Three-Dimensional Path-Following Control of a Robotic Airship with Reinforcement Learning

Table 2

The maximum and the average deviation distance.

Deviation distance	PID	Reinforcement learning
Airship to target maximum (m)	17.6	13.2
Airship to target average (m)	10.1	4.2
Airship to path maximum (m)	40.9	29.2
Airship to path average (m)	19.9	4.8