Instruction Based Learning: how to instruct a personal robot to find HAL.

Future domestic robots will need to adapt to the special needs of their users and to their environment. Programming by natural language will be a key method enabling computer languagenaive users to instruct their robots. Its main advantages over other learning methods are speed of acquisition and ability to build high level symbolic rules into the robot. This paper describes the design of a practical system that uses unconstrained speech to teach a vision-based robot how to navigate in a miniature town. The robot knows a set of primitive navigation procedures that the user can refer to when giving route instructions. Since the user is likely to refer to a procedure that is not pre-programmed in the robot, the system must be able to learn it. This paper investigates how to make the learning process possible. In particular, a method is proposed to fasten the choice of an initial set of primitives to the natural human speech chunking. Moreover, the use of Instruction-Based Learning (IBL) imposes a number of constraints on the design of robotics systems and knowledge representation. These issues are developed in the paper and proposed solutions described.