 02-06-2023",

url = "https://aamas2023.soton.ac.uk/",

}

TY - GEN

T1 - ML-MAS: a Hybrid AI Framework for Self-Driving Vehicles

AU - Cardoso, Rafael C.

PY - 2023/1/3

Y1 - 2023/1/3

N2 - Machine Learning (ML) techniques have been shown to be widely successful in environments that require processing a large amount of perception data, such as in fully autonomous self-driving vehicles. Nevertheless, in such a complex domain, ML-only approaches have several limitations. In this paper, we propose a hybrid Artificial Intelligence (AI) framework for fully autonomous self-driving vehicles that uses rule-based agents from symbolic AI to supplement the ML models in their decision-making. Our framework is evaluated using routes from the CARLA simulation environment, and has been shown to improve the driving score of the ML models.

AB - Machine Learning (ML) techniques have been shown to be widely successful in environments that require processing a large amount of perception data, such as in fully autonomous self-driving vehicles. Nevertheless, in such a complex domain, ML-only approaches have several limitations. In this paper, we propose a hybrid Artificial Intelligence (AI) framework for fully autonomous self-driving vehicles that uses rule-based agents from symbolic AI to supplement the ML models in their decision-making. Our framework is evaluated using routes from the CARLA simulation environment, and has been shown to improve the driving score of the ML models.

KW - Hybrid AI

KW - BDI

KW - deep learning

KW - self-driving vehicles

KW - CARLA

M3 - Published conference contribution

BT - Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023)

PB - International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)

CY - London

T2 - 22nd International Conference on Autonomous Agents and Multiagent Systems

Y2 - 29 May 2023 through 2 June 2023

ER -

ML-MAS: a Hybrid AI Framework for Self-Driving Vehicles

Abstract

Conference

Keywords

Fingerprint

Cite this