Decision tree learning for intelligent mobile robot navigation
Year: 2019
Type: dissertation
Abstract: The replication of human intelligence, learning and reasoning by means of computer\nalgorithms is termed Artificial Intelligence (Al) and the interaction of such\nalgorithms with the physical world can be achieved using robotics. The work described in\nthis thesis investigates the applications of concept learning (an approach which takes its\ninspiration from biological motivations and from survival instincts in particular) to robot\ncontrol and path planning. The methodology of concept learning has been applied using\nlearning decision trees (DTs) which induce domain knowledge from a finite set of training\nvectors which in turn describe systematically a physical entity and are used to train a robot\nto learn new concepts and to adapt its behaviour.\nTo achieve behaviour learning, this work introduces the novel approach of hierarchical\nlearning and knowledge decomposition to the frame of the reactive robot architecture.\nFollowing the analogy with survival instincts, the robot is first taught how to survive in\nvery simple and homogeneous environments, namely a world without any disturbances or\nany kind of "hostility". Once this simple behaviour, named a primitive, has been established, the robot is trained to adapt new knowledge to cope with increasingly complex\nenvironments by adding further worlds to its existing knowledge. The repertoire of the\nrobot behaviours in the form of symbolic knowledge is retained in a hierarchy of clustered\ndecision trees (DTs) accommodating a number of primitives. To classify robot perceptions,\ncontrol rules are synthesised using symbolic knowledge derived from searching the\nhierarchy of DTs.\nA second novel concept is introduced, namely that of multi-dimensional fuzzy associative\nmemories (MDFAMs). These are clustered fuzzy decision trees (FDTs) which are trained\nlocally and accommodate specific perceptual knowledge. Fuzzy logic is incorporated to\ndeal with inherent noise in sensory data and to merge conflicting behaviours of the DTs.\nIn this thesis, the feasibility of the developed techniques is illustrated in the robot\napplications, their benefits and drawbacks are discussed.
Author: G. Hossein Shah Hamzei (7202189)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7204433763
