(2006). Executive attention, task selection and attention-based learning in a neurally controlled simulated robot.
Behaviour based robots have problems related to inappropriate behaviours expressed by the machines. We identify two classes of problem, capture errors and perseverative behaviour which can cause a machine to fail to meet its real-time goals. We suggest that these errors may be moderated or eliminated by the use of an executive or Supervisory Attentional… (More)
We have developed a robot controller based upon a neural implementation of Norman and Shallice's model of executive attentional control in humans. A simulation illustrates how atten-tional control leads to the suppression of action selection errors in neurally controlled robots. A related demonstration illustrates how lesioning of the control architecture… (More)
We describe the design and implementation of an integrated neural architecture, modelled on human executive attention, which is used to control both automatic (reactive) and willed action selection in a simulated robot. The model, based upon Norman and Shallice's supervisory attention system, incorporates important features of human attentional control:… (More)
Extended Abstract Building autonomous robotic agents that interact with the real-world is a complex and difficult task and several distinct paradigms are used to develop such machines. In the past decade there has been an exploration of approaches inspired by evolutionary and/or neurodynamical principles. [1, 2, 3, 4]. In earlier work, we have examined… (More)