Autonomous Behavior Control for Modular Robots
碩士 === 國立中正大學 === 光機電整合工程所 === 98 === The main objective of the thesis is to study on the multiple robots formation by individual own ability. The experiment uses a camera to set a field with known coordinate. A stand-aside computer executes the image processing and the learning algorithm, and trans...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en_US |
| Published: |
2010
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/78232502810758854533 |
| Summary: | 碩士 === 國立中正大學 === 光機電整合工程所 === 98 === The main objective of the thesis is to study on the multiple robots formation by individual own ability. The experiment uses a camera to set a field with known coordinate. A stand-aside computer executes the image processing and the learning algorithm, and transmits the commands to robots which are equipped with dspic33F chip as its core from RF. Before field test the learning algorithm for individual and fused behavior is trained in simulations .The algorithm used in the thesis is Fusion Approach Based on Q-Learning which has been evolved for several generations in the lab. We designed three behaviors including the behaviors of following distance, following angle, and obstacle avoidance so that the robots can reach the target with complete formation safely. The robot can judge the situation independently and safely where it should go in the formation under the condition that the robot only knows its own s and other teammates’ coordinates as long as the destination coordinates and types of formations are given to the team.
|
|---|