Real-time obstacle avoidance for manipulators and mobile robots
International Journal of Robotics Research
Parallel and distributed computation: numerical methods
Parallel and distributed computation: numerical methods
The connection machine
Parameter estimation using competitively inhibited neural networks
Parameter estimation using competitively inhibited neural networks
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Problem-Solving Methods in Artificial Intelligence
Problem-Solving Methods in Artificial Intelligence
Hi-index | 0.00 |
This paper proposes a neural network solution to path planning by two degree-of-freedom (DOF) robots. The proposed network is a two-dimensional sheet of neurons forming a distributed representation of the robot's workspace. Lateral interconnections between neurons are cooperative, so that the field exhibits oscillatory behavior. This paper shows how that oscillatory behavior can be used to solve the path-planning problem. The results reported show that the proposed neural network finds the variational solution of Bellman's dynamic programming equation.