Artificial Neural Networks for Control of Autonomous Mobile Robots

1994 ◽  
Vol 27 (4) ◽  
pp. 157-162
Author(s):  
M.-W. Han ◽  
T. Kolejka
1970 ◽  
Vol 110 (4) ◽  
pp. 101-104 ◽  
Author(s):  
T. Proscevicius ◽  
A. Bukis ◽  
V. Raudonis ◽  
M. Eidukeviciute

Methods for intelligent mobile robots control which are based on principles of hierarchical control systems will be reviewed in this article. Hierarchical intelligent mobile robots are new direction for development of robotics, which have wide application perspectives. Despite increasing progress in technologies, the main problem of autonomous mobile robots development is that, they are ineffective in their control. In each of the hierarchical control levels (movement in space, problems solving and signal processing sets) will define by specific management of objectives, goals and rules. Communication and management between hierarchies are implemented by higher level of hierarchy using obtained information about the environment and lover level of hierarchy. Studies have shown that artificial neural networks, fuzzy logic are widely used for the development of the hierarchical systems. The main focus of the work is on communications in hierarchy levels, since the robot must be controlled in real time. Ill. 4, bibl. 13 (in English; abstracts in English and Lithuanian).http://dx.doi.org/10.5755/j01.eee.110.4.298


Energies ◽  
2021 ◽  
Vol 14 (20) ◽  
pp. 6722
Author(s):  
Krystian Góra ◽  
Mateusz Kujawinski ◽  
Damian Wroński ◽  
Grzegorz Granosik

A detailed literature analysis depicts that artificial neural networks are rarely used for the power consumption estimation in the mobile robotics field. Instead, researchers prefer to develop analytical models of investigated robots. This manuscript presents a comparison of mathematical models and non-complex artificial neural networks in energy prediction tasks for differential and skid-steer drive robots which move over various types of surfaces. The results show that both methods could be used interchangeably but AI methods are more universal, do not depend on the kinematic structure of a robot and are tolerant for designers not having a complex knowledge about the system.


2015 ◽  
Vol 13 (10) ◽  
pp. 3405-3414 ◽  
Author(s):  
Jessyca Almeida Bessa ◽  
Darlan Almeida Barroso ◽  
Ajalmar Rego da Rocha Neto ◽  
Auzuir Ripardo de Alexandria

Sign in / Sign up

Export Citation Format

Share Document