Trajectory Planning and the Target Search by the Mobile Robot in an Environment Using a Behavior-Based Neural Network Approach
- 14 November 2019
- journal article
- research article
- Published by Cambridge University Press (CUP) in Robotica
- Vol. 38 (9) , 1627-1641
Abstract
SUMMARY: Navigation and path analysis in a cluttered environment is a challenging task over the last few decades. In this paper, a behavior-based neural network (BNN) and reactive control architecture have been presented for navigation of the mobile robot. Two different reactive behaviors have been taken as inputs function. Obstacle position is the first reactive behavior given by u(o), whereas obstacle angle u(n) according to the target position is the second reactive behavior. The angular velocity and steering angle are the output of the controller. The backpropagation architecture reduces the errors of weight function and records the best weight data that match the BNN controller. Using the BNN algorithm, the robot reacts quickly as compared to other developed techniques. To validate the performance of the controller, simulation and experimental results have been compared in the common platforms. The deviation in results for both the scenarios is found to be within 10%. The results of the BNN algorithm have also been compared with other existing techniques. Effectiveness of the proposed technique is measured in terms of smoothness of the realistic path, collision point detection, path length, and performance time.Keywords
This publication has 21 references indexed in Scilit:
- Shakey 2016 - How Much Does it Take to Redo Shakey the Robot?IEEE Robotics and Automation Letters, 2017
- Homotopy Path Planning for Terrestrial Robots Using Spherical AlgorithmIEEE Transactions on Automation Science and Engineering, 2017
- Intercepting Rogue Robots: An Algorithm for Capturing Multiple Evaders With Multiple PursuersIEEE Robotics and Automation Letters, 2016
- Adaptive Neuro-Fuzzy Technique for Autonomous Ground Vehicle NavigationRobotics, 2014
- Evaluation of the EKF-Based Estimation Architectures for Data Fusion in Mobile RobotsIEEE/ASME Transactions on Mechatronics, 2014
- Integrating Arduino-Based Educational Mobile Robots in ROSJournal of Intelligent & Robotic Systems, 2014
- A dynamic localization algorithm for a high-speed mobile robot using indoor GPSRobotica, 2011
- The Utilization of Artificial Neural Networks for Multisensor System Integration in Navigation and Positioning InstrumentsIEEE Transactions on Instrumentation and Measurement, 2006
- Navigation of multiple mobile robots using a neural network and a Petri Net modelRobotica, 2003
- Control of a nonholonomic mobile robot using neural networksIEEE Transactions on Neural Networks, 1998