Optimal Path Planning for Wireless Power Transfer Robot Using Area Division Deep Reinforcement Learning

Table 1

Symbols and explanations.

Symbol	Explanation
	The number of energy harvesters
	Rectifier efficiency
	Gain of transmitter’s antenna
	Gain of receiver’s antenna
	Wavelength of transmitted signal
	Polarization loss
	Friis’s free space adjustable parameter
	Distance between transmitter and harvester
	Transmit power
	Received power
	Angle between transmitter and the vertical reference line
	Maximum effective transmit area
	Effective received area
	Time instant
	Position and units to left and upmost edges
	Position of th energy harvester
	Effective charging area for th IoT devices
	Present system state
	Next system state
	Action taken at
	Total time consumption
	Transition probability from state to state taking action
	Reward function at state taking action
	Indicator whether harvesters have been charged
	Unit price for reward function
	Optimal strategy
	Cost function at state taking action
	Reward decay
	Learning rate for Q-learning
	Selected location for th area
	th area