An orientation reflex for autonomous air vehicles based on a neural model of the cockroach escape response

Abstract

This paper investigates a biologically inspired orientation reflex for air vehicles and munitions in the endgame phase flight. The reflex is based upon an artificial neural network model of the American Cockroach’s escape reflex. Guidance commands are output to a Linear Quadratic Regulator (LQR) autopilot that pilots the munition to an optimal path destination and orientation for target strike or obstacle evasion. Simulation and flight test results are presented that demonstrate the reflex’s capability for aerial collision avoidance and instantaneous target strike on evasive targets, even in the presence of false or disruptive sensor data.

More information

Identifiers

Catalogue record

Export record