2021 Volume 141 Issue 3 Pages 464-470
A neural network based automatic adjustment system of PID gains is proposed. By this online learning method, the 4-rotor flying robot can deal with model errors and disturbances. Meanwhile, the sensor system makes the robot able to track objects and avoid obstacles automatically. The effectiveness of the proposed system is proven by experiments.
The transactions of the Institute of Electrical Engineers of Japan.C
The Journal of the Institute of Electrical Engineers of Japan