Skip to main content

2018 | Buch

Robotic Grasping and Manipulation

First Robotic Grasping and Manipulation Challenge, RGMC 2016, Held in Conjunction with IROS 2016, Daejeon, South Korea, October 10–12, 2016, Revised Papers

insite
SUCHEN

Über dieses Buch

This book constitutes the refereed proceedings of the First Robotic Grasping and Manipulation Challenge, RGMC 2016, held at IROS 2016, Daejeon, South Korea, in October 2016.The 13 revised full papers presented were carefully reviewed and are describing the rules, results, competitor systems and future directions of the inaugural competition. The competition was designed to allow researchers focused on the application of robot systems to compare the performance of hand designs as well as autonomous grasping and manipulation solutions across a common set of tasks. The competition was comprised of three tracks that included hand-in-hand grasping, fully autonomous grasping, and simulation.

Inhaltsverzeichnis

Frontmatter
Robotic Grasping and Manipulation Competition: Task Pool
Abstract
A Robot Grasping and Manipulation Competition was held during IROS 2016. The competition provided a common set of robot tasks for researchers focused on the application of robot systems to compare the performance of hand designs as well as autonomous grasping and manipulation solutions. Tracks one and two of the competition were supported by tasks chosen from a predefined pool of tasks. This task pool was assembled by the authors based on the challenges faced in developing robot systems that have the flexibility to grasp and manipulate a wide range of object geometries. This paper provides an overview of the task pool as well as the selection of tasks to support the various stages of the competition.
Yu Sun, Joe Falco, Nadia Cheng, Hyouk Ryeol Choi, Erik D. Engeberg, Nancy Pollard, Maximo Roa, Zeyang Xia
Advanced Grasping with the Pisa/IIT SoftHand
Abstract
This chapter presents the hardware, software and overall strategy used by the team UNIPI-IIT-QB to participate to the Robotic Grasping and Manipulation Competition. It relies on the PISA/IIT SoftHand, which is underactuated soft robotic hand that can adapt to the grasped object shape and is compliant with the environment. It was used for the hand-in-hand and for the simulation tracks, where the team reached first and third places respectively.
Manuel Bonilla, Cosimo Della Santina, Alessio Rocchi, Emanuele Luberto, Gaspare Santaera, Edoardo Farnioli, Cristina Piazza, Fabio Bonomo, Alberto Brando, Alessandro Raugi, Manuel G. Catalano, Matteo Bianchi, Manolo Garabini, Giorgio Grioli, Antonio Bicchi
Design of Modular Humanoid Robotic Hand Driven by SMA Actuator
Abstract
With excellent properties of light weight, low energy consumption and high power weight ratio, shape memory alloy (SMA) actuator has been widely applied in robotic hand nowadays. A novel modular humanoid robotic hand driven by SMA actuator is proposed and fabricated by 3D printer in this paper. An innovation displacement amplification pulley is designed to increase the output displacement of SMA actuator. The novel permanent magnet restoring structure can generate larger output force than that in conventional spring restoring structure in grasping process. In addition, modular design of hand makes it easy to assemble and disassemble, and the motion of hand is underactuated grasping form which simplifies the control system. The grasping tests of different shape and dimension of objects show that the hand has well working performance. The grasping diameter of object is less than 120 mm, and the maximum grasping weight is 500 g.
Yang Chen, Shaofei Guo, Hui Yang, Lina Hao
The TU Hand: Using Compliant Connections to Modulate Grasping Behavior
Abstract
Guided by the notion that the five-fingered anthropomorphic hand is a good general purpose manipulator, Team Tulsa approached the hand-in-hand portion of the grasping and manipulation competition using a simplified anthropomorphic hand. The hand had a simplified thumb, fixed in the opposed position, and only two actuators. Motions of the fingers and thumb were coupled together using a “ties and skips” architecture where thumb and finger tendons were tied to specific coils of a “mainspring” in a manner that produced the best behavior across the wide range of challenges. The actuators could move or deform the spring in common mode, which resulted in an enveloping grasp) or differential mode (which resulted in a pinch grasp) and superimpose the two modes. The compliant nature of the hand allowed the fingers to conform to the object as the grasp was acquired. This strategy allowed the retrieval of all objects from the basket (all on the first or second attempt by the volunteer), and scooping peas from the dish, but could not operate the hammer (due to its weight) the syringe, or the scissors (as they required increased dexterity).
Dipayan Das, Nathanael J. Rake, Joshua A. Schultz
Design and Application of Dorabot-hand2 System
Abstract
We present Dorabot-hand2, a dexterous robot hand and its design principles. The goal of designing this hand is to gain capability of handling everyday tasks. The hand is tendon-driven and is based on modular design. We focus on certain aspects of the design, including strength, friction, cost and maintainability. We conclude with a description of the hand’s performance when competing in the Robotic Grasping and Manipulation Competition at IROS 2016.
Zhikang Wang, Shuo Liu, Hao Zhang
Manipulation Using the “Utah” Prosthetic Hand: The Role of Stiffness in Manipulation
Abstract
We describe our approach to the IROS “Hand-in-Hand” manipulation challenge using a simple one degree-of-freedom prehensor, which is known to be highly effective in prosthetic applications. The claw consists of two prongs of which only one is mobile, requiring the user to first make contact with the immobile prong to create a constraint and then use the second prong to exert force on the object. Despite its simplicity, this design is able to grasp a wide variety of objects and reliably manipulate them. In particular, stiffness is advantageous both when manipulating very small objects, where force needs to be applied precisely, as well as heavy ones, where forces needs to be exerted without deforming the claw itself. This approach reaches its limitations during tasks that require more degrees of freedom, for example grasping and subsequently actuating scissors. These tasks instead highlight the benefits of compliance and underactuation, stimulating a discussion about trade-offs in hand designs.
Radhen Patel, Jacob Segil, Nikolaus Correll
SKKU Hand Arm System: Hardware and Control Scheme
Abstract
In this work, we introduce the SKKU Hand Arm System I (SKKU-HAS-I) focusing on the hardware design and control scheme of the arm and hand systems. For the robot arm system, a driving module unit is designed and the workspace analysis is performed for the arm. A Virtual Spring Damper based controller is applied to the arm system for the task of the control. The design of the robot hand is based on mimicking the human hand and we perform an optimization process for three different design measures, workspace intersection volumes, manipulability, and opposing angles. The developed robot hand is equipped with various sensors for the contact information. Experimental results are provided for the evaluation of the developed robot hand.
Dongmin Choi, Byung-jin Jung, Hyungpil Moon
A Robotic System for Autonomous Grasping and Manipulation
Abstract
A robotic system that consists of only a gripper can be utilized for certain applications such as supporting disabled people. However, with a robot manipulator introduced into the system, it can achieve far more tasks such as automation of manufacturing and logistics processes. The autonomous track of the IROS2016 Robotic Grasping and Manipulation Competition was designed to bring a robotic system into ordinary everyday tasks involving grasping and manipulation. The main objective of this paper is the evaluation of the autonomous robotic system by comparing the performance against manual human-interacted system in terms of intelligence and robustness.
We used UR5, Dora-Hand2 and Realsense SR300 to build an autonomous system for grasping and manipulation. The system has been evaluated by performing ten manipulation tasks and a pick-and-place task. The overall performance was below the manual system. However, for the tasks that involved repetitive motion, the automated system out-performed the manual system.
Mingu Kwon, Dandan Zhou, Shuo Liu, Hao Zhang
Improving Grasp Performance Using In-Hand Proximity and Contact Sensing
Abstract
We describe the grasping and manipulation strategy that we employed at the autonomous track of the Robotic Grasping and Manipulation Competition at IROS 2016. A salient feature of our architecture is the tight coupling between visual (Asus Xtion) and tactile perception (Robotic Materials), to reduce the uncertainty in sensing and actuation. We demonstrate the importance of tactile sensing and reactive control during the final stages of grasping using a Kinova Robotic arm. The set of tools and algorithms for object grasping presented here have been integrated into the open-source Robot Operating System (ROS). We have focused exclusively on the manipulation aspect (Track 1) of the competition as the bin-picking task (Track 2) would require a different perception strategy, focusing more on object identification.
Radhen Patel, Rebeca Curtis, Branden Romero, Nikolaus Correll
Robotic Grasping and Manipulation Competition @IROS2016: Team Tsinghua
Abstract
This chapter describes the preparation and implementation of the Robotic Grasping and Manipulation Competition @IROS 2016. Our Tsinghua Team participated in both the hand-in-hand and fully-autonomous tracks. The structure of a novel designed gripper and an algorithm for object detection and grasp pose estimation are described. The competition results demonstrates the effectiveness of the strategies used in the competition.
Fuchun Sun, Huaping Liu, Bin Fang, Di Guo, Tao Kong, Chao Yang, Yao Huang, Mingxuan Jing, Junyi Che
Complete Robotic Systems for the IROS Grasping and Manipulation Challenge
Abstract
Advances in perception, motion planning and grasping algorithms have enabled the movement from pick-and-place robots incapable of handling disturbances in the environment to intelligent robots with manipulation algorithms capable of dealing with novel surroundings. While the tasks outlined by the IROS Grasping and Manipulation Challenge included many challenging tasks (some of which surpassed current progress in robotic manipulation), assumptions about the competition environment were allowed. With these assumptions, we present our vision on two full robotic system pipelines behind the autonomous basket picking and task completion components of the IROS Grasping and Manipulation Competition.
Eadom Dessalene, Daniel Lofaro
Robotic Grasping and Manipulation Competition: Competitor Feedback and Lessons Learned
Abstract
The First Robot Grasping and Manipulation Competition, held during IROS 2016, allowed researchers focused on the application of robot systems to compare the performance of hand designs as well as autonomous grasping and manipulation solutions across a common set of tasks. The competition was comprised of three tracks that included hand-in-hand grasping, fully autonomous grasping, and simulation. The hand-in-hand and fully autonomous tracks used 18 predefined manipulation tasks and 20 objects. Additionally, a bin picking operation was also performed within the hand-in-hand and fully autonomous tracks using a shopping basket and a subset of the objects. The simulation track included two parts. The first was a pick and place operation, where a simulated hand extracted as many objects as possible from a cluttered shelf and placed them randomly in a bin. The second part was a bin picking operation where a simulated robotic hand lifted as many balls as possible from a bin and deposited them into a second bin. This paper presents competitor feedback as well as an analysis of lessons learned towards improvements and advancements for the next competition at IROS 2017.
Joe Falco, Yu Sun, Maximo Roa
Robotic Grasping and Manipulation Competition: Future Tasks to Support the Development of Assembly Robotics
Abstract
The Robot Grasping and Manipulation Competition, held during the 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) in Daejeon, South Korea was sponsored by the IEEE Robotic and Automation Society (RAS) Technical Committee (TC) on Robotic Hands Grasping and Manipulation (RHGM) [1]. This competition was the first of a planned series of grasping and manipulation-themed events of increasing difficulty that are intended to spur technological developments and advance test methods and benchmarks so that they can be formalized for use by the community. The coupling of standardized performance testing with robot competitions will promote the use of unbiased evaluation methods to assess how well a robot system performs in a particular application space. A strategy is presented for a series of grasping and manipulation competitions that facilitate objective performance benchmarking of robotic assembly solutions. This strategy is based on test methods that can be used for more rigorous assessments and comparison of systems and components outside of the competition regime. While competitions have proven to be useful mechanisms for assessing the relative performance of robotic systems with measures of success, they often lack a methodical measurement science foundation. Consequently, scientifically sound and statistically significant metrics, measurement, and evaluation methods to quantify performance are missing. Using performance measurement methods in a condensed format will accommodate competition time limits while introducing the methods to the community as tools for benchmarking performance in the developmental and deployment phases of a robot system. The particular evaluation methods presented here are focused on the mechanical assembly process, an application space that is expected to accelerate with the new robot technologies coming to market.
Karl Van Wyk, Joe Falco, Elena Messina
Backmatter
Metadaten
Titel
Robotic Grasping and Manipulation
herausgegeben von
Prof. Yu Sun
Joe Falco
Copyright-Jahr
2018
Electronic ISBN
978-3-319-94568-2
Print ISBN
978-3-319-94567-5
DOI
https://doi.org/10.1007/978-3-319-94568-2