1270 search results - page 60 / 254 » Dogged Learning for Robots |
ICRA
2005
IEEE
14 years 2 months ago
2005
IEEE
— This paper presents a new reinforcement learning algorithm for accelerating acquisition of new skills by real mobile robots, without requiring simulation. It speeds up Q-learni...
CORR
2006
Springer
13 years 8 months ago
2006
Springer
We address the problem of autonomously learning controllers for visioncapable mobile robots. We extend McCallum's (1995) Nearest-Sequence Memory algorithm to allow for genera...
ICRA
2010
IEEE
13 years 7 months ago
2010
IEEE
— Teaching a robot to learn new knowledge is a repetitive and tedious process. In order to accelerate the process, we propose a novel template-based approach for robot arm moveme...
DAGSTUHL
2003
13 years 10 months ago
2003
The developmental approach enables us to build adaptive robots, and furthermore, to understand the essence of intelligence from the constructivist viewpoint. In this paper, a new d...
AMS
2007
Springer
14 years 2 months ago
2007
Springer
Autonomous robots that can adapt to novel situations has been a long standing vision of robotics, artificial intelligence, and cognitive sciences. Early approaches to this goal du...