scholarly journals Mobile Robot Feature-Based SLAM Behavior Learning, and Navigation in Complex Spaces

2019 ◽  
Author(s):  
Ebrahim A. Mattar
Keyword(s):  
Mobile Robot ◽  
Complex Spaces ◽  
Behavior Learning ◽  
Feature Based

Autonomous feature-based exploration using a low-cost mobile robot

2014 ◽  
Author(s):  
Luciano Buonocore ◽  
Areolino de Almeida Neto ◽  
Cairo Lucio Nascimento Junior
Keyword(s):  
Mobile Robot ◽  
Low Cost ◽  
Feature Based

Experimental Study on Behavior Acquisition of Mobile Robot by Deep Q-Network

2017 ◽  
Vol 21 (5) ◽  
pp. 840-848 ◽  
Author(s):  
Hikaru Sasaki ◽  
Tadashi Horiuchi ◽  
Satoru Kato ◽  
◽  
◽  
...  
Keyword(s):  
Mobile Robot ◽  
Visual Information ◽  
Profit Sharing ◽  
Simulation Software ◽  
Learning Performance ◽  
Simulation Environment ◽  
Q Learning ◽  
Robot Behavior ◽  
Target Network ◽  
Behavior Learning

Deep Q-network (DQN) is one of the most famous methods of deep reinforcement learning. DQN approximates the action-value function using Convolutional Neural Network (CNN) and updates it using Q-learning. In this study, we applied DQN to robot behavior learning in a simulation environment. We constructed the simulation environment for a two-wheeled mobile robot using the robot simulation software, Webots. The mobile robot acquired good behavior such as avoiding walls and moving along a center line by learning from high-dimensional visual information supplied as input data. We propose a method that reuses the best target network so far when the learning performance suddenly falls. Moreover, we incorporate Profit Sharing method into DQN in order to accelerate learning. Through the simulation experiment, we confirmed that our method is effective.

Real-Time Adaptive Fuzzy Motivations for Evolutionary Behavior Learning by a Mobile Robot

2006 ◽  
pp. 101-111
Author(s):  
Wolfgang Freund ◽  
Tomas Arredondo Vidal ◽  
César Muñoz ◽  
Nicolás Navarro ◽  
Fernando Quirós
Keyword(s):  
Mobile Robot ◽  
Real Time ◽  
Adaptive Fuzzy ◽  
Behavior Learning

KSU-IMR Mobile Robot Navigation Maps Building and Learning

2015 ◽  
Vol 789-790 ◽  
pp. 717-722
Author(s):  
Ebrahim Mattar ◽  
K. Al Mutib ◽  
M. AlSulaiman ◽  
Hedjar Ramdane
Keyword(s):  
Mobile Robot ◽  
Dimensionality Reduction ◽  
Robot Navigation ◽  
Mobile Robot Navigation ◽  
Research Outcomes ◽  
Neuro Fuzzy ◽  
Robot Behavior ◽  
Behavior Learning ◽  
Mobile Maps

It is essential to learn a robot navigation environment. We describe research outcomes for KSU-IMR mapping and intelligence. This is for navigating and robot behavior learning. The mobile maps learning and intelligence was based on hybrid paradigms and AI functionaries. Intelligence was based on ANN-PCA for dimensionality reduction, and Neuro-Fuzzy architecture.

Sign in / Sign up

Export Citation Format

Share Document