Cost-sensitive robot learning

Robot learning aims to improve the connection of a robot's perception to action. However, the majority of work in robot learning has not dealt realistically with perception and action. A common assumption is that sensors provide a complete picture of the external world at no cost and actions can be executed instantly. In reality, robots only have limited resources. There are always costs (e.g., sensing or moving speed) associated with perception and action. This dissertation is a study of cost-sensitive robot learning that considers such costs explicitly. The main thesis is that it is possible for a learning robot to gradually improve learning accuracy without sacrificing learning efficiency.;This dissertation also presents a unified framework for cost-sensitive learning of classification knowledge from examples and constructing examples from scratch. Within this framework, various cost-sensitive learning methods can be instantiated. This dissertation develops two such cost-sensitive learning methods: a decision-tree-based method and an instance-based method, and it evaluates the tradeoff between their learning efficiency and learning accuracy.;This dissertation demonstrates the generality of cost-sensitive learning in three ways. First, it uses cost-sensitive learning to accomplish the approach-recognize task. Second, it applies cost-sensitive learning to medical diagnosis domains. Third, it uses cost-sensitive learning to construct a task-dependent internal representation for use by a reinforcement learning method as it learns a decision policy. Experimental results confirm the efficiency of the overall approach.;Specifically, this dissertation describes a cost-sensitive learning system called CSL that learns to perform an approach-recognize task for a mobile robot. Given a set of unknown objects and the speeds of sensors and actions, CSL learns where to sense, which sensor to use, and which action to apply. As a result, it learns to approach, recognize, and grasp objects efficiently. CSL integrates learning with control to handle sensing noise and grasping failures. Compared with traditional learning approaches, in experiments involving 14 training objects and 11 test objects, CSL is an order of magnitude faster during training and at least 30% faster during testing. Its overall success rate on novel objects is over 80% and many failures can be eliminated through incremental learning.