Tse Min Chen

Development of a multi-behavior based mobile robot for remote supervisory control through the Internet

We review the networked mobile robot systems and suggest taxonomy based on the three levels of control commands. The performance analysis result shows that direct control has potential difficulty for implementation due to the unpredicted transmission delay of the network. To tackle this problem, we have suggested the behavior-programming control concept to avoid disturbances of the Internet latency. For this purpose, primitive local intelligence of the mobile robot is grouped into motion planner, motion executor, and motion assistant, where each of a group is treated as an agent. They are integrated by centralized control architecture based on multi-agent concept, communicated through a center information memory. The event-driven concept is applied on the robot to switch the behaviors to accommodate the unpredicted mission autonomously. We have successfully demonstrated experimentally the feasibility and reliability for system through a performance comparison with direct remote control.

Intelligent autonomous mobile robot control through the Internet

With rapid growth of computer technology, Internet-based teleoperation of robotic systems has created new opportunities in resources sharing, long-distance learning, and remote experimentation. This paper presents a basic architecture and its functional components for remote control of robotic systems. A variety of control modes for existing robotic systems were surveyed and the Internet transmission latency was discussed. An illustrative application was used to demonstrate the effectiveness of the proposed architecture and the control scheme. Experimental results clearly indicate that the proposed behavior control mode is superior to direct control mode in terms of efficiency, operating environment, complex task handling, and control capability.

Remote supervisory control of a sensor based mobile robot via Internet

A remote supervisory control architecture which combines computer network and an autonomous mobile robot is constructed. The main feature of this architecture is that users just need a general purpose computer and a World Wide Web browser, they can command the mobile robot in a remote location through Internet and Home Page. Hardware configuration of this architecture includes a mobile robot, as server workstation, and other computers, each of them is able to communicate with others via computer network. Software design includes assignment of the server, communication between the server and robot, and the user interface. The architecture has extensive capabilities for teleoperation, telerobotics operations, and other multimedia services. Based on this architecture we have implemented multilevel operations for the user on various remote applications. At present, the system allows users to operate our mobile robot via the Internet and a friendly user interface (via our Home Page) using supervisory and direct control modules and they can receive live images captured by a CCD camera which is mounted on the robot and other data from sensor measurement.

Mobile target tracking using hierarchical grey-fuzzy motion decision-making method

This paper presents a hierarchical grey-fuzzy motion decision-making (HGFMD) algorithm, which is capable of integrating multiple sequential data for decision making and for the design of the control kernel of the target tracking system. The algorithm combines multiple grey prediction modules, each of them can online estimate the suitable model from sequential sensory information to approximate the observed dynamic system model for future-trend prediction, and for decision making through a multilayered fuzzy logic inference engine. We designed the HGFMD controller for target tracking system and implemented in our autonomous mobile robot. The HGFMD is compared with the conventional fuzzy logic controller, multilayered fuzzy controller, and the original grey-fuzzy controller we have developed previously in various target-tracking experiments. The results obtained show the high reliability of the HGFMD controller and tracking system.

Visual tracking using adaptive color histogram model

Color provides a useful cue for image analysis and object recognition in robotics and automation applications. In most color based target recognition systems, the color models are invariant in a-priori and are never adjusted while the illumination condition changed. In this case, the system recognition is prone to error due to the change of surrounding illumination. To solve this problem, we have proposed a modeling method with high-tolerance based on probability distribution. The model is adaptive based on the change of illumination condition through on-line adjustment of the model parameters. We called this vision system an adaptive color vision system (ACVS). In this paper, we describe this ACVS system in detail and demonstrate it through the application of the histogram backprojection algorithm. We have conducted experiments which demonstrate the color object tracking by ACVS in a natural environment is an adaptive robustness and flexible system.

Multisensor based autonomous mobile robot through Internet control

A remote supervisory control system that combines a computer network and an autonomous mobile robot is constructed. The main feature of this system is that users just need a general-purpose computer and a World Wide Web browser, they can command the mobile robot in a remote location through the Internet and Home Page. Hardware configuration of this architecture includes an autonomous mobile robot, server workstation, and other computers, each of them is able to communicate with others via a computer network. Software design includes assignment of the server, communication between the server and robot, and the user interface. The system has extensive capabilities for teleoperation, telerobotics operations, and other multimedia services. Based on this architecture we have implemented multi-level operations for the user on various remote applications. The system allows users to directly control our mobile robot via the Internet and a friendly user interface (via our Home Page), and they can receive real-time images captured by a CCD camera that is mounted on the robot and other data from sensor measurement. At present, one can select a place in our laboratory by clicking a point on the grid map shown in the Home Page WWW. After receiving the high level command, the robot will deliver the sequential live images during the movement to the remote user site.

Networked intelligent autonomous mobile robot: issues and opportunities

A truly intelligent autonomous mobile robot should have a common representation model, which can simultaneously satisfy low level navigational capabilities, medium level self-referencing capabilities, high level motion planning capabilities, and the ability to be controlled through the Internet. In this presentation, the issues for a truly intelligent autonomous mobile robot is first addressed. The issues for supervisory control of an intelligent autonomous mobile robot through the Internet will also be discussed. Finally, the opportunities for the application of intelligent autonomous mobile robot is described. Video presentation to demonstrate the feasibility of these techniques is also included.

Multilevel multi-agent based team decision fusion for mobile robot behavior control

Multilevel fusion is a key issue for developing the decision-making kernel of multi-agent systems. This article presents a formulation of predictive decision-making algorithm for multilevel multi-agent based team decision-making system with the I/O mode characterizations of features in decision methods. The sequential data fusion is conducted through a dynamic behavior modeling method capable of estimating the observed system parameters from the raw sensory measurements over a period of time. The method is implemented for an autonomous tracking system that consists of a target tracking agent whose inputs are visual and ultrasonic range measurements, and a collision avoidance agent whose inputs are ultrasonic range measurements. The experimental results conducted by a mobile robot and intelligent electrical wheelchair demonstrate the feasibility, accuracy and robustness of the system based on the multisensor fusion method.

Multiagent system with event driven control for autonomous mobile robot navigation

A multiagent with event driven obstacle avoidance system (MEDOAS) has been developed, which is capable of avoiding stationary and moving obstacles and achieve the goal position. The multiagent design enables the mobile robot to perform sensing, steering and driving control in parallel. Event driven motion control of the system enables the robot to cope with various difficulties of the given assignment in a dynamic changing task environment. The MEDOAS is implemented by multi-thread programming on a time sharing operating system running on the main control system on our mobile robot system in the laboratory. The performance of MEDOAS is experimentally tested on the mobile robot. Experimental results demonstrate the resultant MEDOAS system capable of navigating a mobile robot through the cluttered environment efficiently.

Integrated multi-behavior mobile robot navigation using decentralized control

The components for providing autonomous capabilities of a mobile robot are grouped into few basic modules, namely motion planner, motion executor, motion assistant, and behavior arbitrator. The primitive motion executors such as obstacle avoidance, goal following, wall following, docking, and path tracking for mobile robot navigation are developed in this paper. They are integrated with motion planner, motion assistants, and behavior arbitrator together based on decentralized control architecture with a hierarchical shared information memory. Event driven concept is used on switching the motion behaviors. The resultant intelligence for mobile robot navigation is capable of efficiently performing motion behavior and detecting environmental event in parallel to adapt dynamically changed environment. It also allows the human to program the motion behaviors in high level to complete a task. Experimental results on a real mobile robot have demonstrated the robustness of the motion executors and the overall system.