Learning architecture for real robotic systems-extension of connectionist Q-learning for continuous robot control domain

2002 ◽  
Author(s):  
F. Saito ◽  
T. Fukuda
Keyword(s):  
Robot Control ◽  
Robotic Systems ◽  
Q Learning

scholarly journals Reduction of Complexity in Q-Learning a Robot Control for an Assembly Cell by using Multiple Agents

2020 ◽  
Vol 30 (3) ◽  
pp. 117-124
Author(s):  
Georg Kunert ◽  
Thorsten Pawlette ◽  
Sven Hartmann
Keyword(s):  
Robot Control ◽  
Multiple Agents ◽  
Q Learning ◽  
Assembly Cell

Towards Concurrent Q-Learning on Linked Multi-Component Robotic Systems

2011 ◽  
pp. 463-470 ◽  
Author(s):  
Borja Fernandez-Gauna ◽  
Jose Manuel Lopez-Guede ◽  
Manuel Graña
Keyword(s):  
Robotic Systems ◽  
Q Learning

Matlab RTW-based Internet Accessible Remote Laboratory for Teaching Robot Control

2012 ◽  
pp. 362-379
Author(s):  
Zdenko Kovacic ◽  
Davor Jerbic ◽  
Vedran Vojvoda ◽  
Siniša Dujmovic
Keyword(s):  
Real Time ◽  
Management System ◽  
Web Application ◽  
Robot Control ◽  
Degrees Of Freedom ◽  
Robotic Systems ◽  
Remote Laboratory ◽  
Scara Robot ◽  
Control Schemes

This chapter describes the use of Matlab Real Time Workshop (RTW) for implementing an Internet Accessible Laboratory (IAL) for teaching robot control. The IAL architecture consists of three key components - IAL Web Application, IAL database, and a set of robot control schemes prepared for students’ laboratory curriculum that are running in Matlab RTW. The IAL management system supports multilingual access and enables easy addition of new users, new robotic systems, and new laboratory exercises related to robot control. The IAL functionality is demonstrated with the example of controlling a four degrees of freedom SCARA robot.

scholarly journals Deep SIMBAD: Active Landmark-based Self-localization Using Similarity-based Scene Descriptor

2021 ◽  
Author(s):  
kanji tanaka
Keyword(s):  
Robot Control ◽  
Nearest Neighbor ◽  
Inverted Index ◽  
Localization Task ◽  
State Recognition ◽  
Q Learning ◽  
Recognition Ability ◽  
Ill Posed ◽  
Visual Place Recognition ◽  
Next Best View

Landmark-based robot self-localization has attracted recent research interest as an efficient maintenance-free approach to visual place recognition (VPR) across domains (e.g., times of the day, weathers, seasons). However, landmark-based self-localization can be an ill-posed problem for a passive observer (e.g., manual robot control), as many viewpoints may not provide effective landmark view. Here, we consider active self-localization task by an active observer, and present a novel reinforcement-learning (RL) -based next-best-view (NBV) planner. Our contributions are summarized as follows. (1) SIMBAD-based VPR: We present a landmark ranking -based compact scene descriptor by introducing a deep-learning extension of similarity-based pattern recognition (SIMBAD). (2) VPR-to-NBV knowledge transfer: We tackle the challenge of RL under uncertainty (i.e., active self-localization) by transferring the VPR's state recognition ability to NBV. (3) NNQL-based NBV: We view the available VPR as the experience database by adapting a nearest-neighbor -based approximation of Q-learning (NNQL). The result is an extremely compact data structure that compresses both the VPR and NBV modules into a single incremental inverted index. Experiments using public NCLT dataset validate the effectiveness of the proposed approach.

scholarly journals Cooperative Multi-Agent Reinforcement Learning for Multi-Component Robotic Systems: guidelines for future research

2011 ◽  
Vol 2 (2) ◽  
Author(s):  
Manuel Graña ◽  
Borja Fernandez-Gauna ◽  
Jose Manuel Lopez-Guede
Keyword(s):  
Reinforcement Learning ◽  
Control Systems ◽  
Robot Control ◽  
Robotic Systems ◽  
Future Research ◽  
Multi Agent Systems ◽  
Feedback Information ◽  
Agent Systems ◽  
Innovative Solutions ◽  
Multi Agent

AbstractReinforcement Learning (RL) as a paradigm aims to develop algorithms that allow to train an agent to optimally achieve a goal with minimal feedback information about the desired behavior, which is not precisely specified. Scalar rewards are returned to the agent as response to its actions endorsing or opposing them. RL algorithms have been successfully applied to robot control design. The extension of the RL paradigm to cope with the design of control systems for Multi-Component Robotic Systems (MCRS) poses new challenges, mainly related to coping with scaling up of complexity due to the exponential state space growth, coordination issues, and the propagation of rewards among agents. In this paper, we identify the main issues which offer opportunities to develop innovative solutions towards fully-scalable cooperative multi-agent systems.

scholarly journals The Integration of Collaborative Robot Systems and Their Environmental Impacts

Processes ◽  
2020 ◽  
Vol 8 (4) ◽  
pp. 494 ◽  
Author(s):  
Lucian Stefanita Grigore ◽  
Iustin Priescu ◽  
Daniela Joita ◽  
Ionica Oncioiu
Keyword(s):  
Control Systems ◽  
Autonomous Vehicles ◽  
Robot Control ◽  
Sensory Feedback ◽  
Industrial Robots ◽  
Robotic Systems ◽  
Ground Vehicles ◽  
Robot Systems ◽  
Aerial Vehicle ◽  
Collaborative Robot

Today, industrial robots are used in dangerous environments in all sectors, including the sustainable energy sector. Sensors and processors collect and transmit information and data from users as a result of the application of robot control systems and sensory feedback. This paper proposes that the estimation of a collaborative robot system’s performance can be achieved by evaluating the mobility of robots. Scenarios have been determined in which an autonomous system has been used for intervention in crisis situations due to fire. The experimental model consists of three autonomous vehicles, two of which are ground vehicles and the other is an aerial vehicle. The conclusion of the research described in this paper highlights the fact that the integration of robotic systems made up of autonomous vehicles working in unstructured environments is difficult and at present there is no unitary analytical model.

Sign in / Sign up

Export Citation Format

Share Document