Adaptive critic designs-based autonomous unmanned vehicles navigation: Application to robotic farm vehicles

PATIÑO DANIEL; TOSETTI SANTIAGO; CAPRARO FLAVIO

Nashville

Congreso; IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning; 2009

IEEE

This paper addresses the problem of generating autonomously an optimal control action sequence for robotic autonomous unmanned vehicles based on adaptive critic designs (ACDs) for their use in autonomous agriculture vehicles, in the context of precision agriculture. The main objective is to design autonomously an optimal controller that steers the center of the vehicle through a number of waypoints in a particular order using a minimum amount of time and energy consumption. The last aspect is very important for the endurance performance in autonomous unmanned vehicles. In general, the steering of unmanned robotic vehicles depends on the interactions between the vehicle and its supporting medium. Planning for the future encounters with the waypoints should be part of the current control decision, since the vehicles position and orientation as it moves through one gate greatly alter the case of navigation through successive points. The proposed ACD-based intelligent controller learns to guide the vehicle through a set of points autonomously. The simulation results show the performance of the proposed approach for a simple case of mobile robotics.