Oscar Nasisi

Adaptive servo visual robot control

Abstract Adaptive controllers for robot positioning and tracking using direct visual feedback with camera-in-hand configuration are proposed in this paper. The controllers are designed to compensate for full robot dynamics. Adaptation is introduced to reduce the design sensitivity due to robot and payload dynamics uncertainties. It is proved that the control system achieves the motion control objective in the image coordinate system. Simulations are carried out to evaluate the controller performance. Also, discretization and measurement effects are considered in simulations.

Stable AGV corridor navigation with fused vision-based control signals

This work presents a control strategy for mobile robots navigating in corridors, using the fusion of the control signals from vision based controllers. To this aim two controllers are proposed to generate the control signals to be fused: one is based on the optical flow calculation and the other is based on the perspective lines in the corridor. Both controllers generate angular velocity commands to keep the robot navigating along the corridor, and compensate for the dynamics of the robot. The fusion of both control signals is made by using a Kalman filter. Stability of the resulting control system in analyzed. Experiments on a laboratory robot are presented to show the feasibility and performance of the proposed controller.

Adaptive robot control with visual feedback

In this paper we propose an adaptive controller for robots with camera-in-hand configuration using visual feedback. The controller is designed to compensate for full robot dynamics. Adaptation is introduced to reduce the design sensitivity due to robot and payload dynamic uncertainties. The control system is proved to asymptotically achieve the position control objective in the image coordinate system. Simulations are carried out to evaluate the controller performance.

Combined force and visual control of an industrial robot

This work proposes control structures that efficiently combine force control with vision servo control of robot manipulators. Impedance controllers are considered which are based both on visual servoing and on physical or fictitious force feedback, the force and visual information being combined in the image space. Force and visual servo controllers included in extended hybrid control structures are also considered. The combination of both force and vision based control allows the tasks range of the robot to be extended to partially structured environments. The proposed controllers, implemented on an industrial SCARA-type robot, are tested in tasks involving physical and virtual contact with the environment.

Mobility and Orientation aid for blind persons using Artificial Vision

Blind or vision-impaired persons are limited in their normal life activities. Mobility and orientation of blind persons is an ever-present research subject because no total solution has yet been reached for these activities that pose certain risks for the affected persons. The current work presents the design and development of a device conceived on capturing environment information through stereoscopic vision. The images captured by a couple of video cameras are transferred and processed by configurable and sequential FPGA and DSP devices that issue action signals to a tactile feedback system. Optimal processing algorithms are implemented to perform this feedback in real time. The components selected permit portability; that is, to readily get used to wearing the device.

Vision-Based Interfaces Applied to Assistive Robots

This paper presents two vision-based interfaces for disabled people to command a mobile robot for personal assistance. The developed interfaces can be subdivided according to the algorithm of image processing implemented for the detection and tracking of two different body regions. The first interface detects and tracks movements of the users head, and these movements are transformed into linear and angular velocities in order to command a mobile robot. The second interface detects and tracks movements of the users hand, and these movements are similarly transformed. In addition, this paper also presents the control laws for the robot. The experimental results demonstrate good performance and balance between complexity and feasibility for real-time applications.

Robotic wheelchair controlled through a vision-based interface

In this work, a vision-based control interface for commanding a robotic wheelchair is presented. The interface estimates the orientation angles of the users head and it translates these parameters in command of maneuvers for different devices. The performance of the proposed interface is evaluated both in static experiments as well as when it is applied in commanding the robotic wheelchair. The interface calculates the orientation angles and it translates the parameters as the reference inputs to the robotic wheelchair. Control architecture based on the dynamic model of the wheelchair is implemented in order to achieve safety navigation. Experimental results of the interface performance and the wheelchair navigation are presented.

Tracking adaptive impedance robot control with visual feedback

In this paper we propose a tracking adaptive impedance controller for robots with visual feedback. It is based on a generalized impedance concept where the sensed distance is introduced as a fictitious force to the control in order to avoid obstacles in restricted motion tasks. The controller is designed to compensate for full non-linear robot dynamics. Robot parameters adjustment is introduced to reduce the sensibility of the controller design to dynamic uncertainties of the robot and the manipulated load. It is proved that the vision control errors are ultimately bounded in the image coordinate system. Simulations are carried out to evaluate the controller performance.

Control based on perspective lines of a non-holonomic mobile robot with camera-on-board

This paper addresses the control of wheeled mobile robots based on visual information of perspective lines. These lines can be generated by the projection of environment lines like those formed by the intersection of walls and floor, the structural features delimiting paths, or by painted lines on the floor. The control objective is to navigate at a desired speed along the lines, keeping a specified separating distance from them. No assumption is made on the absolute location of either the robot or the lines. A smooth time-invariant controller is proposed in order to command the angular velocity of the robot, while the linear velocity is generated to achieve a cautious and smooth motion. By invoking the LaSalles invariance principle convergence is shown to a proper invariant set which guarantees accomplishment of the control objective. Finally, experimental results illustrating the performance of the control system are presented.

A stable visual servo controller for camera-in-hand robotic systems

In this paper we present a new visual servo controller for camera-in-hand robotic systems. We provide a Lyapunov stability analysis including the full nonlinear robot dynamics into the overall closed-loop system. Besides the closed-loop stability property, the control system obviates the use of the inverse kinematics and inverse Jacobian. Experiments on a two degrees of freedom robot manipulator are presented to illustrate the controller performance.