Abstract
A primary factor in the evolution of vision was undoubted the need for perceptual support of gait modulation and decision making related to locomotion. The ability to attend and respond to objects meaningful in a locomotory sense is particularly important as animal species increase in size and agility. In this work, it is shown how a generic architecture can very quickly learn to attend to objects in the environment that are meaningful to an agent, in this case a robot. These objects are important because they affect the robot's primary purpose in life—to walk. The robot responds to meaningful objects, not just novel ones. Thus, under this paradigm attention is not driven by bottom-up processing but by the need to support a behavior.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
