Acquiring Transferrable Mobile Manipulation Skills
نویسندگان
چکیده
This abstract summarizes recent research on the autonomous acquisition of transferrable manipulation skills. We describe a robot system that learns to sequence a set of innate controllers to solve a task, and then extracts transferrable manipulation skills from the resulting solution. Using the extracted skills, the robot is able to significantly reduce the time required to discover the solution to a second task.
منابع مشابه
An evidence-based evaluation of transferrable skills and job satisfaction for science PhDs
PhD recipients acquire discipline-specific knowledge and a range of relevant skills during their training in the life sciences, physical sciences, computational sciences, social sciences, and engineering. Empirically testing the applicability of these skills to various careers held by graduates will help assess the value of current training models. This report details results of an Internet sur...
متن کاملPBL for Doctoral Students in Collaboration with SMEs: “Thinking like a Professional Engineer”
The recent global economic downturn brought sharply into focus the need for engineers that excel not only technically and academically but also having a multiplicity of transferable skills, flexibility of mind and resilience. Considerable effort has been focused in UK and internationally on the development of doctoral students with such mind-sets and skills. At the Universities of Sheffield & M...
متن کاملOptimal Trajectory Planning of a Box Transporter Mobile Robot
This paper aims to discuss the requirements of safe and smooth trajectory planning of transporter mobile robots to perform non-prehensile object manipulation task. In non-prehensile approach, the robot and the object must keep their grasp-less contact during manipulation task. To this end, dynamic grasp concept is employed for a box manipulation task and corresponding conditions are obtained an...
متن کاملBuilding elementary robot skills from human demonstration
This paper presents a general approach to the acquisition of sensor-based robot skills from human demonstrations. Since human-generated examples cannot be assumed to be optimal with respect to the robot, adaptation of the initially acquired skill is explicitly considered. Results for acquiring and reening manipulation skills for a Puma 260 manipulator are given.
متن کاملCST: Constructing Skill Trees by Demonstration
We describe recent work on CST, an online algorithm for constructing skill trees from demonstration trajectories. CST segments a demonstration trajectory into a chain of component skills, where each skill has a goal and is assigned a suitable abstraction from an abstraction library. These properties permit skills to be improved efficiently using a policy learning algorithm. Chains from multiple...
متن کامل