Position Paper: Human Skills for Programming-by-Demonstration of Robots
نویسندگان
چکیده
“Programming-by-Demonstration” (PbD) is a very intuitive and efficient means for programming robots for a specific task. One approach for PbD uses manual guided robots to show the task the robot has to perform. Even though manual guidance is a lot more intuitive than traditional programming, first experiences showed that there is still training needed to make full use of such a system. This paper discusses concepts for PbD and studies the required skills. The focus is less on task skills that are to be transferred to a robot but more on the skills for using a PbD system (system skills). Furthermore, several tools for PbD, like virtual fixtures, compliant motion or authoring are discussed. Two demonstrators for evaluating concepts and tools for PbD are proposed and described, one augmented reality and one virtual reality demonstrator, both based on the DLR/KUKA Light Weight Robot. These demonstrators are suited as skill transfer system for programming robots, as well as training platforms to teach novice users how to program a robot with PbD.
منابع مشابه
Learning Force-Based Assembly Skills from Human Demonstration for Execution in Unstructured Environments
Robots have been used successfully in structured settings , where the environment is controlled; this research is inspired by the vision of robots moving beyond the structured, controlled settings. The work fo-cuses on the problem of learning low-level force-based assembly skills from human demonstration. To avoid position dependencies, force-based discrete states are used to describe qualitati...
متن کاملLearning Robot Behaviour and Skills Based on Human Demonstration and Advice: The Machine Learning Paradigm
Service robots require easy programming methods allowing the unexperienced human user to easily integrate motion and perception skills or complex problem solving strategies. To achieve this goal, robots should learn from operators how and what to do considering hardand software constraints. Various approaches modelling the man-machine skill transfer have been proposed. Systems following the Pro...
متن کاملApproaches for Learning Human-like Motor Skills which Require Variable Stiffness During Execution
Humans employ varying stiffness in everyday life for almost all human motor skills, using both passive and active compliance. Robots have only recently acquired variable passive stiffness actuators and they are not yet mature. Active compliance controllers have existed for a longer time, but the problem of automatic determination of the necessary compliance to achieve a task has not been thorou...
متن کاملA Survey of Robot Programming Systems
Robots have become significantly more powerful and intelligent over the last decade, and are moving in to more service oriented roles. As a result robots will more often be used by people with minimal technical skills and so there is a need for easier to use and more flexible programming systems. This paper reviews the current state of the art in robot programming systems. A distinction is made...
متن کاملAcquiring robust, force-based assembly skills from human demonstration
Robots have been used successfully in structured settings, where the environment is controlled; this research is inspired by the vision of robots moving beyond structured, controlled settings. The work focuses on the problem of teaching robots forcebased assembly skills from human demonstration. To avoid position dependencies, force-based discrete states (contact formations) are used to describ...
متن کامل