Movement-Flow-Based Visual Servoing and Force Control Fusion for Manipulation Tasks in Unstructured Environments

Abstract

Abstract-In this paper, a new approach for fusing visual and force information is shown. First, a new method for tracking trajectories, called movement flow-based visual servoing system, which presents the correct behavior in the image and in the three-dimensional space, is described. The information obtained from this system is fused with that obtained from a force control system in unstructured environments. To do so, a new method of recognizing the contact surface and a system for fusing visual and force information are described. The latter method employs variable weights for each sensor system, depending on a criteria based on the detection of changes in the interaction forces processed by a Kalman filter.

Automatic robotic tasks in unstructured environments using an image path tracker

“…This aspect is more clearly described in Section 5.3. In previous works a time-independent (the references do not depend on the time) tracking system based on image-based visual servoing has been presented (Pomares & Torres, 2005). This approach, called movement flow-based visual servoing, employs the concept of movement flow.…”

“…Movement flow-based visual servoing (Pomares & Torres, 2005) is a time-independent method to track trajectories in the image space using a visual servoing system. However, this method presents problems when high velocities are required for the tracking.…”

“…To solve the time-variable reference problem previously addressed, in Pomares and Torres (2005), a time-independent method to track trajectories called movement flow-based visual servoing is presented. However, this method presents several problems which must be solved in order to be applied in a real workspace.…”

A cooperative robotic system based on multiple sensors to construct metallic structures

“…Only two techniques have been found in the literature with this time-independent behaviour when tracking an image path using visual servoing [15,16]. In [16], the visual servoing system proposed to track the trajectory in the image moves the robot to a position in the path by using a classical image-based visual servoing control law.…”

“…Thus, this system is not able to maintain a constant velocity during the tracking. In [15] a visual servoing approach based on movement flow is presented. The movement flow is a vector field that indicates the direction in which the desired features to be used by an image-based visual servoing system must be located.…”