Lifelong Robot Learning1
نویسندگان
چکیده
Learning provides a useful tool for the automatic design of autonomous robots. Recent research on learning robot control has predominantly focussed on learning single tasks that were studied in isolation. If robots encounter a multitude of control learning tasks over their entire lifetime, however, there is an opportunity to transfer knowledge between them. In order to do so, robots may learn the invariants of the individual tasks and environments. This task-independent knowledge can be employed to bias generalization when learning control, which reduces the need for real-world experimentation. We argue that knowledge transfer is essential if robots are to learn control with moderate learning times in complex scenarios.Two approaches to lifelong robot learning which both capture invariant knowledge about the robot and its environments are presented. Both approaches have been evaluated using a HERO2000 mobile robot. Learning tasks included navigation in unknown indoor environments and a simple find-and-fetch task.
منابع مشابه
Research and Development of a Positioning Service for Learning Networks for Lifelong Learning1
Positioning in learning networks is a process that assists learners in finding a starting point and an efficient route through the network that will foster competence building. This contribution presents the rationale for the positioning project and provides an overview about methodological questions for the research and development of a positioning service for lifelong learning and a short out...
متن کاملLifelong robot-assisted mobility: Models, Tools, and Challenges
Increasing the autonomy of users with disabilities through robot-assisted mobility has the potential of facilitating their sensorimotor and social development, as well as reducing the burden of caring for such populations in both inpatient and outpatient settings. While techniques for task-specific assistance exist, they are largely focused on satisfying shortterm goals, utilising stationary us...
متن کاملLifelong Planning for Mobile Robots
Mobile robots often have to replan as their knowledge of the world changes. Lifelong planning is a paradigm that allows them to replan much faster than with complete searches from scratch, yet nds optimal solutions. To demonstrate this paradigm, we apply it to Greedy Mapping, a simple sensor-based planning method that always moves the robot from its current cell to the closest cell that it has ...
متن کاملWiimote Interfaces for Lifelong Robot Learning
We believe that one of the major impediments to involvement in the field of robotics and AI is the difficulty end-users face in creating viable robot control policies. We seek to address this difficulty with lifelong robot learning and have developed an intuitive robot control interface using the Nintendo Wii remote to aid in this task. From three large public demos and several smaller ones, we...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1993