A Switched-System Approach to Shared Robust Control and Obstacle Avoidance for Mobile Robots

2014 ◽  
Author(s):  
Jingfu Jin ◽  
Nicholas Gans ◽  
Yoon-Gu Kim ◽  
Sung-Gil Wee
Keyword(s):  
Robust Control ◽  
Mobile Robots ◽  
Obstacle Avoidance ◽  
System Approach ◽  
Variable Structure ◽  
Switched System ◽  
Shared Control ◽  
Nonholonomic Mobile Robots ◽  
Control Approach ◽  
Free Region

We propose a shared control structure for nonholonomic mobile robots, in which a human operator can command motions that override autonomous operation, and the robot overrides either the teleoperation or autonomous controller if it encounters an obstacle. We divide the whole configuration, including orientation, space into an obstacle avoidance and an obstacle-free region. This enables a switched-system approach to switch between autonomous and teleoperation mode, or the obstacle avoidance and the obstacle-free region. To reject disturbances or noise present in the error dynamics, two different robust control laws are proposed using a high gain and a variable structure approach. Lyapunov-based stability analysis is provided. To rigorously test the approach under different circumstances, experiments have been conducted by two different research groups. The results from two groups show that the shared control approach works effectively both in the teleoperation mode and autonomous mode with different system settings and environments.

Fuzzy Behavior-Based Control for a Task of Three-Link Manipulator with Obstacle Avoidance

1999 ◽  
Vol 11 (6) ◽  
pp. 502-509 ◽  
Author(s):  
Palitha Dassanayake ◽  
◽  
Keigo Watanabe ◽  
Kiyotaka Izumi ◽  
◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Mobile Robots ◽  
Obstacle Avoidance ◽  
Basic Concept ◽  
Online Information ◽  
Acceptable Solution ◽  
Control Approach ◽  
Task Control ◽  
Behavior Based Control ◽  
Behavior Based

Our objective is for a 3-link manipulator to reach a target while avoiding obstacles with online information using a fuzzy-behavior-based control approach. Control applied to mobile robots elsewhere is modified to suit to the manipulator. Fuzzy behavior elements are trained using a genetic algorithm. A component apart from the basic concept is introduced to overcome gravitation. Result shows the manipulator reaches the target with an acceptable solution for 3 simulations, so the proposed approach is suitable to multilink manipulator task control.

scholarly journals Discrete-time predictive trajectory tracking control for nonholonomic mobile robots with obstacle avoidance

2019 ◽  
Vol 16 (5) ◽  
pp. 172988141987731
Author(s):  
Jingjun Zhang ◽  
Shaobo Zhang ◽  
Ruizhen Gao
Keyword(s):  
Obstacle Avoidance ◽  
Discrete Time ◽  
Trajectory Tracking ◽  
Tracking Control ◽  
Control Law ◽  
Nonholonomic Mobile Robots ◽  
Trajectory Tracking Control ◽  
Time Model ◽  
Control Approach ◽  
Avoidance Control

This article presents a tracking control approach with obstacle avoidance for a mobile robot. The control law is composed of two parts. The first is a discrete-time model predictive method-based trajectory tracking control law that is derived using an optimal quadratic algorithm. The second part is the obstacle avoidance strategies that switch according to two different designed obstacle avoidance regions. The controllability of the avoidance control law is analyzed. The simulation results validate the effectiveness of the proposed control law considering both trajectory tracking and obstacle avoidance.

Neural Control System for Autonomous Vehicles

2011 ◽  
pp. 1197-1204
Author(s):  
Francisco García-Córdova ◽  
Antonio Guerrero-González ◽  
Fulgencio Marín-García
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Mobile Robot ◽  
Mobile Robots ◽  
Obstacle Avoidance ◽  
Neural Control ◽  
Learning Rule ◽  
Nonholonomic Mobile Robots ◽  
Neural Architecture ◽  
Neuro Controller

Neural networks have been used in a number of robotic applications (Das & Kar, 2006; Fierro & Lewis, 1998), including both manipulators and mobile robots. A typical approach is to use neural networks for nonlinear system modelling, including for instance the learning of forward and inverse models of a plant, noise cancellation, and other forms of nonlinear control (Fierro & Lewis, 1998). An alternative approach is to solve a particular problem by designing a specialized neural network architecture and/or learning rule (Sutton & Barto, 1981). It is clear that biological brains, though exhibiting a certain degree of homogeneity, rely on many specialized circuits designed to solve particular problems. We are interested in understanding how animals are able to solve complex problems such as learning to navigate in an unknown environment, with the aim of applying what is learned of biology to the control of robots (Chang & Gaudiano, 1998; Martínez-Marín, 2007; Montes-González, Santos-Reyes & Ríos- Figueroa, 2006). In particular, this article presents a neural architecture that makes possible the integration of a kinematical adaptive neuro-controller for trajectory tracking and an obstacle avoidance adaptive neuro-controller for nonholonomic mobile robots. The kinematical adaptive neuro-controller is a real-time, unsupervised neural network that learns to control a nonholonomic mobile robot in a nonstationary environment, which is termed Self-Organization Direction Mapping Network (SODMN), and combines associative learning and Vector Associative Map (VAM) learning to generate transformations between spatial and velocity coordinates (García-Córdova, Guerrero-González & García-Marín, 2007). The transformations are learned in an unsupervised training phase, during which the robot moves as a result of randomly selected wheel velocities. The obstacle avoidance adaptive neurocontroller is a neural network that learns to control avoidance behaviours in a mobile robot based on a form of animal learning known as operant conditioning. Learning, which requires no supervision, takes place as the robot moves around a cluttered environment with obstacles. The neural network requires no knowledge of the geometry of the robot or of the quality, number, or configuration of the robot’s sensors. The efficacy of the proposed neural architecture is tested experimentally by a differentially driven mobile robot.

Sign in / Sign up

Export Citation Format

Share Document