Vision System Calibration of Agricultural Wheeled-Mobile Robot Based on BP Neural Network

2007 ◽  
Author(s):  
Bo Zhao ◽  
Zhong-Xiang Zhu ◽  
En-Rong Mao ◽  
Zheng-He Song
Keyword(s):  
Neural Network ◽  
Mobile Robot ◽  
Bp Neural Network ◽  
Vision System ◽  
Wheeled Mobile Robot ◽  
System Calibration

Robust adaptive dynamic programming based online tracking control algorithm for real wheeled mobile robot with omni-directional vision system

2016 ◽  
Vol 39 (6) ◽  
pp. 832-847 ◽  
Author(s):  
Nguyen Tan Luy
Keyword(s):  
Neural Network ◽  
Dynamic Programming ◽  
Mobile Robot ◽  
System Dynamics ◽  
Vision System ◽  
Dynamic Programming Algorithm ◽  
Wheeled Mobile Robot ◽  
Adaptive Dynamic Programming ◽  
Adaptive Dynamic ◽  
Robust Adaptive

This paper proposes a new method to design an online robust adaptive dynamic programming algorithm (RADPA) for a wheeled mobile robot which is equipped with an omni-directional vision system. To integrate kinematic and dynamic controllers into the unique controller, we transform the strict feedback system dynamics into tracking error dynamics. Then, we propose a control scheme which uses only one neural network rather than three proposed in the actor-critic-based control schemes for the two-player zero-sum game problem. A neural network weight update law is designed for approximating the solution of the Hamilton–Jacobi–Isaacs equation without knowing knowledge of internal system dynamics. To implement the scheme, we propose the online RADPA, in which control and disturbance laws are updated simultaneously in an iterative loop. The convergence and stability of the online RADPA are proven by Lyapunov techniques. Simulations and experiments on a wheeled mobile robot testbed are carried out to verify the effectiveness of the proposed algorithm.

scholarly journals DESIGNING A ROBUST ADAPTIVE TRACKING BACKTEPPING CONTROLLER CONSIDERING ACTUATOR SATURATION FOR A WHEELED MOBILE ROBOT TO COMPENSATE UNKNOWN SLIPPAGE

2020 ◽  
Vol 36 (2) ◽  
pp. 187-204
Author(s):  
Chung Le ◽  
Kiem Nguyen Tien ◽  
Linh Nguyen ◽  
Tinh Nguyen ◽  
Tung Hoang
Keyword(s):  
Neural Network ◽  
Mobile Robot ◽  
Basis Function ◽  
Actuator Saturation ◽  
Wheeled Mobile Robot ◽  
Technical Solution ◽  
Control Approach ◽  
Adaptive Tracking ◽  
Simulation Results ◽  
Robust Adaptive

This article highlights a robust adaptive tracking backstepping control approach for a nonholonomic wheeled mobile robot (WMR) by which the bad problems of both unknown slippage and uncertainties are dealt with. The radial basis function neural network (RBFNN) in this proposed controller assists unknown smooth nonlinear dynamic functions to be approximated. Furthermore, a technical solution is also carried out to avoid actuator saturation. The validity and efficiency of this novel controller, finally, are illustrated via comparative simulation results.

scholarly journals Experiments on mobile robot stereo vision system calibration under hardware imperfection

2018 ◽  
Vol 161 ◽  
pp. 03020 ◽  
Author(s):  
Ramil Safin ◽  
Roman Lavrenov ◽  
Subir Kumar Saha ◽  
Evgeni Magid
Keyword(s):  
Mobile Robot ◽  
Stereo Vision ◽  
Experimental Approach ◽  
Vision System ◽  
Robot Vision ◽  
System Calibration ◽  
Stereo Vision System ◽  
Calibration Methods ◽  
Vertical Level ◽  
Grid Based

Calibration is essential for any robot vision system for achieving high accuracy in deriving objects metric information. One of typical requirements for a stereo vison system in order to obtain better calibration results is to guarantee that both cameras keep the same vertical level. However, cameras may be displaced due to severe conditions of a robot operating or some other circumstances. This paper presents our experimental approach to the problem of a mobile robot stereo vision system calibration under a hardware imperfection. In our experiments, we used crawler-type mobile robot «Servosila Engineer». Stereo system cameras of the robot were displaced relative to each other, causing loss of surrounding environment information. We implemented and verified checkerboard and circle grid based calibration methods. The two methods comparison demonstrated that a circle grid based calibration should be preferred over a classical checkerboard calibration approach.

Path-tracking controller design and implementation of a vision-based wheeled mobile robot

2009 ◽  
Vol 223 (6) ◽  
pp. 847-862 ◽  
Author(s):  
J-L Yang ◽  
D-T Su ◽  
Y-S Shiao ◽  
K-Y Chang
Keyword(s):  
Mobile Robot ◽  
Tracking Control ◽  
Intelligent System ◽  
Vision System ◽  
Dead Reckoning ◽  
Path Tracking ◽  
Wheeled Mobile Robot ◽  
Detection Methods ◽  
Control Laws ◽  
The Dead

This paper presents techniques for building system configuration, control architecture, and implementation of a vision-based wheeled mobile robot (WMR). The completed WMR has been built with the dead-reckoning method so as to determine the vehicle's velocity and posture by the numerical differentiation/integration over short travelling. The developed proportional-integral-derivative (PID) controllers show good transient performances; that is, the velocity of right and left wheels can track the commands quickly and correctly. Moreover, the path-tracking control laws have also been executed within the digital signal processor (DSP)-based controller in the WMR. The image-recognized system can obtain motion information at 15 frames/s by using the hybrid intelligent system (HIS) model, which is one of the well-known colour detection methods. The better performance a vision system has, the more successful the control laws design. The WMR obtains its posture from the dead-reckoning device together with the vision system. These subsystems are integrated, and the operators of the whole system are completed. This WMR system can be thought of as a platform for testing various tracking control laws and a signal-filtering method. To solve the problem of position/orientation tracking control of the WMR, two kinematical optimal non-linear predictive control laws are developed to manipulate the vehicle to follow the desired trajectories asymptotically. A Kalman filter scheme is used to reduce the bad effect of the imagine nose; thereby the accuracy of pose estimation can be improved. The experimental system is composed of a wireless RS232 modem, a DSP-based controller for the WMR, and a vision system with a host computer. A computation-effective and high-performance DSP-based controller is constructed for executing the developed sophisticated path-tracking laws. Finally, the simulation and experimental results show the feasibility and effectiveness of the proposed control laws.

Neural Network Vision-Guided Mobile Robot for Retrieving Driving-Range Golf Balls

2006 ◽  
Vol 10 (2) ◽  
pp. 181-186 ◽  
Author(s):  
Elmer P. Dadios ◽  
◽  
Kaoru Hirota ◽  
Michelle L. Catigum ◽  
Albert C. Gutierrez ◽  
...  
Keyword(s):  
Neural Network ◽  
Mobile Robot ◽  
Open Field ◽  
Vision System ◽  
Time Of Day ◽  
Autonomous Mobile Robot ◽  
Rotating Blades ◽  
Driving Range

We developed an autonomous mobile robot with neural network (NN) vision that searches for and collects golf balls on an open or an indoor golf driving range. The robot recognizes range borderlines by red stripes. Scattered golf balls are collected using mechanically designed rotating blades. The NN vision identifies objects that are not golf balls and prevents the robot from picking them. The vision system is robust enough to navigate an open field and pick up the golf balls any time of day. Results of the experiments showed that our proposal operates accurately and reliably.

Sign in / Sign up

Export Citation Format

Share Document