Ahmed Al-Araji
Start date: 1-10-2009
End date: 11-9-2012
Email: ahmed.al-araji@brunel.ac.uk
Supervisor: Prof Hamed S. Al-Raweshidy
Research title: Design of a Cognitive Neural Predictive Controller for Mobile Robot
Mobile robot can be defined as a mechanical device that performs automated tasks, wither according to direct human supervision, a pre-defined program, or a set of general guidelines, using artificial intelligence techniques. Cognitive control methodologies have been proven to be a source of inspiration and a guidance to overcome current limitations in the controller for more complex and adaptive systems. The fundamental essence of the motivation for this work is to generate an optimal path for mobile robots in order to avoid static obstacles and track the desired trajectory with minimum tracking error and save the battery energy of the robot through the design of an adaptive robust controller. Simulation results and experimental work show the effectiveness of the three proposed control methodologies, which achieved excellent tracking for Lemniscates and Circular as a continuous and Square as a non-continuous gradients trajectories with collision-free path for the actual mobile robot and reduced the tracking error to less than 1cm. The actions of the proposed controller were small smooth values of the torques for right and left wheels without sharp spikes and less than maximum torque (0.235 N.m); therefore, the velocity of the actual mobile robot does not exceed the maximum value (0.165 m/sec). The proposed controller can be given in the form of the block diagram shown in Figure below.
Publications
- Ahmed S. Al-Araji, Maysam F. Abbod and Hamed S. Al-Raweshidy, Applying posture identifier in designing an adaptive nonlinear predictive controller for nonholonomic mobile robot. Accepted in Neurocomputing Elsevier Journal 8-6-2012 and online available 24-8-2012.
