Seminar

Seminar Series 5/2009: "Improved Mobile Robot Navigation Using Soft Computing Techniques"

Ms Soh Chin Yun (MEngSc (research) student


Date: 2009-04-28
Time: 15:00 to 16:00
Venue: 9504


Abstract

Robotics is the science and technology of robots, their design, manufacture, and applications. The main focus of the PhD work lies on the mobile robot navigation techniques which are applied to the mobile robots (built with low cost sensors) in a highly unstructured, unknown and uncertain environment. The Soft Computing techniques are used to improve mobile robot navigation. In the preliminary research, Artificial Neural Network is used to enable the QLearning controller to learn from its environment and improve its environment through learning. Comparative study of Fuzzy Logic and Neural Network for Obstacle Avoidance and Wall Following behaviors has been carried out. The combination of Neural Network controller for Obstacle Avoidance behavior and Fuzzy Logic controller for Wall Following behavior was found to give better results. The real time implementation of both Neural Q-Learning approach and Neural Fuzzy approach in mobile robot navigation techniques were tested. Both simulation and real time implementations have shown the flexibility and robustness of the proposed algorithms. Some of the basic behaviors including Goal Seeking, Obstacle Avoidance and Wall Following are responses to the various sensor data received from the simple low cost ultrasonic sensors that are locally available on the mobile robot. In the proposed research, the enhanced hybrid Genetic Algorithm approach for Optimal Path Planning in mobile robot navigation will be explored. Combination of three Soft Computing techniques including Fuzzy Logic, Neural Network and Genetic Algorithm will be carried out in order to come out with a Fuzzy-Neuro-Genetic approach for the specific problem domain i.e. Optimal Path Planning in mobile robot navigation. This approach can either be a new algorithm or the enhancement of the existing algorithms. The improved autonomous mobile robot navigation techniques aim to effectively guide the mobile robot from the starting point to the specified destination/target in a shortest path without colliding with obstacles in the environment. These techniques are used to avoid all type of obstacles that are detected by the sonar sensors (ultrasonic sensors) of the mobile robot in the environment.

About the Speaker

Ms Soh Chin Yun is our current 1st year HDR (MEngSc (research)) student under Dr V. Ganapathy’s supervision. She will be sharing with you by presenting her research progress and plans in her PhD candidature as the fulfillment of candidature conversion (from MEngSc (research) to PhD).

There will be a Q&A session after the 20 minutes of presentation. Please come and support!