Dogged Learning for Robots

— Ubiquitous robots need the ability to adapt their behaviour to the changing situations and demands they will encounter during their lifetimes. In particular, non-technical users must be able to modify a robot’s behaviour to enable it to perform new, previously unknown tasks. Learning from Demonstration is a viable means to transfer a desired control policy onto a robot and Mixed-Initiative Control provides a method for smooth transitioning between learning and acting. We present a learning system (Dogged Learning) that combines Learning from Demonstration and Mixed Initiative Control to enable lifelong learning for unknown tasks. We have implemented Dogged Learning on a Sony Aibo and successfully taught it behaviours such as mimicry and ball seeking. I. MOTIVATION If robots are ubiquitous then the average user will likely be non-technical, but will have the desire to alter robot behaviour. That is, he or she will be unwilling or unable to sit down and program a robot in a traditi...

• Type: Conference
• Year: 2007
• Where: ICRA
• Authors: Daniel H. Grollman, Odest Chadwicke Jenkins
• Keywords: ICRA 2007, Robotics, Robots, Robot’s Behaviour, Unknown Tasks