Yibin Li

Control of an inspection robot for 110KV power transmission lines based on expert system design methods

The paper presents a new control strategy and its real-time implementation for a power transmission line inspection robot based on expert system design methods. In this paper, an algorithm is proposed to coordinate the operations between distributed expert systems, in which the principle of the goodness to fit to the rules and facts is employed for decision making and reasoning. To implement the control strategy, a combination of computer languages including C, VC++ and CLIPS are adopted that provide a convenient and effective software platform. On-line experiment results show that the control strategy can guide the inspection robot to patrol along the transmission lines and cross various typical obstacles efficiently. At the locations of corners and bends of the transmission line, more complicated obstacles occur, so two sub-expert systems work together and guide the robot passing through the locations smoothly. At those locations, the speed of the robot obviously slows down for safety consideration

Study on Intelligent Vehicle Lane Change Path Planning and Control Simulation

For autonomous intelligent vehicle (TV), lane change is an important lateral motion pattern which comprises path planning and path track control. Firstly, a kind of IV lane change Path planning algorithm, which satisfies jerk restraint (LCP2SJR), was developed. Then fuzzy-neural network (FNN) and genetic algorithm (GA) were used to design the IV Lane Change robust controller (LCRC). At last, simulations of the lane change track control were done. The results show that under the guidance of the path planed by LCP2SJR and the control of LCRC, IV can implements high precise, smooth and strong robust lane change motion.

ADRC Based Ship Course Controller Design and Simulations

Because of the strong non-linearity, uncertainty and the dynamics restraints of rudder, designing a high performance ship course controller is yet a challenge work. First, the ADRC control method was introduced briefly. Then the ship course motion characteristics were analyzed and the nonlinear model with the autopilot dynamic restrictions was given. Then the ship course motion system was expressed as a serial system, and the ADRC controllers were designed. At last, the ships course change and keeping control simulations were done in uncertainty environment. The results show that the ADRC controller can adapt well to the nonlinearity of ship course motion and has strong robustness to ships parameter perturbations and the systems disturbances.

Application of Artificial Neural Network Based on Q-learning for Mobile Robot Path Planning

Path planning is a difficult part of the navigation task for the mobile robot under dynamic and unknown environment. It needs to solve a mapping relationship between the sensing space and the action space. The relationship can be achieved through different ways. But it is difficult to be expressed by an accurate equation. This paper uses multi-layer feedforward artificial neural network (ANN) to construct a path-planning controller by its powerful nonlinear functional approximation. Then the path planning task is simplified to a classified problem which are five state-action mapping relationship. One reinforcement learning method, Q-learning, is used to collect training samples for the ANN controller. At last the trained controller runs in the simulation environment and retrains itself furthermore combining the reinforcement signal during the interaction with the environment. Strategy based on the Combination of ANN and Q-learning is better than using only one of the two methods. The simulation result also shows that the strategy can find the optimal path than using Q-learning only.

Q-Learning Based Method of Adaptive Path Planning for Mobile Robot

Reinforcement learning (RL) is a learning technique based on trial and error. Q-learning is a method of RL algorithms. It has been applied widely in the adaptive path planning for the autonomous mobile robot. In order to decrease the learning space and increase the learning convergent speed, this paper adopts Q-layered learning method to divide the task of searching optimal path into three basic behaviors (or subtasks), namely static obstacle-avoidance, dynamic obstacle-avoidance and goal approaching. Especially in the learning for the static obstacle-avoidance behavior, a novel priority Q search method (PQA) is used to avoid the blindly search of the random search algorithm (RA) which is always used to select actions in Q- learning. PQA uses the sum of weighted vectors pointing away from obstacles to predict the magnitude of the reinforcement reward receiving from the possible state-action after executing the action. Robot controller will select an action based on the result at the next executing time. At last PQA and RA are both simulated in two different environments. The learning results show that learn steps are fewer by PQA than by RA under same environment to achieve the task. And in the total learning periods PQA has the higher task complete percent. PQA is an effective way to solve the problem of the path planning under dynamic and unknown environment.

Multi-objective Path Planning for the Mobile Robot

Based on the global information environment, this paper introduces a multi-objective path planning algorithm for the mobile robot using grid map under the uncertainty environment. Establish global information environment maps utilizing Hough transform. Give value to the free grids using target distance information to simplify the establishment of the grid maps state space and the search strategy. Execute relatively shortest path search using the state space of the grid map with path chain list method. On this basis will give a group of path meeting with several indexes. The exploration method doesnt need complicated computation. Furthermore it is effectiveness in maturity, time complexity, space complexity and optimization meeting with multi-objective. The simulation results also demonstrate the effectiveness of the algorithm.

The Design and Implementation of OpenGL-based Comprehensive Educational Robot System

In this paper, the authors present the design and implementation of MountTai, a cost effective OpenGL based comprehensive educational robot system for Chinas primary and high school education. Firstly the systems goal and framework is introduced, then it is described the MountTai robots functions and construction in hardware. The paper expatiates at length how VR technology is used to implement the system software as well as how the softwares functions are designed to illustrate robotics in different perspectives relating to mechanics, electronics, communication, artificial intelligence, language programming. The Web-based teaching course dedicated to robot-DIY tutorials is also shown. Finally, concluding remarks for future works are given.

Design of Wireless Sensor Network Node CC2510 Based and Study on Communication Protocol

Design of wireless sensor node with CC2510, which is a low-cost system-on-chip containing a UHF RF transceiver and a high performance, low-power 8051-based microcontroller is introduced, and based on this node communication protocol was studied. The power cost of the node is low, and the size is small. The wireless sensor network realized data many to jump and the self-organization when the nodes were randomly distributed. It can be applied to various fields, such as data wireless communication systems, military affairs scout, environmental monitoring, and safe precaution systems

Search strategy of path for mobile robot

In this paper, a model-based strategy is used to realize rapid searching of the shortest path in order to solve the global optimizing problem in the path planning of the mobile robot. The Hough transform is used to build the cell map of the working environment for the mobile robot by extracting the fringes information of the solid obstacles and map them into a 2D plane. We simplify the construction of the state space and design of the search strategy based on free cells evaluation by the distance which is between the start point and the goal point. The relatively shortest paths search is realized through the state space of the cell map by path search tree. The experimental and simulation results show that the path search strategy doesnt need complicated computations. Furthermore it is effectiveness in completeness, time complexity, space complexity and optimality.

Control Strategy and Implementation of an Inspection Robot for 110kV Power Transmission Lines

A new control strategy and its real-time implementation were presented for a power transmission line inspection robot based on expert system. Furthermore an algorithm was proposed to coordinate the operations between distributed expert systems, in which the principle of the goodness to fit to the rules and facts was employed for the decision making and reasoning mechanism. To implement the control strategy, a combination of computer languages including C, VC++ and CLIPS were adopted to provide a convenient and effective software platform. On-line experiment results show that the control strategy can guide the inspection robot to patrol along the transmission lines and cross various typical obstacles efficiently. At the locations of corners and bends of the transmission line, more complicated obstacles occur, so two sub-expert systems work together and guide the robot passing through the locations smoothly. At those locations, the speed of the robot obviously slows down for safety consideration