An Efficient Neural Network Model for Path Planning of Car-like Robots in Dynamic Environment

2000 ◽  
Vol 4 (3) ◽  
pp. 220-229 ◽  
Author(s):  
Simon X. Yang ◽  
◽  
Max Meng ◽  
Keyword(s):  
Neural Network ◽  
Path Planning ◽  
Real Time ◽  
Dynamic Environment ◽  
Lyapunov Stability Theory ◽  
Network Size ◽  
Computationally Efficient ◽  
Neural Network Approach ◽  
The Neural Network ◽  
The Stability

In this paper, an effcient neural network approach to real-time path planning with obstacle avoidance of holonomic car-like robots in a dynamic environment is proposed. The dynamics of each neuron in this biologically inspired, topologically organized neural network is characterized by a shunting equation or an additive equation. The state space of the neural network is the configuration space of the robot. There are only local lateral connections among neurons. Thus the computational complexity linearly depends on the neural network size. The real-time collision-free path is planned through the dynamic neural activity landscape of the neural network without explicitly searching over neither the free workspace nor the collision paths, without any prior knowledge of the dynamic environment, without any learning procedures, and without any local collision checking procedures at each step of the robot movement. Therefore it is computationally efficient. The stability of the neural network is proven by both qualitative analysis and the Lyapunov stability theory. The effectiveness and efficiency are demonstrated through simulation studies.

scholarly journals A Biological Inspired Approach to Collision-Free Path Planning and Tracking Control of a Mobile Robot

2004 ◽  
Vol 8 (3) ◽  
pp. 243-251 ◽  
Author(s):  
Simon X. Yang ◽  
◽  
Max Q.-H. Meng ◽  
Gavin X. Yuan ◽  
Peter X. Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Path Planning ◽  
Mobile Robot ◽  
Real Time ◽  
Free Path ◽  
Tracking Control ◽  
Biological Membrane ◽  
Dynamic Environment ◽  
Dynamic Activity ◽  
Neural Network Approach

In this paper, a novel biologically inspired neural network approach is proposed for real-time collision-free path planning and tracking control of a nonholonomic mobile robot in a dynamic environment. The real-time collision-free robot trajectory is generated by a topologically organized neural network, where the dynamics of each neuron is characterized by a shunting equation derived from Hodgkin and Huxley’s biological membrane equation. The dynamically changing environment is represented by the dynamic activity landscape of the neural network, where the neural activity propagation is subject to the nonholonomic kinematic constraint of the mobile robot. The tracking velocities for the mobile robot are generated by a novel neural dynamics based controller, which is based on two shunting equations and the conventional backstepping technique. Unlike the conventional backstepping controllers suffer from sharp jumps, the proposed tracking controller can generate smooth and continuous commands. The effectiveness and efficiency of the proposed approach are demonstrated through simulation and comparison studies.

scholarly journals Weighted Multiple-Model Neural Network Adaptive Control for Robotic Manipulators with Jumping Parameters

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-12 ◽  
Author(s):  
Jiazhi Li ◽  
Weicun Zhang ◽  
Quanmin Zhu
Keyword(s):  
Neural Network ◽  
Adaptive Control ◽  
External Disturbance ◽  
Lyapunov Stability Theory ◽  
Robotic Manipulators ◽  
Adaptive Observer ◽  
Multiple Model ◽  
Neural Network Controller ◽  
The Neural Network ◽  
The Stability

This study addresses the tracking control issue for n-link robotic manipulators with largely jumping parameters. Based on radial basis function neural networks (RBFNNs), we propose weighted multiple-model neural network adaptive control (WMNNAC) approach. To cover the variation ranges of the parameters, different models of robotic are constructed. Then, the corresponding local neural network controller is constructed, in which the neural network has been used to approximate the uncertainty part of the control law, and an adaptive observer is implemented to estimate the true external disturbance. The WMNNAC strategy with improved weighting algorithm is adopted to ensure the tracking performance of the robotic manipulator system when parameters jump largely. Through the Lyapunov stability theory and the method of virtual equivalent system (VES), the stability of the closed-loop system is proved. Finally, the simulation results of a two-link manipulator verify the feasibility and efficiency of the proposed WMNNAC strategy.

Neural Network Adaptive Control of Free Floating Space Robot with Actuator Saturation

2014 ◽  
Vol 590 ◽  
pp. 380-385 ◽  
Author(s):  
Guo Liang Zhang ◽  
Ting Lei ◽  
Fan Yang ◽  
Zhuang Cai
Keyword(s):  
Neural Network ◽  
Adaptive Learning ◽  
Control Strategy ◽  
Actuator Saturation ◽  
Space Robot ◽  
Global Approximation ◽  
Neural Network Approach ◽  
The Neural Network ◽  
On Line ◽  
The Stability

This paper proposes an adaptive neural network law for trajectory tracking of a class of free-floating space robot with actuator saturation. Using neural network with global approximation, the control strategy design an on-line real time adaptive learning law to approach the uncertain model and the actuator saturation nonlinearity. The neural network approach errors and outside disturbance can be eliminated by a robust controller.The control strategy need not depend on the model, and can be used under actuator saturation.The control strategy can guarantee the stability of system and the asymptotic convergence of tracking errors based on the Lyapunov’s theory. The simulation results indicate that the proposed strategy can effectively work with actuator saturation.

A Biologically Inspired Neural Network Approach to Real-Time Map Building and Path Planning

2011 ◽  
pp. 69-86
Author(s):  
Simon X. Yang
Keyword(s):  
Neural Network ◽  
Path Planning ◽  
Real Time ◽  
Map Building ◽  
Network Approach ◽  
Biologically Inspired ◽  
Dynamic Activity ◽  
Neural Network Approach ◽  
The Real ◽  
Sensor Information

A novel biologically inspired neural network approach is proposed for real-time simultaneous map building and path planning with limited sensor information in a non-stationary environment. The dynamics of each neuron is characterized by a shunting equation with both excitatory and inhibitory connections. There are only local connections in the proposed neural network. The map of the environment is built during the real-time robot navigation with its sensor information that is limited to a short range. The real-time robot path is generated through the dynamic activity landscape of the neural network. The effectiveness and the efficiency are demonstrated by simulation studies.

VIRTUAL INSTRUMENTATION BASED SYSTEMS FOR REAL-TIME PATH PLANNING OF MOBILE ROBOTS USING BIO-INSPIRED NEURAL NETWORKS

2011 ◽  
Vol 10 (03) ◽  
pp. 357-375 ◽  
Author(s):  
ABDALLAH HAMMAD ◽  
SIMON X. YANG ◽  
M. TAREK ELEWA ◽  
HALA MANSOUR ◽  
SALAH ALI
Keyword(s):  
Neural Network ◽  
Path Planning ◽  
Mobile Robots ◽  
Real Time ◽  
Virtual Instruments ◽  
Virtual Instrumentation ◽  
Computing Platform ◽  
The Neural Network ◽  
On Line ◽  
On Line Learning

In this paper, novel virtual instrumentation based systems for real-time collision-free path planning and tracking control of mobile robots are proposed. The developed virtual instruments are computationally simple and efficient in comparison to other approaches, which act as a new soft-computing platform to implement a biologically-inspired neural network. This neural network is topologically arranged with only local lateral connections among neurons. The dynamics of each neuron is described by a shunting equation with both excitatory and inhibitory connections. The neural network requires no off-line training or on-line learning, which is capable of planning a comfortable trajectory to the target without suffering from neither the too close nor the too far problems. LabVIEW is chosen as the software platform to build the proposed virtual instrumentation systems, as it is one of the most important industrial platforms. We take the initiative to develop the first neuro-dynamic application in LabVIEW. The developed virtual instruments could be easily used as educational and research tools for studying various robot path planning and tracking situations that could be easily understood and analyzed step by step. The effectiveness and efficiency of the developed virtual instruments are demonstrated through simulation and comparison studies.

scholarly journals Augmented Reality Maintenance Assistant Using YOLOv5

2021 ◽  
Vol 11 (11) ◽  
pp. 4758
Author(s):  
Ana Malta ◽  
Mateus Mendes ◽  
Torres Farinha
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Object Recognition ◽  
Augmented Reality ◽  
Real Time ◽  
Recognition System ◽  
High Accuracy ◽  
Video Streams ◽  
The Neural Network ◽  
Deep Learning Neural Network

Maintenance professionals and other technical staff regularly need to learn to identify new parts in car engines and other equipment. The present work proposes a model of a task assistant based on a deep learning neural network. A YOLOv5 network is used for recognizing some of the constituent parts of an automobile. A dataset of car engine images was created and eight car parts were marked in the images. Then, the neural network was trained to detect each part. The results show that YOLOv5s is able to successfully detect the parts in real time video streams, with high accuracy, thus being useful as an aid to train professionals learning to deal with new equipment using augmented reality. The architecture of an object recognition system using augmented reality glasses is also designed.

Sign in / Sign up

Export Citation Format

Share Document