Behavior Learning and Evolution of Individual Robot for Cooperative Behavior of Swarm Robot System

Swarm robotic systems (SRSs) are a type of multi-robot system in which robots operate without any form of centralized control. The typical design methodology for SRSs comprises a behavior-based approach, where the desired collective behavior is obtained manually by designing the behavior of individual robots in advance. In contrast, in an automatic design approach, a certain general methodology is adopted. This paper presents a deep reinforcement learning approach for collective behavior acquisition of SRSs. The swarm robots are expected to collect information in parallel and share their experience for accelerating their learning. We conducted real swarm robot experiments and evaluated the learning performance of the swarm in a scenario where the robots consecutively traveled between two landmarks.

Download Full-text

Object tracking algorithm of Swarm Robot System for using Polygon based Q-learning and parallel SVM

International Journal of Fuzzy Logic and Intelligent Systems ◽

10.5391/ijfis.2008.8.3.220 ◽

2008 ◽

Vol 8 (3) ◽

pp. 220-224 ◽

Cited By ~ 2

Author(s):

Snag-Wook Seo ◽

Hyun-Chang Yang ◽

Kwee-Bo Sim

Keyword(s):

Object Tracking ◽

Tracking Algorithm ◽

Robot System ◽

Q Learning ◽

Swarm Robot

Download Full-text

DEVELOPMENT OF LEADER AND FOLLOWER STRATEGY FOR SWARM ROBOT APPLICATIONS

Jurnal Teknologi ◽

10.11113/jt.v77.6791 ◽

2015 ◽

Vol 77 (28) ◽

Author(s):

Humairah Mansor ◽

Abdul Hamid Adom ◽

Norasmadi Abdul Rahim

Keyword(s):

Wireless Communication ◽

Mobile Robot ◽

Mobile Robots ◽

Communication Strategy ◽

Robot System ◽

Testing Environment ◽

Odour Source ◽

Wide Range ◽

Robust System ◽

Swarm Robot

Swarming robots basically consist of a group of several simple robots that interact and collaborate with each other to achieve shared goals. A single robot system is not suitable to be used as an agent for the navigation usually covers a wide range of area. Therefore, a group of simple robots is introduced. A group of robots can perform their tasks together in a more efficient way compared to a single robot; hence develop a more robust system. In order to interact, a wireless communication strategy is implemented to enable the group of mobile robots to perform their tasks. This project implements the swarming algorithm by supplementing the ability of mobile robot platforms with autonomy and odour detection. The work focused on the localization of chemical odour source in the testing environment and the leader and follower swarm formation through wireless communication. To enable the mobile robots to communicate with each other and able to perform leader and follower designation once the target has been found, the RSSI value of X-Bee module is used.

Download Full-text