Control structure for a car-like robot using artificial neural networks and genetic algorithms
- PDF / 3,502,507 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 76 Downloads / 232 Views
(0123456789().,-volV)(0123456789().,-volV)
S.I. : ADVANCES IN BIO-INSPIRED INTELLIGENT SYSTEMS
Control structure for a car-like robot using artificial neural networks and genetic algorithms Camilo Andre´s Ca´ceres Flo´rez1
•
Joa˜o Maurı´cio Rosa´rio1 • Dario Amaya2
Received: 16 December 2017 / Accepted: 27 April 2018 Ó The Natural Computing Applications Forum 2018
Abstract The idea of improving human’s life quality by making life more comfortable and easy is nowadays possible using current technologies and techniques to solve complex daily problems. The presented idea in this work proposes a control strategy for autonomous robotic systems, specifically car-like robots. The main objective of this work is the development of a reactive navigation controller by means of obstacles avoidance and position control to reach a desired position in an unknown environment. This research goal was achieved by the integration of potential fields and neuroevolution controllers. The neuro-evolutionary controller was designed using the (NEAT) algorithm ‘‘Neuroevolution of Augmented Topologies’’ and trained using a designed training environment. The methodology used allowed the vehicle to reach a certain level of autonomy, obtaining a stable controller that includes kinematic and dynamic considerations. The obtained results showed significant improvements compared to the comparison work. Keywords Neuroevolution Artificial neural network Genetic algorithm Control strategy Non-holonomic wheeled robot Car-like robot
1 Introduction Nowadays, due to the evolution of transport systems and intelligent systems, the requirement of autonomous transportation systems has increased, creating an important area of study for mobile robots and several control schemes that works under real conditions. Likewise, mobile robotic development and the improvement of new automation technologies and data processing have created the need to
& Camilo Andre´s Ca´ceres Flo´rez [email protected] Joa˜o Maurı´cio Rosa´rio [email protected] Dario Amaya [email protected] 1
Mechanical Engineering School, Integrated Systems Department, Universidade Estadual de Campinas – UNICAMP, Rua Mendeleiev, 200, Campinas, Sa˜o Paulo CEP 13083-860, Brazil
2
Faculty of Engineering, Mechatronic Engineering Program, Universidad Militar Nueva Granada – UMNG, Carrera 11 #101-80, Bogota´, Cundinamarca, Colombia
develop control systems that improve the autonomy of mobile robots in different work environments. In the mobile robotics field, trajectory, position, and orientation controls have been the key development topics, applying techniques such as PID controllers, neuronal networks, and fuzzy logic controllers, specifically in coupled constrained models, like the car-like robot system. The navigation controller development for wheeled devices with kinematic constraints, like the non-holonomic robots, is significantly more complex than controllers designed for unconstrained robots. In the following work, a constrained and non-holonomic mobile ca
Data Loading...
