Gait identification and optimisation for amphi-underwater robot by using ant colony algorithm
Manoeuvrable robot commonly has become the focus of the latest heated issues especially in applications that involved disaster rescue, military missions and underwater or extra-terrestrial explorations. Currently, the manoeuvrable robot is controlled manually by the operator and it’s a wheeled type....
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Blue Eyes Intelligence Engineering and Sciences Publication
2019
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/79646/ http://irep.iium.edu.my/79646/ http://irep.iium.edu.my/79646/1/79646_Gait%20identification%20and%20optimisation.pdf http://irep.iium.edu.my/79646/2/79646_Gait%20identification%20and%20optimisation_SCOPUS.pdf |
| Summary: | Manoeuvrable robot commonly has become the focus of the latest heated issues especially in applications that involved disaster rescue, military missions and underwater or extra-terrestrial explorations. Currently, the manoeuvrable robot is controlled manually by the operator and it’s a wheeled type. It is used for rescue missions to transport people from disaster area to the safe zone. However, the robot is incapable of moving automatically, and it goes through terrain or landscape like swarm. Therefore, a suitable platform is required to transport or for other uses especially in dangerous mission. It is very difficult to estimate the movement of the robot to avoid obstacles and choose the alternative path. Hence, this research presents the point-to-point gait identification or path planning of the behavious of the robot to manuever autonomously on both on-land and underwater environment. For the optimization, the robot will travel from one specific point to another with the predefined position within optimized gait and fastest time by using Ant Colony Optimization (ACO) technique. The algorithm being compared, between Ant Colony Algorithm (ACO) and the Particle Swarm Optimisation (PSO) in terms of time and distance. The ACO been chosen because of the positive feedback for rapid discovery and able to use in dynamic applications for example adapts to changes like new distances. The performance of the algorithm showed that the execution time of ACO is more realistic. Hence, Matlab is used to determine the best cost extracted from the ACO with the pre-define of number of iteration and the number of ants. The laboratory-scaled prototype for amphibious vehicle was developed to test the design controlled with ACO technique where Global Positioning System (GPS) is used for the coordination of the robot and Magnetometer for the position of the robot. The robot prototype is able to move autonomously and optimized by the ant colony optimization with predefined position and terrain condition © BEIESP. |
|---|