Autonomous vehicle navigation utilizing electrostatic potential fields and fuzzy logic

TLDR

The path of maximum current through the resistor network corresponds to an approximately optimal path in the environment. The system maps the environment into a resistor network, generates an electrostatic potential field via current injection, and employs a two‑layer fuzzy logic engine to fuse sensor data and enforce collision avoidance while following the EPF trajectory. Experimental tests on the Nomad 200 mobile robot demonstrated the feasibility of the EPF‑fuzzy logic navigation approach.

Abstract

An electrostatic potential field (EPF) path planner is combined with a two-layered fuzzy logic inference engine and implemented for real-time mobile robot navigation in a 2-D dynamic environment. The environment is first mapped into a resistor network; an electrostatic potential field is then created through current injection into the network. The path of maximum current through the network corresponds to the approximately optimum path in the environment. The first layer of the fuzzy logic inference engine performs sensor fusion from sensor readings into a fuzzy variable, collision, providing information about possible collisions in four directions, front, back, left and right. The second layer guarantees collision avoidance with dynamic obstacles while following the trajectory generated by the electrostatic potential field. The proposed approach is experimentally tested using the Nomad 200 mobile robot.