Learning and Leveraging Conventions in the Design of Haptic Shared Control Paradigms for Steering a Ground Vehicle

The main objective of this paper is to establish a framework to study the co-adaptation between humans and automation systems in a haptic shared control framework. We specifically used this framework to design control transfer strategies between humans and automation systems to resolve a conflict wh...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of control, automation, and systems Jg. 21; H. 10; S. 3324 - 3335
Hauptverfasser: Izadi, Vahid, Ghasemi, Amir H.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Bucheon / Seoul Institute of Control, Robotics and Systems and The Korean Institute of Electrical Engineers 01.10.2023
Springer Nature B.V
제어·로봇·시스템학회
Schlagworte:
Adaptation
Automation
Control
Conventions
Cost function
Design
Engineering
Human performance
Mechatronics
Modular structures
Optimization
Regular Papers
Representations
Robotics
Steering
제어계측공학
Conventions and co-adaption
semi-automated vehicles
human-robot interaction
haptic shared control
ISSN:1598-6446, 2005-4092
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The main objective of this paper is to establish a framework to study the co-adaptation between humans and automation systems in a haptic shared control framework. We specifically used this framework to design control transfer strategies between humans and automation systems to resolve a conflict when co-steering a semi-automated ground vehicle. The proposed framework contains three main parts. First, we defined a modular structure to separate partner-specific strategies from task-dependent representations and use this structure to learn different co-adaption strategies. In this structure, we assume the human and automation steering commands can be determined by optimizing cost functions. For each agent, the costs are defined as a combination of a set of hand-coded features and vectors of weights. The hand-coded features can be selected to describe task-dependent representations. On the other hand, the weight distributions over these features can be used as a proxy to determine the partner-specific conventions. Second, to leverage the learned co-adaptation strategies, we developed a map connecting different strategies to the outputs of human-automation interactions by employing a collaborative-competitive game concept. Finally, using the map, we designed an adaptable automation system capable of co-adapting to human driver’s strategies. Specifically, we designed an episode-based policy search using the deep deterministic policy gradients technique to determine the optimal weights vector distribution of automation’s cost function. The simulation results demonstrate that the handover strategies designed based on co-adaption between human and automation systems can successfully resolve a conflict and improve the performance of the human automation teaming.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
http://link.springer.com/article/10.1007/s12555-022-0509-6
ISSN:1598-6446
2005-4092
DOI:10.1007/s12555-022-0509-6