Error regulation strategies for Model Based visual servoing tasks: Application to autonomous object grasping with Nao robot

Moughlbay, Amine Abou; Cervera, E.; Martinet, Philippe

doi:10.1109/icarcv.2012.6485335

Cited by 4 publications

(4 citation statements)

References 17 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The output linguistic terms for each PID gain k p , k i and k d are (Fig. method is used to defuzzify the output variable (22). In order to obtain feasible and optimum value for the PID parameters, the actual gains are computed using the range of each parameter determined experimentally (23) from the outputs of the fuzzy inference system.…”

Section: ) Adaptive Position Controlmentioning

confidence: 99%

“…The gain value is small initially (η 0 ) while the error is larger, and the error is reduced exponentially until it reaches a specific threshold (∂) near the equilibrium point (r φ S = 0). Then, as the orientation error got smaller, the gain switches to a larger gain value (η 0 < η 1 ) to eliminate the remaining orientation error as fast as possible [22]. By using the adaptive orientation signal, the robot end-effector orientation angles are calculated by (28).…”

Section: ) Adaptive Orientation Controlmentioning

confidence: 99%

See 1 more Smart Citation

A Mode-Switching Motion Control System for Reactive Interaction and Surface Following Using Industrial Robots

Nakhaeinia

Payeur

Laganière

2018

IEEE/CAA J. Autom. Sinica

View full text Add to dashboard Cite

This work proposes a sensor-based control system for fully automated object detection and exploration (surface following) with a redundant industrial robot. The control system utilizes both offline and online trajectory planning for reactive interaction with objects of different shapes and color using RGB-D vision and proximity/contact sensors feedback where no prior knowledge of the objects is available. The RGB-D sensor is used to collect raw 3D information of the environment. The data is then processed to segment an object of interest in the scene. In order to completely explore the object, a coverage path planning technique is proposed using a dynamic 3D occupancy grid method to generate a primary (offline) trajectory. However, RGB-D sensors are very sensitive to lighting and provide only limited accuracy on the depth measurements. Therefore, the coverage path planning is then further assisted by a real-time adaptive path planning using a fuzzy self-tuning proportional integral derivative (PID) controller. The latter allows the robot to dynamically update the 3D model by a specially designed instrumented compliant wrist and adapt to the surfaces it approaches or touches. A modeswitching scheme is also proposed to efficiently integrate and smoothly switch between the interaction modes under certain conditions. Experimental results using a CRS-F3 manipulator equipped with a custom-built compliant wrist demonstrate the feasibility and performance of the proposed method.

show abstract

Section: ) Adaptive Position Controlmentioning

confidence: 99%

Section: ) Adaptive Orientation Controlmentioning

confidence: 99%

A Mode-Switching Motion Control System for Reactive Interaction and Surface Following Using Industrial Robots

Nakhaeinia

Payeur

Laganière

2018

IEEE/CAA J. Autom. Sinica

View full text Add to dashboard Cite

show abstract

“…La plataforma NAO, utilizada en este proyecto, ha sido usada en visual servoing [9], fútbol robótico [10], aprendizaje de movimientos por imitación [11], navegación en ambientes [12], técnicas de caminata bípeda [13], además en estudios sobre la interacción humanorobot, donde el sistema de visión permite la grabación de la actividad, y la detección de rostros, movimientos de asentimiento y negación con la cabeza [14], [15], [16], entre otras.…”

Section: Plataforma Robóticaunclassified

Screw and wrench orientation estimation using the artificial vision in the NAO humanoid robot

Pena

Hoyos

Prieto

et al. 2013

2013 II International Congress of Engineering Mechatronics and Automation (CIIMA)

View full text Add to dashboard Cite

Resumen-Industrial robots are having major involvement in assembly lines, where they are able to identify, classify and even grasp objects and place them in non-default locations; furthermore, assembling pieces autonomously. We describe step by step the image processing to determine the objects orientation located in the field of view of the NAO robot, initial step in posterior developments in task execution using those objects. The processing stages described are: RGB color space segmentation, interest points detection and objects orientation estimation with respect to a reference frame. The results are compared with measures obtained using a commercial image processing software. The absolute error is less than 1.5 o in the objects orientation angles, which is considered acceptable due to the size of the processed objects. The introduced methodology is a first step in the execution of assembling tasks or handling of tools by a robotic platform, where the artificial vision has a relevant place in the identification, location and orientation of the objects.Index Terms-Image processing, objects detection, image segmentation, humanoid robots, robotic vision systems I. INTRODUCCIÓNLa programación por demostración (PbD por sus siglas en inglés) es una técnica donde, al contrario de la programación detallada que convencionalmente se hace al robot, este aprende movimientos parciales o incluso una tarea completa, con sólo ver una o varias demostraciones por parte de un humano.1 Docente Universidad del Quindío Entre las tareas que se espera desarrollen los robots, es común que se requiera la interacción con herramientas para llevar a cabo una determinada acción. El manejo de herramientas puede dividirse en: reconocimiento, agarre y posicionado, y reproducción de los movimientos para realizar la tarea. La plataforma utilizada, denominada NAO [1], es un robot humanoide programable de 58 centímetros de alto desarrollado por la compañía francesa Aldebaran. Entre sus principales características se encuentran: un cuerpo con 25 grados de libertad, una red de sensores, incluyendo dos cámaras, 4 micrófonos, sensor de distancia basado en ultrasonido, dos emisores y receptores infrarrojos, sensor de inercia, 9 sensores táctiles, y 8 sensores de presión. El autómata contiene una CPU Intel ATOM a 1,6 GHz que ejecuta un kernel Linux soportando el middleware propietario de Aldebaran (NAOqi). En este proyecto los programas se escribieron en lenguaje C++, accediendo desde un portátil a la cámara del robot y obteniendo el video en tiempo real.El trabajo presentado hace parte de un proyecto que pretende desarrollar técnicas que integren visión, programación por demostración y medida de fuerzas para realizar la tarea de apretar una tuerca. El robot, a partir de la demostración, aprende el movimiento de apretar, con la visión se logra flexibilidad en la tarea demostrada ya que permite variaciones de posición y orientación de la tuerca, con lo que se puede alinear la llave con la cabeza del tornillo, porúltimo se hace una medida de la corrient...

show abstract

“…robot control based on visual information, has been a well studied problem [1], [2]. Several methods were developed targeting different applications, such as grasping [3], mobile robot navigation [4] or autonomous aerial vehicle guidance [5]. In this paper we are interested in visual servoing using a robot head, commonly referred to as head-eye coordination, which was studied in a wide range of applicative scenarios involving a single object/person of interest [6], [7], [8], [9], [10], [11], [12], [13], [14] and based on methodologies such as detect and pursuit, image feature tracking, or Kalmann filtering.…”

Section: Introductionmentioning

confidence: 99%

Tracking a varying number of people with a visually-controlled robotic head

Ban

Alameda-Pineda

Badeig

et al. 2017

2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Abstract-Multi-person tracking with a robotic platform is one of the cornerstones of human-robot interaction. Challenges arise from occlusions, appearance changes and a time-varying number of people. Furthermore, the final system is constrained by the hardware platform: low computational capacity and limited field-of-view. In this paper, we propose a novel method to simultaneously track a time-varying number of persons in three-dimensions and perform visual servoing. The complementary nature of the tracking and visual servoing enables the system to: (i) track several persons while compensating for large ego-movements and (ii) visually control the robot to keep a selected person of interest within the field of view. We propose a variational Bayesian formulation allowing us to effectively solve the inference problem through the use of closed-form solutions. Importantly, this leads to a computationally efficient procedure that runs at 10 FPS. The experiments on the NAO-MPVS dataset confirm the importance of using visual servoing for tracking multiple persons.

show abstract

Error regulation strategies for Model Based visual servoing tasks: Application to autonomous object grasping with Nao robot

Cited by 4 publications

References 17 publications

A Mode-Switching Motion Control System for Reactive Interaction and Surface Following Using Industrial Robots

A Mode-Switching Motion Control System for Reactive Interaction and Surface Following Using Industrial Robots

Screw and wrench orientation estimation using the artificial vision in the NAO humanoid robot

Tracking a varying number of people with a visually-controlled robotic head

Contact Info

Product

Resources

About