Knowledge, Skill, and Behavior Transfer in Autonomous Robots: Papers from the AAAI Fall Symposium
Matteo Leonetti, Chair
Eric Eaton and Pooyan Fazli, Cochairs
November 15–17, 2014, Arlington, Virginia
Technical Report FS-14-04
Softcover version of the technical report: $30.00 softcover
(For international orders please shipping options before ordering on website.)
Autonomous robots have achieved high levels of performance and reliability at specific tasks. However, for them to be practical and effective at everyday tasks in our homes and offices, they must be able to learn to perform different tasks over time, demonstrating versatility.
Learning each task in isolation is an expensive process, requiring large amounts of both time and data. In robotics, this expensive learning process also has secondary costs, such as energy usage and joint fatigue. Furthermore, as robotic hardware evolves or new robots are acquired, these robots must be trained, which is extremely inefficient if performed tabula rasa.
Recent developments in transfer and multitask learning provide a potential solution to this problem, enabling robots to minimize the time and cost of learning new tasks by building upon knowledge learned from other tasks or by other robots. This ability is essential to enable the development of versatile autonomous robots that are expected to perform a wide variety of tasks and rapidly learn new abilities.
Various aspects of this problem have been addressed by research across several different communities, including machine learning, knowledge representation, optimal control, and robotics. This symposium will seek to draw together researchers from these different communities toward the goal of enabling autonomous robots to support a wide variety of tasks, rapidly and robustly learn new abilities, adapt quickly to changing contexts, and collaborate effectively with other robots and humans.