On computing task-oriented grasps

El-Khoury, Sahar; Souza, Ravin de; Billard, Aude

doi:10.1016/j.robot.2014.11.016

Cited by 9 publications

(9 citation statements)

References 21 publications

(54 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The grasp wrench space (Mishra et al, 1987;Borst et al, 2004), for example the volume of its largest inscribed sphere (Ferrari and Canny, 1992), can be used as a metric to measure the general quality of a grasp configuration. The task-oriented grasping literature (Dang and Allen, 2012;El-Khoury et al, 2015;Nikandrova and Kyrki, 2015) studies the problem of grasping an object for a particular task, an important part of which is modelling the particular external wrench expected on the target object during the task. For example, Li and Sastry (1988) presents the task wrench space as a metric to measure how good a grasp is under task-relevant external wrenches.…”

Section: Grasp Analysismentioning

confidence: 99%

Manipulation planning under changing external forces

2020

View full text Add to dashboard Cite

show abstract

Section: Grasp Analysismentioning

confidence: 99%

Manipulation planning under changing external forces

2020

View full text Add to dashboard Cite

show abstract

“…These facts are particularly relevant to enable such functions as tactile servoing or slip detection during contact regimes subject to gravity and other external forces, since they allow for mapping patterns of tactile data with autonomous behaviors not mediated by high-level reasoning processes, as it would be required for reactive behaviors in prosthetic devices. It is noteworthy that, as far as robot grasping is concerned, such mappings have been developed by De Souza et al (2015) to infer grasp intentions in humans and by El-Khoury et al (2015) to synthetise robot grasping behaviors for the specific task at hand.…”

Section: From Task-based To Structure-based Designs: the Contributmentioning

confidence: 99%

Active Haptic Perception in Robots: A Review

et al. 2019

View full text Add to dashboard Cite

In the past few years a new scenario for robot-based applications has emerged. Service and mobile robots have opened new market niches. Also, new frameworks for shop-floor robot applications have been developed. In all these contexts, robots are requested to perform tasks within open-ended conditions, possibly dynamically varying. These new requirements ask also for a change of paradigm in the design of robots: on-line and safe feedback motion control becomes the core of modern robot systems. Future robots will learn autonomously, interact safely and possess qualities like self-maintenance. Attaining these features would have been relatively easy if a complete model of the environment was available, and if the robot actuators could execute motion commands perfectly relative to this model. Unfortunately, a complete world model is not available and robots have to plan and execute the tasks in the presence of environmental uncertainties which makes sensing an important component of new generation robots. For this reason, today's new generation robots are equipped with more and more sensing components, and consequently they are ready to actively deal with the high complexity of the real world. Complex sensorimotor tasks such as exploration require coordination between the motor system and the sensory feedback. For robot control purposes, sensory feedback should be adequately organized in terms of relevant features and the associated data representation. In this paper, we propose an overall functional picture linking sensing to action in closed-loop sensorimotor control of robots for touch (hands, fingers). Basic qualities of haptic perception in humans inspire the models and categories comprising the proposed classification. The objective is to provide a reasoned, principled perspective on the connections between different taxonomies used in the Robotics and human haptic literature. The specific case of active exploration is chosen to ground interesting use cases. Two reasons motivate this choice. First, in the literature on haptics, exploration has been treated only to a limited extent compared to grasping and manipulation. Second, exploration involves specific robot behaviors that exploit distributed and heterogeneous sensory data.

show abstract

“…These were collected from human demonstrations of 3 tasks (circle drawing, cutting, screw-driving) with a sensorized tool (i.e. force/torque sensor at the end-effector) El-Khoury et al (2015). These task-ellipsoids are used to represent the principal directions of the forces f = {f x , f y , f z } and torques τ = {τ x , τ y , τ z } exerted on an object to achieve a task.…”

Section: Datasets and Metrics For Similarity Function And Clusteringmentioning

confidence: 99%

“…In Kronander and Billard (2012); Ajoudani et al (2015), stiffness ellipsoids, representing the stiffness of the robot's end-effector, are used to characterize impedance controllers. Further, in Li and Sastry (1988); El-Khoury et al (2015), ellipsoids are used to model tasks in the wrench space of a manipulated object or tool 2 , to represent the principal directions of the forces/torques exerted on an object to achieve a manipulation task. Finally, in many Learning from Demonstration (LfD) (Argall et al, 2009;Billard et al, 2008) approaches, Gaussian Mixture Models (GMM) and Hidden Markov Models (HMM), are regularly used for motion modeling, action recognition and segmentation (Calinon et al, 2007;Khansari-Zadeh and Billard, 2011;Calinon, 2015).…”

Section: Introductionmentioning

confidence: 99%

Transform-Invariant Non-Parametric Clustering of Covariance Matrices and its Application to Unsupervised Joint Segmentation and Action Discovery

Figueroa,

Billard

2017

Preprint

Self Cite

View full text Add to dashboard Cite

In this work, we tackle the problem of transform-invariant unsupervised learning in the space of Covariance matrices and applications thereof. We begin by introducing the Spectral Polytope Covariance Matrix (SPCM) Similarity function; a similarity function for Covariance matrices, invariant to any type of transformation. We then derive the SPCM-CRP mixture model, a transform-invariant non-parametric clustering approach for Covariance matrices that leverages the proposed similarity function, spectral embedding and the distance-dependent Chinese Restaurant Process (dd-CRP) (Blei and Frazier, 2011). The scalability and applicability of these two contributions is extensively validated on real-world Covariance matrix datasets from diverse research fields. Finally, we couple the SPCM-CRP mixture model with the Bayesian non-parametric Indian Buffet Process (IBP) -Hidden Markov Model (HMM) , to jointly segment and discover transform-invariant action primitives from complex sequential data. Resulting in a topicmodeling inspired hierarchical model for unsupervised time-series data analysis which we call ICSC-HMM (IBP Coupled SPCM-CRP Hidden Markov Model). The ICSC-HMM is validated on kinesthetic demonstrations of uni-manual and bi-manual cooking tasks; achieving unsupervised human-level decomposition of complex sequential tasks.

show abstract

On computing task-oriented grasps

Cited by 9 publications

References 21 publications

Manipulation planning under changing external forces

Manipulation planning under changing external forces

Active Haptic Perception in Robots: A Review

Transform-Invariant Non-Parametric Clustering of Covariance Matrices and its Application to Unsupervised Joint Segmentation and Action Discovery

Contact Info

Product

Resources

About