Decision Trees and CBR for the Navigation System of a CNN-based Autonomous Robot

Author(s):  
Giovanni Egidio Pazienza ◽  
Elisabet Golobardes-Ribé ◽  
Xavier Vilasís-Cardona ◽  
Marco Balsi
Author(s):  
Salvador E. Ayala-Raggi ◽  
Pedro de Jesús González ◽  
Susana Sánchez-Urrieta ◽  
Aldrin Barreto-Flores

An autonomous robot can navigate in a given region and reach to a specified location. The navigation system for these robots has to be reliable, versatile and rugged. In this paper, design and development aspects of such navigation system are discussed. A two level architecture is proposed for navigation of the autonomous robot. The low level controller (LLC) generates odometry data and implements closed loop feedback based PID algorithm. The high level controller (HLC) is used to generate velocity commands based on the path planned and inputs sensed from environment. The two controllers continuously exchange data with each other to reach the final destination. This navigation system platform can be used to develop autonomous mobile robots


2017 ◽  
Vol 24 (4) ◽  
pp. 353-367
Author(s):  
Long Thanh Ngo ◽  
Long The Pham ◽  
Phuong Hoang Nguyen

Robot navigation using fuzzy behavior is suited in unknown and unstructured environment in which each behavior have an individual task. This paper deals with an approach designing autonomous robot navigation system based on fuzzy behaviors including collision avoidance, wall-following, go-to-target. The proposed hierarchy of fuzzy behaviors is used to fuse the command in which each behavior is a fuzzy inference system and its outputs are fuzzy sets. Its inputs are information fused from sensors using fuzzy directional relationship. The simulation results with some statistics show that the system works correctly. 


Sign in / Sign up

Export Citation Format

Share Document