Super Robust Robot Hand Канада


Video: Super-Robust German Robot Hand

We’re one step closer to the Robocalypse: a team of researchers at German Aerospace Center (DLR) has developed a robot arm that can absorb violent shocks like a champion. Hitting it with a bat (66G impact) or trying to damage the finger tips with a hammer, for example? No problem.

The hand has five fingers that can be moved independently from each other through a web of 38 wires made of a synthetic fiber called Dyneema and motors on the forearm.

The hand has 19 joints and can exert a force of 30 newtons. It’s designed in a way that it can even snap its fingers. The makers say it could cost up to $137,000 to produce one hand-arm unit.

Watch it in action in the video below:

Super Robust Robot Hand

Автор: IEEE Spectrum

Длительность: 55 сек

Битрейт: 192 Kbps

Похожие песни

I Love You Mommy

Yandirdin Kalbimi Aman Mp3 Skachat

Modern Talking Popurri

Dj Nikolaevv Клубный Транс

Хит Музыка Кавказа Девушка Моей Мечты Devran Ft Chanan

Бабушка Заступилась Чалтырь Ленинаван Крым

Вайнран И Алиса Бро

2 Nokia 1280 Ringtones Nokia 1280 Рингтоны

Раз Проехал На Такси Месяц Х Соси

Как Открыть Passat B6 Без Аккумулятора

Классный Клип Про Брата И Сестру

Rabba Ishq Na Hove Andaaz Songs Akshay Kumar Priyanka Chopra Lara Dutta Love Gold Songs

Я Люблю Эту Она Ужасно Взрослая

Сергеич Из Comedy Club Он Же Кутергин Сергей Порвал Всех На Рассмеши Комика

Begzod Haqqiyev Qizlarim Бегзод Хаккиев Кизларим

Патч Интерфейса Для Lineage 2 Interlude Бесплатная Версия Neophron 2020

Super Robust Robot Hand

Название: Super Robust Robot Hand

Загрузил: IEEE Spectrum

Длительность: 55 сек

Битрейт: 192 Kbps

1.21 MB и длительностью 55 сек в формате mp3.

Robotics Soft Tissue Injury Study

How To Build A Moral Robot

High Speed Robot Hand

A Robot That Balances On A Ball

Robot Arm Smashed With Baseball Bat


Robot Lightsaber Duel

10 Advanced Exoskeletons And Their Uses

Marble Conveyor Belt Completed Marble Machine X 78

Dean Kamen S Robotic Luke Arm

Robot Keeps Balance When Kicked Hit

Autonomous Robot With Neurologically Based Control System

Robot Suit Hal Demo At Ces 2011

Maybe The Best Robot Demo Ever Marco Tempest

Incredible Road Technologies That Are Really Insane

Animatronic Hand Robot 3D Printer Inmoov Part4

How Robonaut 2 S Dexterous Hands Work

Titan The Robot Leeds 19 01 16 Arriva Max 229

Female Android Geminoid F

Autom Weight Loss Coach Robot

Abb Concept Robot Frida

Which One Is Faster Laikago By Unitree Robotics Meeting Spotmini From Boston Dynamics

Nao Robot Does Star Wars

Vstone Robovie R3 Robot

Nasa S R2 Golden Bionic Robot Hand Darpa S 2015 Tech Expo

5 Fastest Robots In The World

Japan S Robot Revolution Bbc Click

Dlr Crawler Robot Meets Justin And Hand Arm System

Self Healing Robot Recovers From Damage

Advanced Musculoskeletal Humanoid Robot Kojiro

Aldebaran S New Nao Robot Demo

Hrp 4 Humanoid Platform For Robotics

7 Craziest Robot Animals You Never Knew Existed

Arduino Robot Hand For Under 300 Complete

The Robot Revolution The New Age Of Manufacturing Moving Upstream

Monkey Controls Advanced Robot With Its Mind

Little Rolling Robot Transforms Into Helicopter

Asterisk Omni Directional Insect Robot Picks Up Prey Diginfo

7 Real Life Transformer Cars That Actually Exist 2020

Sand Flea Jumping Robot

Windoro Window Cleaning Robot Demo

Makey Makey Roy The Robot S Hand


9 Advanced Robots From Boston Dynamics Will Change The Jobs Of Humans Boston Dynamics Robot

High Speed Robotic Hands

Irobot S Soft Morphing Blob Bot Takes Its First Steps

Ball Swapping With Manipulation Manifolds

Roboscallop A Bivalve Inspired Swimming Robot

Animatronic Robotic Hand Limited Edition

Namm 17 Wren And Cuff The White Elk Eye See Pi And Gold Comp Bass Demos

Weldon Irvine What Are You Doing For The Rest Of Your Life

Super Robust Robot Hand

Trangia Vs Triad

Hamayun Sakhi Rabab Naghma Sumra Khkuli Mahboba Ye In Slow Motion Tips For Learners

New York Then And Now

Ford Rs200 Evolution Detail

Х Фактор 3 Юлия Плаксина Crazy 2 Прямой Эфир 3 11 2012

Rajbongshi Song Mor Jibon Nosto Rajbongshi Video

Fifa 14 130K Beastly Brasilver Squad Builder

Blue Holler Bounty Hill Racing Rock Rods Ep74

Exactly How The Instagram Algorithm Works In 2020 Must Know To Gain Followers

Rubab Performance At Saidu Medical College Day 2

Libra November December You Ve Waited Your Entire Life For This General Love Tarot

Silent Assassin Hitman 2 Sniper Assassin 2020 Stealth Gameplay

Kentoptronics Lcd Switchable Transparent Mirror

Lumino Husliin Shunu Lyrics

Road Trip From Newcastle Co Dublin To Clane Co Kildare

03 The Saturdays Interview T4 Takeover 10 30Am 28Th June 2009

Irish Trash Can Cocktail

Mmxfnaf Прощенное Воскресенье Спринграп

To His Coy Mistress By Andrew Marvell Analysis

Part4 Cara Membangkitkan Kundalini Dengan Mengoptimalkan Jalur Sushumna

New Grip Update V 1 2 4 New Racetrack Gameplay In Haze Using Rogue

Crackshot Doing Crackdown Crackshot Emote

How To Get Instafamous 10 Tips To Grow Your Instagram

Chakk 356 Near Dunyapur Multan To Pathralian Hoshiarpur 177 Partition Of Punjab By Sanwal Dhami

Riva Quenery Kahit Ayaw Mo Na Net25 Letters And Music

Updesh Rana Reaction Video Imran Khan Aa Ja Ab Veer Kay Hath D D

Taarak Mehta Ka Ooltah Chashmah Ep 2863 Full Episode 15Th November 2020


Khloe Kardashian Fights Back After Amber Rose Rips Tyga And Kylie Jenner S Relationship

Driving Guide To The Alps How To Put On Snow Chains

Lil Flip Sunshine Instrumental

Svadba Mako Ramona 5 Part Carlos King 01 10 2020 Hamburg Studio Roma Fullhd Leskovac

Every Road Leads Back Bette Midler Johnny Carson

Nden Son Te 1 2 Version Malinke

Star Wars Plush Episode Viii

Grilled Sea Scallops And Foie Gras From Chef Thierry Rautureau

Nade Ali As Parhana Jaiz Ha Islam Mn By Muhammad Ali Mirza Engineer

Wwe 2020 Bobby Lashley New Wwe Contract Unveiled Huge Backstage News Wwe Rumors

Beamng Drive Ep 5 Altitude Speed Run Big Air Vanster

Senior Variete1 Radu Ratoi Moldovia

The Lion King Discover The Costumes

Naif Road Video Deira Dubai United Arab Emirates

Flashing And Trust Trading W Wolffeycat 1Ikeaboss And Ladollclic

Best Characters To Limit Break Rainbow One Piece Treasure Cruise

Последний День На Земле Last Day On Earth Survival

Super Robust Robot Hand

Название: Super Robust Robot Hand

Загрузил: IEEE Spectrum

Длительность: 55 сек

Битрейт: 192 Kbps

1.21 MB и длительностью 55 сек в формате mp3.

Robotics Soft Tissue Injury Study

How To Build A Moral Robot

High Speed Robot Hand

A Robot That Balances On A Ball

Robot Arm Smashed With Baseball Bat

Robot Lightsaber Duel

10 Advanced Exoskeletons And Their Uses

Marble Conveyor Belt Completed Marble Machine X 78

Dean Kamen S Robotic Luke Arm

Robot Keeps Balance When Kicked Hit

Autonomous Robot With Neurologically Based Control System

Robot Suit Hal Demo At Ces 2011

Maybe The Best Robot Demo Ever Marco Tempest


Incredible Road Technologies That Are Really Insane

Animatronic Hand Robot 3D Printer Inmoov Part4

How Robonaut 2 S Dexterous Hands Work

Titan The Robot Leeds 19 01 16 Arriva Max 229

Female Android Geminoid F

Autom Weight Loss Coach Robot

Abb Concept Robot Frida

Which One Is Faster Laikago By Unitree Robotics Meeting Spotmini From Boston Dynamics

Nao Robot Does Star Wars

Vstone Robovie R3 Robot

Nasa S R2 Golden Bionic Robot Hand Darpa S 2015 Tech Expo

5 Fastest Robots In The World

Japan S Robot Revolution Bbc Click

Dlr Crawler Robot Meets Justin And Hand Arm System

Self Healing Robot Recovers From Damage

Advanced Musculoskeletal Humanoid Robot Kojiro

Aldebaran S New Nao Robot Demo

Hrp 4 Humanoid Platform For Robotics

7 Craziest Robot Animals You Never Knew Existed

Arduino Robot Hand For Under 300 Complete

The Robot Revolution The New Age Of Manufacturing Moving Upstream

Monkey Controls Advanced Robot With Its Mind

Little Rolling Robot Transforms Into Helicopter

Asterisk Omni Directional Insect Robot Picks Up Prey Diginfo

7 Real Life Transformer Cars That Actually Exist 2020

Sand Flea Jumping Robot

Windoro Window Cleaning Robot Demo

Makey Makey Roy The Robot S Hand

9 Advanced Robots From Boston Dynamics Will Change The Jobs Of Humans Boston Dynamics Robot

High Speed Robotic Hands

Irobot S Soft Morphing Blob Bot Takes Its First Steps

Ball Swapping With Manipulation Manifolds

Roboscallop A Bivalve Inspired Swimming Robot

Animatronic Robotic Hand Limited Edition

Namm 17 Wren And Cuff The White Elk Eye See Pi And Gold Comp Bass Demos

Weldon Irvine What Are You Doing For The Rest Of Your Life


Super Robust Robot Hand

Trangia Vs Triad

Hamayun Sakhi Rabab Naghma Sumra Khkuli Mahboba Ye In Slow Motion Tips For Learners

New York Then And Now

Ford Rs200 Evolution Detail

Х Фактор 3 Юлия Плаксина Crazy 2 Прямой Эфир 3 11 2012

Rajbongshi Song Mor Jibon Nosto Rajbongshi Video

Fifa 14 130K Beastly Brasilver Squad Builder

Blue Holler Bounty Hill Racing Rock Rods Ep74

Exactly How The Instagram Algorithm Works In 2020 Must Know To Gain Followers

Rubab Performance At Saidu Medical College Day 2

Libra November December You Ve Waited Your Entire Life For This General Love Tarot

Silent Assassin Hitman 2 Sniper Assassin 2020 Stealth Gameplay

Kentoptronics Lcd Switchable Transparent Mirror

Lumino Husliin Shunu Lyrics

Road Trip From Newcastle Co Dublin To Clane Co Kildare

03 The Saturdays Interview T4 Takeover 10 30Am 28Th June 2009

Irish Trash Can Cocktail

Mmxfnaf Прощенное Воскресенье Спринграп

To His Coy Mistress By Andrew Marvell Analysis

Part4 Cara Membangkitkan Kundalini Dengan Mengoptimalkan Jalur Sushumna

New Grip Update V 1 2 4 New Racetrack Gameplay In Haze Using Rogue

Crackshot Doing Crackdown Crackshot Emote

How To Get Instafamous 10 Tips To Grow Your Instagram

Chakk 356 Near Dunyapur Multan To Pathralian Hoshiarpur 177 Partition Of Punjab By Sanwal Dhami

Очень важная для вас статья:  международные права Канада

Riva Quenery Kahit Ayaw Mo Na Net25 Letters And Music

Updesh Rana Reaction Video Imran Khan Aa Ja Ab Veer Kay Hath D D

Taarak Mehta Ka Ooltah Chashmah Ep 2863 Full Episode 15Th November 2020

Khloe Kardashian Fights Back After Amber Rose Rips Tyga And Kylie Jenner S Relationship

Driving Guide To The Alps How To Put On Snow Chains

Lil Flip Sunshine Instrumental

Svadba Mako Ramona 5 Part Carlos King 01 10 2020 Hamburg Studio Roma Fullhd Leskovac

Every Road Leads Back Bette Midler Johnny Carson

Nden Son Te 1 2 Version Malinke

Star Wars Plush Episode Viii

Grilled Sea Scallops And Foie Gras From Chef Thierry Rautureau


Nade Ali As Parhana Jaiz Ha Islam Mn By Muhammad Ali Mirza Engineer

Wwe 2020 Bobby Lashley New Wwe Contract Unveiled Huge Backstage News Wwe Rumors

Beamng Drive Ep 5 Altitude Speed Run Big Air Vanster

Senior Variete1 Radu Ratoi Moldovia

The Lion King Discover The Costumes

Naif Road Video Deira Dubai United Arab Emirates

Flashing And Trust Trading W Wolffeycat 1Ikeaboss And Ladollclic

Best Characters To Limit Break Rainbow One Piece Treasure Cruise

Последний День На Земле Last Day On Earth Survival

Super Robust Robot Hand

Автор: IEEE Spectrum

Длительность: 55 сек

Битрейт: 192 Kbps

Похожие песни

Абдуллох Домла Мусулмон Ким

Анекдот Про Валеру

Забери Меня К Себе На Небеса

I Love You Mommy

Yandirdin Kalbimi Aman Mp3 Skachat

Modern Talking Popurri

Dj Nikolaevv Клубный Транс

Хит Музыка Кавказа Девушка Моей Мечты Devran Ft Chanan

Бабушка Заступилась Чалтырь Ленинаван Крым

Вайнран И Алиса Бро

2 Nokia 1280 Ringtones Nokia 1280 Рингтоны

Раз Проехал На Такси Месяц Х Соси

Как Открыть Passat B6 Без Аккумулятора

Классный Клип Про Брата И Сестру

Rabba Ishq Na Hove Andaaz Songs Akshay Kumar Priyanka Chopra Lara Dutta Love Gold Songs

Я Люблю Эту Она Ужасно Взрослая

Сергеич Из Comedy Club Он Же Кутергин Сергей Порвал Всех На Рассмеши Комика

Begzod Haqqiyev Qizlarim Бегзод Хаккиев Кизларим

Патч Интерфейса Для Lineage 2 Interlude Бесплатная Версия Neophron 2020

German Researchers Build Terminator Robot Hand

Share

German Researchers Build Terminator Robot Hand


Warning: Do not watch this video if you lay awake at night, kept from sleep by the terrifying knowledge that one day soon the human race will be thrown into slavery by The Machines. For the more naïve amongst us, here’s the clip:

Oh, I forgot to say that if you don’t like to see a finger being locked in a vice and then whacked with a metal bar, you probably shouldn’t watch, either. Sorry.

The robot hand you see is German made, by researchers at the Institute of Robotics and Mechatronics. In building the first part of the Terminator, the researchers were going for robustness, and they appear to have achieved quite chilling success.

Not that utility has been traded for toughness: As the video shows, the hand is capable of an astonishing range of movement. The fingers are controlled by 38 tendons, each of which is driven by its own motor inside the forearm. Two tendons serve each joint. When their motors turn the same way, the joint moves. When they turn in opposite directions, the joint stiffens. This lets it toughen up to catch balls, yet be loose enough to perform delicate operations.

During tests, the researchers went all Joe Pesci on their robot creation, and took a baseball bat to the arm – a 66G whack. The result? Nothing. The hand came away unscathed.

Not only can the hand take punishment, it can also deal it out, exerting up to 30 Newtons of pressure with its fingers, plenty for either a stimulating massage or a deadly choking grip. It is also fast. The joints can spin at 500-degrees per second. If it tenses the springs joined to the tendons first, and then releases that energy, the joints can reach a head-spinning 2,000-degrees per second, or 333 rpm. That’s fast enough for it to snap its fingers and summon a human slave to do its bidding.

It doesn’t stop there. The head of the hand team, Markus Grebenstein (don’t you just wish it was Grabenstein?), says that the plan is to build a torso with two arms. His excuse? According to an interview with IEEE Spectrum, Grebenstein says that «The problem is, you can’t learn without experimenting.»

Yes you can, Mr. Grebenstein. Just watch Terminator 2.

Robust proprioceptive grasping with a soft robot hand

  • Bianca S. Homberg
  • Robert K. Katzschmann
  • Mehmet R. Dogar
  • Daniela Rus

Abstract

This work presents a soft hand capable of robustly grasping and identifying objects based on internal state measurements along with a combined system which autonomously performs grasps. A highly compliant soft hand allows for intrinsic robustness to grasping uncertainties; the addition of internal sensing allows the configuration of the hand and object to be detected. The finger module includes resistive force sensors on the fingertips for contact detection and resistive bend sensors for measuring the curvature profile of the finger. The curvature sensors can be used to estimate the contact geometry and thus to distinguish between a set of grasped objects. With one data point from each finger, the object grasped by the hand can be identified. A clustering algorithm to find the correspondence for each grasped object is presented for both enveloping grasps and pinch grasps. A closed loop system uses a camera to detect approximate object locations. Compliance in the soft hand handles that uncertainty in addition to geometric uncertainty in the shape of the object.

Keywords

Bianca S. Homberg and Robert K. Katzschmann have contributed equally to this work.

1 Introduction

Soft and under-actuated robotic hands have a number of advantages over traditional hard hands (Dollar and Howe 2006 , 2010 ; Deimel and Brock 2013 , 2014 ; Ilievski et al. 2011 ; Stokes et al. 2014 ; Shepherd et al. 2013 ; Brown et al. 2010 ). The additional compliance confers a greater intrinsic robustness to uncertainty, both for manipulating a broad range of objects and for conforming during interactions with the static environment.

Traditionally, grasping with rigid robotic hands requires detailed knowledge of the object geometry and precise location information for the object. Complex algorithms calculate the precise locations where the hand will grasp an object. With soft hands, we can grasp with a simpler, more intuitive approach handling more uncertainty.

The soft robotic hand, mounted to the wrist of a Baxter robot, is picking up a sample object

In this paper we build on our previous work (Katzschmann et al. 2015 ; Marchese et al. 2015 ) and develop a soft robotic gripper called the DRL (Distributed Robotics Laboratory) Soft Hand (Fig. 1 ). The DRL soft hand is modular, allowing for the interchange of digits. Internal sensing from bend and force sensors prov >proprioceptive grasping capability and its robustness to object pose uncertainty during grasping.

In evaluating the proprioceptive grasping capability of this new hand, we build a model to relate the values coming from integrated bend sensors to the configuration of the soft hand. We then use this model for haptic identification of objects during grasping: The DRL soft hand is able to identify a set of representative objects of different shape, size and compliance by grasping them. We do this by building a relation between objects and the configurations the soft hand takes while grasping them. Then, given an unidentified object from our training set, the robot grasps it and uses proprioception to identify it. We also present an online identification algorithm where the hand learns new objects progressively as it encounters them by detecting measured sensor differences from grasps of known objects.

The intrinsic compliance of the DRL soft hand allows it to pick up objects that a rig >enveloping grasps, pinch grasps, s >top grasps.

A modular, proprioceptive soft hand that includes integrated bend and force sensors;

Evaluation of the proprioceptive grasping capabilities of the soft hand, which includes development of algorithms for the haptic identification of objects;

Evaluation of the hand’s robustness to object pose uncertainty during grasping, which includes an end-to-end solution to grasping that starts by visually recognizing the placement of the object, continues with planning an approach, and ends by successfully grasping the object by a Baxter robot;

Extensive set of grasping experiments that evaluates the hand with a wide variety of objects under various grasping modes.

In Sect. 2 , we start with a discussion of related work. In Sect. 3 , we present the DRL soft hand and describe the components and fabrication. In Sect. 4 , we discuss the high-level system and algorithms used to control the hand and >5 , we describe the experiments val >6 , we conclude with a discussion of future work.

2 Related work

We build on recent developments in the fabrication of soft or underactuated hands. An overview of soft robotics is presented in Rus and Tolley ( 2015 ), Laschi et al. ( 2020 ) and Polygerinos et al. ( 2020 ). Dollar and Howe ( 2006 , 2010 ) presented one of the earliest examples of underactuated and flexible grippers. Ilievski et al. ( 2011 ) created a pneumatic starfish-like gripper composed of silicone and PDMS membranes and demonstrated it grasping an egg. Deimel and Brock ( 2013 ) developed a pneumatically actuated three-fingered hand made of reinforced silicone that was mounted to a hard robot and capable of robust grasping. More recently, they have developed an anthropomorphic soft pneumatic hand capable of dexterous grasps (Deimel and Brock 2014 , 2020 ). Stokes et al. ( 2014 ) used a soft elastomer quadrupedal robot to grasp objects in a hard-soft hybr >2013 ). An alternative to positive pressure actuated soft grippers is the robotic gripper based on the jamming of granular material developed by Brown et al. ( 2010 ). The fast Pneu-net designs by Mosadegh et al. detailed in Mosadegh et al. ( 2014 ) and by Polygerinos et al. detailed in Polygerinos et al. ( 2013 ) is closely related to the single finger design used in this paper. The design and the lost-wax fabrication of the fingers of the DRL soft hand builds upon the soft gripper and arm structure proposed in Katzschmann et al. ( 2015 ), which demonstrates autonomous soft grasping of objects on a plane.

To the best of our knowledge, configuration estimates of soft robots so far have been acquired primarily through exteroceptive means, for example motion tracking systems (Marchese et al. 2014 ) or RGB cameras (Marchese et al. 2014 ). Various sensor types that can measure curvature and bending have been studied, but few have been integrated into a soft robot. Park et al. ( 2010 , 2012 ) have shown that an artificial skin made of multi-layered embedded microchannels filled up with liqu >1999 ) described a fiber optic curvature sensor, called Shape Tape, that could sense bend and twist. Weiß and Worn ( 2005 ) have reported on the working principle of resistive tactile sensor cells to sense applied loads. B >2006 ) described the use of electroactive polymeric sensors to sense bend angles and bend rates in protheses. Kusuda et al. ( 2007 ) developed a bending sensor for flexible micro structures like Pneumatic Balloon Actuators. Their sensor used the flu >2013 ) and Chossat et al. ( 2014 ). Chuah and Kim ( 2014 ) presented a new force sensor design approach that mapped the local sampling of pressure inside a composite polymeric footpad to forces in three axes.

Очень важная для вас статья:  Редкая флора и фауна Канады

Previous studies on haptic recognition of objects focus on hands with rig >1989 ; Caselli et al. 1994 ; Johnsson and Balkenius 2007 ; Takamuku et al. 2008 ; Navarro et al. 2012 ). Paolini et al. ( 2014 ) presented a method which used proprioception to >2007 ), Jain et al. ( 2013 ), Javdani et al. ( 2013 ) and Koval et al. ( 2013 ).

Liarokapis et al. ( 2015 ) presented a method to >2015 ) placed a liqu >2015 ) presented a free-hanging starfish-like gripper that is pneumatically actuated and has embedded strain sensors made of liqu >1999 ) and Zhao et al. ( 2020 ) presented a soft prosthetic hand that has integrated stretchable optical wavegu >2020 ) showed a custom sensor skin for a soft gripper that can model and twist convex-shaped objects.


A new capability to sense force/contact through the integration of a force sensor in each finger of the soft hand;

Force-controlled grasping experiments using the new force sensors;

Addition of a fourth finger for improved grasping capability;

All experiments previously presented were again conducted with the new hand using also the force sensors;

An algorithm that allows the hand to identify new objects as it encounters them;

New set of experiments to test this online object identification approach;

Incorporation of the DRL Soft Hand into an end-to-end autonomous grasping pipeline and extensive experiments to measure its grasping performance under object pose uncertainty.

Create wax core mold using 3d printed model ( a). For each finger create a wax core by pouring wax into the wax core mold. Create mold assembly for finger base ( c) using wax core, insert part ( f) and white l >c) Melt the wax core out of the rubber piece and remove the insert piece. Re-insert the rubber piece into the base mold. Glue the sensors onto the constraint layer ( d). Place the constraint layer on top of the rubber piece ( e). Pour a second layer of softer rubber into the mold. Remove the finger and plug the hole at the finger tip with solid tubing

3 Device

Internal state sensing capability

Force contact sensing

Constant curvature bending when not loaded

Partially constant curvature bending under loaded conditions

Highly compliant and soft in order to be inherently safer

A cutaway view of the finger, showing the internal air channels, sealed sections, and inserted sensors and constraint layer

The combined hand, which we refer to as the DRL soft hand, is modular. Fingers easily attach and detach via 3D-printed interface parts. We can combine fingers to create different configurations of soft hands with different numbers of fingers. The primary configuration discussed in this paper is a four-fingered hand, an improved version of the previous three-fingered design (Homberg et al. 2015 ). The added finger directly opposes the thumb of the hand, allowing for a better enveloping of the object and an increased payload capability due to the firmer grasp at the center and the additional contact force. The four-fingered design allows for additional grasping options when compared to the previous design, such as a two finger pinch on small objects.

3.1 Fabrication

Views of an individual finger and the entire composed hand

Figure 3 shows an image of the inside of the finished finger; the constraint layer and the sensors are visible.

The updated DRL finger is streamlined at 1.8 cm w >4 . The new version benefits from shaping of the internal air channels and eternal finger shape to avoid all sharp corners which can be places of stress on the rubber. While the old version of the finger often broke intermittently, sometimes after only light use, the new version of the finger lasts several months and many hundreds of grasps before succumbing to rubber fatigue.

3.2 Actuation

Each finger is connected via a tube attached along the arm to a pneumatic piston. The actuation system is described in Katzschmann et al. ( 2015 ); Marchese et al. ( 2015 ).

3.3 Sensing

There are two sensors in each finger: the Flexi-force force sensor at the tip of the finger and the Bendshort-2.0 flex sensor from iCubeX. Both sensors are resistive sensors: as the sensor is pressed or bent, the resistance of the sensor changes.

(1) Force sensor The force sensor has a range of 4.5N but has an op-amp circuit to lower the range and increase the sensitivity. In order to get accurate results, we place a small metal piece behind the active area of the sensor. This prevents the bending of the finger from affecting the resistance of the sensor so that any sensed measurement comes just from the contact of the finger with an object.

(2) Bend sensor The sensors embedded in each finger are resistive bend sensors. The resistance of a sensor changes as it is bent.

3.4 Resistive sensor characterization

Due to the construction of the sensor, the relative change in resistance increases as the curvature of the sensor increases. Thus, the sensor has better accuracy and resolution as its diameter decreases. The diameter we refer to is the diameter of a circle tangent to the bend sensor at every point, for some constant curvature bend of the sensor. This relation between diameter of the finger and sensor value is shown in Fig. 5 , where sensor values versus finger curvatures are plotted for the unloaded case.

The diameter of the finger versus the sensor values

4 Control

In this section we discuss the high level algorithms governing control for the finger and overall DRL soft hand. Implementation details are discussed in the next section.

4.1 Architecture

For the hand-specific control, there are three sets of components: the physical fingers, the electronics, and the control software. The fingers are actuated via pneumatic tubing. The pneumatic tubing is pressurized by a piston, and the piston is driven by a linear actuator. Motor controllers, one per linear actuator, set the position of the linear actuators, setting the volume of the air in each finger. Additionally, each finger has a bend and a force sensor. Each of the sensors are connected to filtering and buffering electronics and then measured using an Arduino board.

On the software side for the hand, there is a middle-level controller enabling us to command the hand using primitive actions such as “close the hand” or “open the hand”. This middle-level controller communicates with the low-level motor controllers via serial communication. It also receives sensor values from the Arduino board on the hand through rosserial. 1

On the robot s >2009 ). One main ROS node coordinates the overall behavior. One ROS node reads the camera input streams and performs object detection using basic image processing in OpenCV (Bradski 2000 ). One strength of the DRL soft hand is its ability to grasp unknown objects with uncertain pose estimation. This vision system serves to detect approximate poses of objects even if they are completely unknown to the robot. A suite of ROS nodes run for the MoveIt planner Sucan and Chitta 2020 . One object in the codebase interfaces with the MoveIt planner to coordinate calls to plan motions to different locations. For side grasps, the motion planning node finds a grasp plan given a potential object location using an intermediate way point. The planner considers 16 potential directions by which to approach the object. Along the direction, it first considers an offset pre-grasp location which is offset far enough to be simple to plan to without getting too close to the object. For top grasps, the motion planner is called to find a plan to a pose where the hand is vertically above the object. For top grasps of small objects, first the fingers are half closed to allow the hand to approach closer to the table without the fingers hitting the table and being unable to bend to grasp due to excessive friction. Another object handles the control of the soft hand, opening, closing, and grasping. A separate node sends specific commands via serial to the motor controllers.

4.2 Finger control


The value measured from the force sensor is an approximate force. Due to noise after the hardware low pass filter, we buffer the output in software and consider an average of the past five data samples. If the average of the data samples crosses a certain threshold, we consider this to be a contact between the fingertip and an external object.

4.3 Grasping

We incorporated the DRL soft hand into a complete, end-to-end grasping system. This grasping system demonstrates the versatility of the soft hand by showing its robustness to uncertainty in the location of the object and the minimal need for grasp planning.

4.4 Object >Once trained, the DRL soft hand is able to identify the grasped objects based on a single grasp. We first characterize the relation between hand configurations and sensor readings. Then, we present a data-driven approach to identify an object based on sensor readings.

(1) Modeling the sensor noise The DRL hand has different configurations as it interacts with the environment and grasps objects. We define a configuration of the DRL hand as a vector \(\mathbf = [ q_1, q_2, q_3, q_4]\) , where each \(q_i \in \mathbb \) represents the way finger i is bent. \(\mathbb \) is the configuration space of a finger: that is, the space of all different shapes our soft finger can achieve. For a given configuration of the hand, we get bend sensor readings \(\mathbf = [ s_1, s_2, s_3, s_4 ]\) , where each \(s_i\) represents the bend sensor reading for finger i and a force value \(\mathbf = [f_1, f_2, f_3, f_4]\) , where each \(f_i\) represents the force sensor reading for finger i.

Очень важная для вас статья:  Как оповещают о готовности визы Канада

Note that when the finger is loaded in a grasp, the resulting finger configurations and the corresponding sensor readings have significant variation due to the highly compliant nature of the fingers. Therefore, to identify objects during grasping, we use data collected under the grasp load.

(2) Object identification through grasping We use the sensors on the hand to predict the hand configuration, which we then use to identify the grasped object.

The grasping configuration for an object can be different for different types of grasps. In this work we focus on two types of grasps: enveloping grasps and pinch grasps. For a given object, o, we represent the configuration at the end of an enveloping grasp as \(\mathbf _o^\) ; and we represent the configuration at the end of a pinch grasp as \(\mathbf _o^\) .

4) Online Object Identification: In Algorithm 4, the robot identifies objects online as it grasps new and old objects. Initially, the hand is trained to identify the empty grasp as a baseline via ten grasps. This allows the robot to have a known starting point of what the sensor values are when it has not grasped an object. As the hand grasps objects, the algorithm decides as it grasps each object whether the object is a known object from the objects it has already learned or a new object it has not yet seen. If the object is identified as a known object, it adds the data from that grasp with the label of the identified object. If the object is identified as a new object, it creates a new label and adds the data from that grasp with the new label.

5 Experiments and results

The basic grasping capability of the soft hand (Sect. 5.1 ),

The proprioceptive capability of the hand applied to autonomous object >5.2 ),

The grasping performance of the soft hand under object pose uncertainty within an end-to-end system (Sect. 5.3 ).

5.1 Basic grasping capability

Objects grasped. a \(\sim \) 100 objects grasped by the DRL soft hand and b the six objects the DRL soft hand failed to pick up

Various objects grasped by the DRL soft hand. a Aquaphor, b lemonade bottle, c squash, d mug, e ring and f marker

Rig >a Cup squashed by rig >b gripper performs a compliant grasp to pick up a thin object off a table

During the experiments, each object was placed at a known pose and a grasp was attempted by the Baxter robot using the DRL soft hand. For this set of experiments, our goal was to focus on the grasping capability of the DRL soft hand, and therefore we took the liberty to implement different grasping strategies for different objects. (Section 5.3 presents our set of experiments where we evaluated the soft hand within an end-to-end system using autonomous perception and planning.) Some objects were grasped via enveloping grasps. Others were picked up via a top grasp with two or three fingers in a pinch grasp. The flat objects, e.g. the CD and the piece of paper, were grasped off of the table as was shown in Fig. 8 b. All objects were positioned in the orientations as they are in Fig. 6 . The DRL soft hand was able to successfully grasp and pick up 94 of 100 objects.

We made three key observations during these experiments.

First, the DRL soft hand was capable of grasping a w >6 were chosen to explore the extents of the grasping capability of the soft hand and it, thanks to its soft compliance, easily adapted to different shapes and sizes.

Second, the DRL soft hand was capable of grasping objects that require simultaneous compliant interaction with the environment. Specifically, we tested grasping a CD and a piece of paper off of a table, again using both the DRL soft hand and the default rig >8 b shows how the soft gripper smoothly interacts with the environment to pick up the CD.

Third, the DRL soft hand was qualitatively better at grasping a compliant object when compared with the rig >8 a), it crushed it; the soft gripper was able to pick it up repeatedly without crushing.

The DRL soft hand was not able to pick up six of the 100 objects. These objects can be seen in Fig. 6 b. The hand was not able to pick them up primarily because they were too heavy or too flat for the finger to gain any traction on them. The gripper had trouble picking up a spoon, a pair of scissors, and a propeller because they were not high enough – the fingers were unable to make a good connection. The gripper was unable to pick up an amorphous bag of small objects because of the combination of its odd shape and heaviness, the fingers did not get a solid grasp below the center of mass and the bag deformed to slip out of the fingers. The fish tail could be grasped, but slipped due to its weight. The screw was simply too small to be reliably grasped.

5.2 Proprioceptive grasping

The 4-finger data for a enveloping grasps and b pinch grasps. In both a and b, the first 3D plot uses the curvature values from the first three fingers and the second 2D plot uses the third and fourth fingers. There were ten grasps of each object. These grasps were labeled with true object >1 , with 100% accuracy for most of the objects (Color figure online)

Identification percentages for each of the tested objects. Dashes represent that an object was not used in a particular test due to it not being the right shape for grasping in that orientation

Super Robust Robot Hand Канада

Robot researchers led by Markus Grebenstein in Germany have taken a step towards making the T-800 a reality this week by creating a super strong robot hand. It even looks a little a lot like the T-800:

As the video above shows, this hand is very strong and one of the fingers can be hit with a hammer at speed and not get damaged. It has 38 tendons with a motor attached to each finger and is of similar size to a human hand. Dexterity is built-in and the hand has 19 degrees of freedom (one less than us) and a force of 30 newtons can be applied at the fingertips.

The hand was developed at the Institute of Robotoics and Mechatronics at the German Aerospace Center. The secret to its strength is a combination of a synthetic fiber called Dyneema and a spring attached to each tendon. That allows each finger to take a hard blow, but at the same time move to reduce the force while easily springing back to its original position.

The end result is a very strong hand with almost as much freedom of movement as a human hand. Movement speed at the joints can reach 2,000 degrees per second allowing the hand to snap its fingers.

Not only is it strong, but the use of springs on the joints allows the hand to monitor and adjust the force of its grasp based on the object being help. The lower the tension on the joints the softer the object must be and can therefore be grasped more lightly.

The main reason for the development of the hand was to improve the robustness of robotic hands in general. Grebenstein points out that even the most agile of robot hands can easily break with small amounts of pressue on them. This new design solves that problem without inhibiting movement or speed.

As for how much this hand cost to develop: it’s less than $135,000. Now the research team is turning its efforts to a two-armed torso. Thankfully, no one yet seems to be working on legs so this thing could only escape by dragging itself across the floor.

Робот-автостопщик HitchBOT завершил свое путешествие по Канаде

Забавный робот HitchBOT, о котором мы уже рассказывали на страницах нашего сайта, только что закончил свое путешествие, в ходе которого он пересек всю Канаду, передвигаясь исключительно методом автостопа. Это путешествие началось 27 июля этого года на конце трассы Trans-Canada Highway в городе Галифакс (Halifax) на побережье Атлантического океана. И, передвигаясь автостопом, робот HitchBOT проехал через всю Канаду с востока на запад, от Новой Шотландии до Британской Колумбии, преодолев в общей сложности расстояние в 6228 километров. Его путешествие закончилось в галерее Open Space Gallery города Виктория, близ Ванкувера, куда он прибыл в четверг прошедшей недели.

Напомним нашим читателям, что робот HitchBOT является детищем Фрока Зеллера (Frauke Zeller), профессора из университета Райерсона (Ryerson University) и Дэвида Смита (David Smith), профессора из университета Макмэстера (McMaster University). А целью данного социального эксперимента с путешествием автостопом являлся поиск ответа на вопрос — «Могут ли люди доверять роботам и может ли робот доверять людям настолько, чтобы сесть к ним в машину?».

Для того, чтобы привлечь внимание людей к роботу HitchBOT, его создатели постарались сделать его как можно более забавным и дружелюбным. Конструкция робота изготовлена из самых различных подручных материалов, среди которых ведро, прозрачная крышка, садовые шланги, резиновые сапоги, садовые перчатки и т.п. Единственной движущейся частью конструкции робота является его правая рука, которая способна совершать лишь одно характерное для автостопщиков движение.

Робот имеет достаточно серьезную информационную систему, снабженную технологиями распознавания и синтеза речи, при помощи которой он способен общаться с людьми на совершенно разные темы, используя данные, черпаемые из всемирной энциклопедии Wikipedia.

«Наш робот вернулся из путешествия изрядно потрепанным. Больше всего он сейчас напоминает доску объявлений, ведь почти все люди, которые его подвозили, не преминули оставить на нем свой автограф» — рассказывает Дэвид Смит.

«Но это еще не конец эпопеи нашего робота HitchBOT» — рассказывает Фрок Зеллер, — «В Канаде наш эксперимент удался полностью. Теперь мы ищем источники дополнительного финансирования, и если мы их найдем, то робот может опять появиться на обочине дороги, на этот раз в какой-нибудь другой стране».

Добавить комментарий