Fuzzy optimisation based symbolic grounding for service robots [thesis]

Abstract

Symbolic grounding is a bridge between task level planning and actual robot sensing and actuation. Uncertainties raised by unstructured environments make a bottleneck for integrating traditional artificial intelligence with service robotics. In this research, a fuzzy optimisation based symbolic grounding approach is presented. This approach can handle uncertainties and helps service robots to determine the most comfortable base region for grasping objects in a fetch and carry task. Novel techniques are applied to establish fuzzy objective function, to model fuzzy constraints and to perform fuzzy optimisation. The approach does not have the short comings of others' work and the computation time is dramatically reduced in compare with other methods. The advantages of the proposed fuzzy optimisation based approach are evidenced by experiments that were undertaken in Care-O-bot 3 (COB 3) and Robot Operating System (ROS) platforms.

Date of Award	Nov 2013
Original language	English
Awarding Institution	University of Bedfordshire
Supervisor	Dayou Li (Supervisor) & Yong Yue (Second supervisor)