Relative end-effector control using Cartesian position based visual servoing

By W. Wilson, Carol C. W. Hulls, G. Bell. 1996

Subfields: Computer Vision and Pattern Recognition, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Robotics & Control

Citations in the corpus

End-to-End Training of Deep Visuomotor Policies (2015, methodology): “The goal of our approach is also similar to visual servoing, which performs feedback control on feature points in a camera image [6, 27, 42].”
LILA: Language-Informed Latent Actions (2021, background): “Using these controllers for end-effector control – e.g., via operational space control [25] – is incredibly difﬁcult, requiring frequent mode-switching to control speciﬁc robot DoFs [3, 26].”
Deep visual foresight for planning robot motion (2016, methodology): “Our approach is related to visual servoing, which performs feedback control on features in an image [32], [33], [34] or the image pixels themselves [35].”
Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection (2016, methodology): “…methods are typically concerned with reaching a pose relative to objects in the scene, and often (though not always) rely on manually designed or specified features for feedback control (Espiau et al., 1992; Wilson et al., 1996; Vahrenkamp et al., 2008; Hebert et al., 2012; Mohta et al., 2014).”
Deep spatial autoencoders for visuomotor learning (2015, methodology): “The goal of our method is similar to that of visual servoing, which performs feedback control on image features [24], [25], [26].”
Zero-Shot Visual Imitation (2018, background): “Visual servoing is a standard problem in robotics (Koichi & Tom, 1993) that seeks to take actions that align the agent’s observation with a target configuration of carefully-designed visual features (Wilson et al., 1996; Yoshimi & Allen, 1994) or raw pixel intensities (Caron et al., 2013).”
Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning (2018, background): “Traditional approaches aim to minimize distances of feature points [17, 18, 19], or pixel intensities [20].”
Real-Time Visual Tracking of Complex Structures (2002, background): “A distinction is often made in visual servoing [21] between an image-based approach in which the control loop is closed in the image by driving image features home to desired target positions [13], [29] and a position-based approach in which the control loop operates in an explicitly threedimensiona”
Visual servoing of an under-actuated dynamic rigid-body system: an image-based approach (2002, background): “Visual servo systems may be divided into two main classes [17]: position-based visual servo (PBVS) involves reconstruction of the target pose with respect to the robot and leads to a Cartesian motion planning problem [33].”
ViSP for visual servoing: a generic software platform with a wide class of robot control skills (2005, background): “In particular visual servoing types (most of 3D visual servoing, some 2 1/2 D visual servoing and the 2D visual servoing where the depth information must be recomputed at each iteration), the 3D pose of the camera with respect to the scene is required.”
Homography-based 2D Visual Tracking and Servoing (2007, methodology): “the visual information acquired from the two images (the reference and the current images) is used to explicitly reconstruct the pose (the translation and the rotation in Cartesian space) of the camera (see, for example, Wilson et al. 1996 � Martinet et al. 1997� Basri et al. 1998� Taylor et al. 20”
Survey on Visual Servoing for Manipulation (2002, methodology): “(Walter & Schulter 1993) 3 EL VM4 (Westmore & Wilson 1990) 3 PB VM1 (Wilson et al. 1996) 2/4 PB VM1 (Wunsch & Hirzinger 1997) 6 PB VM1 (Xiao et al.”
Point-based and region-based image moments for visual servoing of planar objects (2005, methodology): “The goals were to combine 2D features and 3D features to decouple the control of the rotation from the control of the translation (as in 3D visual servoing), to ensure as much as possible the visibility of the object in the camera field of view, and also to demonstrate the global stability of the…”
Visual servoing for humanoid grasping and manipulation tasks (2008, background): “Cartesian position and/or orientation of the TCP with respect to the target pose ([ 10 ], [11], [12], [13]).”
Kalman Filter for Robot Vision: A Survey (2012, background): “The data provided by all the cameras are selected according to the prediction of the object self-occlusions, as well as of the mutual occlusions caused by the robot links and tools [19], [32], [92]–[94].”