Control Framework for Dexterous Manipulation Using Dynamic Visual Servoing and Tactile Sensors’ Feedback

Abstract

Tactile sensors play an important role in robotics manipulation to perform dexterous and complex tasks. This paper presents a novel control framework to perform dexterous manipulation with multi-fingered robotic hands using feedback data from tactile and visual sensors. This control framework permits the definition of new visual controllers which allow the path tracking of the object motion taking into account both the dynamics model of the robot hand and the grasping force of the fingertips under a hybrid control scheme. In addition, the proposed general method employs optimal control to obtain the desired behaviour in the joint space of the fingers based on an indicated cost function which determines how the control effort is distributed over the joints of the robotic hand. Finally, authors show experimental verifications on a real robotic manipulation system for some of the controllers derived from the control framework.

FPGA-based architecture for direct visual control robotic systems

“…With the objective of evaluating the improvements obtained when applying the control architecture based on FPGA, this section compares the behavior when applying the control law with chaos compensation obtained when considering W = M −2 by using the proposed architecture in comparison with previous implementations [17] . More specifically, both implementations are evaluated for the tracking of the periodic trajectory indicated in Eq.…”

“…A controller based on the framework presented in [17] is proposed. However, several modifications have been carried out in this framework.…”

“…Considering the framework described in [17] , the control function that minimizes the applied torques of a robotic system while performing a given task is defined by:…”

“…In order to evaluate this architecture, the proposed framework has been implemented in the FPGA. In previous works [17] , this framework is defined to visually guide robotic systems during the manipulation of rigid objects. In this paper, this framework is modified for obtaining a general framework for robotic arms and then implemented in the FPGAbased architecture.…”

A visuo-tactile control framework for manipulation and exploration of unknown objects

“…They, however, only improve contact quality by sliding/twisting the fingertip on the object, thereby only exploiting three of the full six DOFs of the interaction. The tactile-servoing control framework [10] and a similar work [9] propose exploration of unknown object surfaces by fusing tactile proprioceptive feedback to estimate the contact position and contact force. Both works develop their control framework in a rather problem-specific way, either focusing on grasping and manipulation or on unknown environment exploration.…”