An adaptive 'broom balancer' with visual inputs
- 1 January 1988
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 641-647 vol.2
- https://doi.org/10.1109/icnn.1988.23982
Abstract
An adaptive network with visual inputs has been trained to balance an inverted pendulum. Simulation results show that the network is capable of extracting the necessary state information from time sequences of crude visual images. A single linear adaptive threshold element (ADALINE) was adequate for this task. When tested by simulation, the performance achieved was sufficient to keep the pendulum from falling. The adaptive network's ability to generalize made this possible since the training set encompassed only a fraction of all possible states.Keywords
This publication has 2 references indexed in Scilit:
- Neuronlike adaptive elements that can solve difficult learning control problemsIEEE Transactions on Systems, Man, and Cybernetics, 1983
- Punish/Reward: Learning with a Critic in Adaptive Threshold SystemsIEEE Transactions on Systems, Man, and Cybernetics, 1973