Towards Reliable Grasping and Manipulation in Household Environments

Ciocarlie, Matei; Hsiao, Kaijen; Jones, E. Gil; Chitta, Sachin; Rusu, Radu Bogdan; Sucan, Ioan A.

doi:10.1007/978-3-642-28572-1_17

Cited by 135 publications

(107 citation statements)

References 14 publications

Supporting

Mentioning

106

Contrasting

Order By: Relevance

“…Upon clicking this button, the robot automatically aligned to the table and began to look for objects. This consisted of facing the table, un-tucking its arms, driving right up to the table, raising its spine to get an overhead view of the table, and using 3D point cloud data from the Kinect to segment any objects found in the environment (Ciocarlie et al, 2010). Any objects that are found are rendered as a green, 3D model on the 3D visualizer of the interface.…”

Section: The Remote Interfacementioning

confidence: 99%

The Robot Management System: A Framework for Conducting Human-Robot Interaction Studies Through Crowdsourcing

Toris¹,

Kent²,

Chernova³

2014

Journal of Human-Robot Interaction

View full text Add to dashboard Cite

Human-Robot Interaction (HRI) is a rapidly expanding field of study that focuses on allowing nonroboticist users to naturally and effectively interact with robots. The importance of conducting extensive user studies has become a fundamental component of HRI research; however, due to the nature of robotics research, such studies often become expensive, time consuming, and limited to constrained demographics. In this work, we present the Robot Management System (RMS), a novel framework for bringing robotic experiments to the web. We present a detailed description of our open-source system and describe an initial trial of the RMS as a means of conducting user studies. Using a series of navigation and manipulation tasks with a PR2 robot, we compare three user study conditions: users that are co-present with the robot, users that are recruited to the university laboratory but control the robot from a different room, and remote web-based users. Our findings show little statistical differences between usability patterns across these groups, validating the use of web-based crowdsourcing techniques for certain types of HRI evaluations.

show abstract

Section: The Remote Interfacementioning

confidence: 99%

The Robot Management System: A Framework for Conducting Human-Robot Interaction Studies Through Crowdsourcing

Toris¹,

Kent²,

Chernova³

2014

Journal of Human-Robot Interaction

View full text Add to dashboard Cite

show abstract

“…(19) is set to m = 36, as shown in Fig. (6b) 4 . Using all the data from the test dataset as grasping points queries, we evaluate the accuracy of the model in terms of the Mean Absolute Error (MAE) in radians, as reported in Table. 5.…”

Section: Results For Hand Configuration Querymentioning

confidence: 99%

“…7 shows examples of predicted joint angles in comparison with the ground truth joint angles for four different testing cases, the MAE of these four examples are also reported in Table. 5. 4 The BIC gives a range of the number of Gaussians and the final number is determined by a 10-folds cross validation on a separate dataset. To keep the number of grasping points the same for the Allegro hand, we consider only its first three fingers as show in Fig.…”

Section: Results For Hand Configuration Querymentioning

confidence: 99%

“…To achieve this, a common approach is to address two subproblems: grasp planning and grasp execution. Considerable progress has been made during the last couple of years and efficient grasp planning algorithms have been proposed to generate grasps for known, partially known or unknown objects in structured or unstructured environments [1,2,3,4,5]. Robust and reactive grasp control techniques have been developed and validated on different robotic platforms relying on single or multiple sensory feedback.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dexterous grasping under shape uncertainty

Hang

Kragić

et al. 2016

Robotics and Autonomous Systems

View full text Add to dashboard Cite

An important challenge in robotics is to achieve robust performance in object grasping and manipulation, dealing with noise and uncertainty. This paper presents an approach for addressing the performance of dexterous grasping under shape uncertainty. In our approach, the uncertainty in object shape is parameterized and incorporated as a constraint into grasp planning. The proposed approach is used to plan feasible hand configurations for realizing planned contacts using different robotic hands. A compliant finger closing scheme is devised by exploiting both the object shape uncertainty and tactile sensing at fingertips. Experimental evaluation demonstrates that our method improves the performance of dexterous grasping under shape uncertainty.

show abstract

“…The control of their functions is performed by computer interface and, for developing rapport with environment, they use many sensors and many different applications such as: applications for grasping [1], positioning [2], moving objects, as well as for welding [3], painting, assembly [4] and transportation.…”

Section: Introductionmentioning

confidence: 99%

Low Cost Robotic Arm for Object Grasping Applications

Golomeova¹,

Koceski²

2017

IJCA

View full text Add to dashboard Cite

Initially, the emphasis of the robotic arm is placed on grasping and positioning objects in space. These types of robotic arms have a stake in planetary and underwater research, robotic surgery, systems for disabled people, households and so on. The strategy for grasping and positioning objects is based on recording environment with a web camera. Strategic decisions affect the orientation of the hand and the way of opening the gripper. At the same time, opening the gripper should match the shape and size of objects being used. The creation of a system based on this strategy, which then can be practically applied while being inexpensive and simple to implement, is the main goal of this paper.

show abstract

Towards Reliable Grasping and Manipulation in Household Environments

Cited by 135 publications

References 14 publications

The Robot Management System: A Framework for Conducting Human-Robot Interaction Studies Through Crowdsourcing

The Robot Management System: A Framework for Conducting Human-Robot Interaction Studies Through Crowdsourcing

Dexterous grasping under shape uncertainty

Low Cost Robotic Arm for Object Grasping Applications

Contact Info

Product

Resources

About