Title :
Neural network middleware for model predictive path tracking of networked mobile robot over IP network
Author :
Tipsuwan, Yodyium ; Chow, Mo-Yuen
Author_Institution :
Dept. of Electr. & Comput. Eng., North Carolina State Univ., Raleigh, NC, USA
Abstract :
The potential use of IP networks for real-time high performance robots and automation is enormous and appealing. A widely attractive objective for an IP-based mobile robot is to control a mobile robot over the IP network to track a predefined path. This paper proposes a model predictive path tracking control methodology over an IP network via middleware. In addition to the normal use of middleware, this paper utilizes middleware to schedule a control parameter for IP network delay compensation. The parameter is adjusted externally at the output of the path tracking algorithm with respect to the current network traffic conditions and a predictive performance measure computed by a neural network. Simulation results show that the mobile robot with neural network middleware provides significantly better IP networked control system performance.
Keywords :
IP networks; adaptive control; control engineering computing; middleware; mobile robots; neural nets; position control; predictive control; radio tracking; telecommunication traffic; IP network; Internet protocol; adaptive control; delay compensation; distributed control; model predictive path tracking control; networked mobile robot; neural network middleware; real-time systems; Automatic control; Communication system traffic control; IP networks; Middleware; Mobile robots; Neural networks; Predictive models; Processor scheduling; Robot control; Robotics and automation;
Conference_Titel :
Industrial Electronics Society, 2003. IECON '03. The 29th Annual Conference of the IEEE
Print_ISBN :
0-7803-7906-3
DOI :
10.1109/IECON.2003.1280266