Distributing Tasks in Multi-agent Robotic System for Human-Robot Interaction Applications

2020 ◽  
pp. 99-106
Author(s):  
Rinat Galin ◽  
Roman Meshcheryakov ◽  
Saniya Kamesheva
Keyword(s):  
Robotic System ◽  
Human Robot Interaction ◽  
Robot Interaction ◽  
Multi Agent

scholarly journals Calibrating intuitive and natural human–robot interaction and performance for power-assisted heavy object manipulation using cognition-based intelligent admittance control schemes

2018 ◽  
Vol 15 (4) ◽  
pp. 172988141877319 ◽  
Author(s):  
S M Mizanoor Rahman ◽  
Ryojun Ikeura
Keyword(s):  
Predictive Control ◽  
Optimization Algorithm ◽  
Weight Perception ◽  
Robotic System ◽  
Human Robot Interaction ◽  
Admittance Control ◽  
Robot Interaction ◽  
Heavy Object ◽  
Control Scheme ◽  
And Performance

In the first step, a one degree of freedom power assist robotic system is developed for lifting lightweight objects. Dynamics for human–robot co-manipulation is derived that includes human cognition, for example, weight perception. A novel admittance control scheme is derived using the weight perception–based dynamics. Human subjects lift a small-sized, lightweight object with the power assist robotic system. Human–robot interaction and system characteristics are analyzed. A comprehensive scheme is developed to evaluate the human–robot interaction and performance, and a constrained optimization algorithm is developed to determine the optimum human–robot interaction and performance. The results show that the inclusion of weight perception in the control helps achieve optimum human–robot interaction and performance for a set of hard constraints. In the second step, the same optimization algorithm and control scheme are used for lifting a heavy object with a multi-degree of freedom power assist robotic system. The results show that the human–robot interaction and performance for lifting the heavy object are not as good as that for lifting the lightweight object. Then, weight perception–based intelligent controls in the forms of model predictive control and vision-based variable admittance control are applied for lifting the heavy object. The results show that the intelligent controls enhance human–robot interaction and performance, help achieve optimum human–robot interaction and performance for a set of soft constraints, and produce similar human–robot interaction and performance as obtained for lifting the lightweight object. The human–robot interaction and performance for lifting the heavy object with power assist are treated as intuitive and natural because these are calibrated with those for lifting the lightweight object. The results also show that the variable admittance control outperforms the model predictive control. We also propose a method to adjust the variable admittance control for three degrees of freedom translational manipulation of heavy objects based on human intent recognition. The results are useful for developing controls of human friendly, high performance power assist robotic systems for heavy object manipulation in industries.

scholarly journals Dynamic Input Deep Learning Control of Artificial Avatars in a Multi-Agent Joint Motor Task

2021 ◽  
Vol 8 ◽  
Author(s):  
Maria Lombardi ◽  
Davide Liuzza ◽  
Mario di Bernardo
Keyword(s):  
Motor Coordination ◽  
Motor Task ◽  
Human Robot Interaction ◽  
Artificial Agents ◽  
Artificial Agent ◽  
Common Goal ◽  
Robot Interaction ◽  
Joint Task ◽  
Multi Agent ◽  
Human Motor

In many real-word scenarios, humans and robots are required to coordinate their movements in joint tasks to fulfil a common goal. While several examples regarding dyadic human robot interaction exist in the current literature, multi-agent scenarios in which one or more artificial agents need to interact with many humans are still seldom investigated. In this paper we address the problem of synthesizing an autonomous artificial agent to perform a paradigmatic oscillatory joint task in human ensembles while exhibiting some desired human kinematic features. We propose an architecture based on deep reinforcement learning which is flexible enough to make the artificial agent interact with human groups of different sizes. As a paradigmatic coordination task we consider a multi-agent version of the mirror game, an oscillatory motor task largely used in the literature to study human motor coordination.

Mapping Hybrid Agencies Through Multiagent Systems

2009 ◽  
pp. 215-227
Author(s):  
Samuel G. Collins ◽  
Goran Trajkovski
Keyword(s):  
Multiagent Systems ◽  
Human Subjects ◽  
Human Robot Interaction ◽  
Robot Interaction ◽  
Social Phenomena ◽  
Motor Abilities ◽  
Social Actions ◽  
Multi Agent ◽  
Interaction Experiment ◽  
The One

In this chapter, we give an overview of the results of a Human-Robot Interaction experiment, in a near zerocontext environment. We stimulate the formation of a network joining together human agents and non-human agents, in order to examine emergent conditions and social actions. Human subjects, in teams of three to four, are presented with a task–to coax a robot (by any means) from one side of a table to the other–not knowing with what sensory and motor abilities the robotic structure is equipped. On the one hand, the “goal” of the exercise is to “move” the robot through any linguistic or paralinguistic means. But, from the perspective of the investigators, the goal is both broader and more nebulous–to stimulate any emergent interactions whatsoever between agents, human or non-human. Here we discuss emergent social phenomena in this assemblage of human and machine, in particular, turn-taking and discourse, suggesting (counter-intuitively) that the “transparency” of non-human agents may not be the most effective way to generate multi-agent sociality.

scholarly journals Force/position control of a robot manipulator for human-robot interaction

2016 ◽  
Vol 20 (suppl. 2) ◽  
pp. 537-548 ◽  
Author(s):  
Paramin Neranon ◽  
Robert Bicker
Keyword(s):  
Control System ◽  
Real Time ◽  
Position Control ◽  
Force Measurement ◽  
Robot Manipulator ◽  
Robotic System ◽  
Human Robot Interaction ◽  
Robot Interaction ◽  
Integral Control ◽  
Proportional Integral

With regard to both human and robot capabilities, human-robot interaction provides several benefits, and this will be significantly developed and implemented. This work focuses on the development of real-time external force/position control used for human-robot interaction. The force-controlled robotic system integrated with proportional integral control was performed and evaluated to ensure its reliably and timely operational characteristics, in which appropriate proportional integral gains were experimentally adopted using a set of virtual crank-turning tests. The designed robotic system is made up of a robot manipulator arm, an ATI Gamma multi-axis force/torque sensor and a real-time external PC based control system. A proportional integral controller has been developed to provide stable and robust force control on unknown environmental stiffness and motion. To quantify its effectiveness, the robotic system has been verified through a comprehensive set of experiments, in which force measurement and ALTER real-time path control systems were evaluated. In summary, the results indicated satisfactorily stable performance of the robot force/position control system. The gain tuning for proportional plus integral control algorithm was successfully implemented. It can be reported that the best performance as specified by the error root mean square method of the radial force is observed with proportional and integral gains of 0.10 and 0.005 respectively.

Sign in / Sign up

Export Citation Format

Share Document