Rapid, safe, and incremental learning of navigation strategies

  title={Rapid, safe, and incremental learning of navigation strategies},
  author={Jos{\'e} del R. Mill{\'a}n},
  journal={IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society},
  volume={26 3},
In this paper we propose a reinforcement connectionist learning architecture that allows an autonomous robot to acquire efficient navigation strategies in a few trials. Besides rapid learning, the architecture has three further appealing features. First, the robot improves its performance incrementally as it interacts with an initially unknown environment, and it ends up learning to avoid collisions even in those situations in which its sensors cannot detect the obstacles. This is a definite… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 10 references

Integration of representation into goaldriven behaviorbased robots

  • J del R Millin
  • IEEE Trans Robot . Automat .
  • 1992

Convergence of stochastic iterative dynamc programmng algorithms

  • S P Singh
  • Advances in Neural Information Processing Systems
  • 1991

A hybrid architecture applied to robot navigation

  • S. SS
  • Proc . IEEE Int . Conf on Robotics and Automation
  • 1986

L e m n g and sequential decision mhng

  • R. S. Sutton Barto, C. J C H. Watkins
  • Neuronhke elements A 4 an , Cybern .
  • 1983

Red time obstacle avoidance for manipulators and mobile robots

  • B J. A. Krose, J. W. M van Dam
  • Inte J Robot Res

Similar Papers

Loading similar papers…