Mobile Robot with Floor Tracking Device for Localization and Control

2007 ◽  
Vol 19 (1) ◽  
pp. 34-41 ◽  
Author(s):  
Isaku Nagai ◽  
◽  
Yutaka Tanaka

We developed a visual device that tracks floor images and calculates the movement of a camera on a mobile robot. The mobile robot has caterpillar-tread wheels and uses our visual tracking device for localization. The robot is localized and controlled in real time based on the information on the estimated position and direction using FPGA, SRAM, and a small CPU board. Location and direction error over a closed path is eliminated by searching for an original floor image memorized initially at the point from which the robot started the run. Experimental results demonstrate the advantages of the proposal using the visual tracking device localizing a mobile robot with wheel slippage and under changing light conditions. We also show that the robot runs along a closed path repeatedly without a straying from the track by using the original image to correct accumulated error.

2019 ◽  
pp. 41-48
Author(s):  
Yan Guojun ◽  
Oleksiy Kozlov ◽  
Oleksandr Gerasin ◽  
Galyna Kondratenko

The article renders the special features of the design of a tracked mobile robot (MR) for moving over inclined ferromagnetic surfaces while performing specified technological operations. There is conducted a synthesis of the functional structure and selective technological parameters (such as control coordinates) of the computerized monitoring and control system (CMCS) intended for use with this MR. Application of the CMCS with the proposed functional structure allows substantially increasing the accuracy of the MR monitoring and control, which in turn provides for a considerable enhancement in the quality and economic efficiency of the operations on processing of large ferromagnetic surfaces.


1970 ◽  
Vol 23 ◽  
Author(s):  
M. Van Miegroet

A  certain number of measurable characteristics of tree leaves (morphological  characteristics, absorption of light radiation, intensity of respiration and  photosynthesis) are clearly linked with the presence of physiologically  active pigments in the leaves.     Leaf characteristics are highly and inequally influenced by changing  conditions of light environment, especially those related to light intensity,  light quality and duration of the daily illumination period. These  modifications do not only apply to light radiation as created under  laboratory conditions, but also to light conditions ensuing from the place in  the crown of a single tree, the social position of the tree in a forest stand  and the site factors in general.     There are also changes taking place due to the progression of the  vegetation period, at the end of which all species are less tolerant or more  light demanding. The reaction of the leaves towards light radiation out of  different regions of the spectrum is also different. The so-called blue light  radiation (λmax = 440 nm) seems to be of the greatest importance in this  relation, as species react quite different to its action.     The biggest variation in leaf characteristics due to changing light  environment was measured for oak and beech, which both react quickly and are  qualified as 'photolabile species'. No important variations occur in leaves  of ash and maple, which therefore are qualified as 'photostable species'.      As a consequence of variable reactions to changing light conditions, the  relationships between the species are continually modified, even in such a  way that their potential for dominance is not constant.     The classical division into tolerant and intolerant species or  classification of the species based upon the degree of light demand, is  highly inaccurate and it seems preferable to speak of relative light demands  and relative tolerance. All these observations and conclusions bring about a  clear confirmation of the necessity to recognize the individuality of the  single tree, the special character of each growth condition, the own  structure of each forest stand, the specific reaction to one sided  modifications of environmental factors. This is especially important for an  intensive sylvicultural practice.     They also prove the necessity for more physiological and biochemical  research to arrive at a better understanding of growth and its mechanism.      Sylviculture in fact must try to regulate, on an expanded scale, the  phenomens of growth, which is the exchange, absorption and transformation of  energy.     A practical interpretation and regulation of fundamental laws of physiology  and growth will be possible as soon as a clinical form of sylviculture is  created and the adequate instrumentarium developed.


2012 ◽  
Vol 71 (5) ◽  
pp. 699-711 ◽  
Author(s):  
Patricia Hornitschek ◽  
Markus V. Kohnen ◽  
Séverine Lorrain ◽  
Jacques Rougemont ◽  
Karin Ljung ◽  
...  

Machines ◽  
2021 ◽  
Vol 9 (3) ◽  
pp. 66
Author(s):  
Tianci Chen ◽  
Rihong Zhang ◽  
Lixue Zhu ◽  
Shiang Zhang ◽  
Xiaomin Li

In an orchard environment with a complex background and changing light conditions, the banana stalk, fruit, branches, and leaves are very similar in color. The fast and accurate detection and segmentation of a banana stalk are crucial to realize the automatic picking using a banana picking robot. In this paper, a banana stalk segmentation method based on a lightweight multi-feature fusion deep neural network (MFN) is proposed. The proposed network is mainly composed of encoding and decoding networks, in which the sandglass bottleneck design is adopted to alleviate the information a loss in high dimension. In the decoding network, a different sized dilated convolution kernel is used for convolution operation to make the extracted banana stalk features denser. The proposed network is verified by experiments. In the experiments, the detection precision, segmentation accuracy, number of parameters, operation efficiency, and average execution time are used as evaluation metrics, and the proposed network is compared with Resnet_Segnet, Mobilenet_Segnet, and a few other networks. The experimental results show that compared to other networks, the number of network parameters of the proposed network is significantly reduced, the running frame rate is improved, and the average execution time is shortened.


2010 ◽  
Vol 44-47 ◽  
pp. 321-325
Author(s):  
Liang Hua ◽  
Lin Lin Lv ◽  
Ju Ping Gu ◽  
Yu Jian Qiang

The key technilogies of ship-welding mobile robot applied to ship-building in plane block production line were researched and realized. The mechanical structure design of the robot was completed. The motion-controlling system of of two-wheel differential driving mobile robot was developed. A novel precision positioning control method of welding torch using ultrasonic motors was putforward. The mechanism and control-driven system of precision positioning system for welding torch were completed. The platform of obstacle avoidance navigation system was designed and the strategies of seam tracking, trajectory and posture adjustment were preliminary studied. The methods and results put forward in the paper could act as the base of deep research on the theories and technologies of ship-welding mobile robot.


Author(s):  
Jesus Morales ◽  
Jorge L. Martinez ◽  
Anthony Mandow ◽  
Javier Seron ◽  
Alfonso Garcia-Cerezo ◽  
...  

Trees ◽  
1998 ◽  
Vol 12 (6) ◽  
pp. 326-333 ◽  
Author(s):  
R. Tognetti ◽  
Gianfranco Minotta ◽  
Simone Pinzauti ◽  
Marco Michelozzi ◽  
Marco Borghetti

Sign in / Sign up

Export Citation Format

Share Document