SlideShare a Scribd company logo
Learning to grasp without
human supervision
Motivation
• Current methods in grasp learning for previously unseen objects
involve the transfer of features and primitives from humans to
robots.
• These transferred knowledge includes memory of previous
grasps[], human labelled datasets[], pre-defined visual/depth
features[]
• But these previous methods are inherently biased towards a
human’s knowledge and intuition
• For truly autonomous manipulators, we need a framework that
allows the robot itself to learn the knowledge and understanding
for grasping
Our Approach
• We follow a learning by training approach where we have a dataset of images (and
depth point clouds) of objects along with positive and negative grasp points
• Since we need to eliminate the human in the loop, the robot itself should be able to
collect training data
• For this we have a robot execute random grasps on a wide variety of objects. The
robot recognizes successful grasps using its inbuilt gripper force sensors
Grasp Data collected
• Currently our robot is capable of executing about 80 random grasps
an hour per arm. Which on a typical day(running for about 8 hours)
yields about 80*8*2 = 1280 grasps a day.
• As of now, the robot has executed about 17,000 random grasps and
has around 1300 successful grasps. This is already larger than
Cornell Grasp Dataset that is hand labelled and doesn't contain
negative examples (failure grasps)
• Associated with each grasp we record data from 2 RGB image
cameras on the arm, 1 Depth camera (Creative Senz3D) and Kinect
V2 attached to the head of the robot. The recorded streams include
the entire motion of the arm in the grasp sequence
Grasp Data collected

More Related Content

Similar to Grasp slides pptx

What is Artificial intelligence
What is Artificial intelligenceWhat is Artificial intelligence
What is Artificial intelligence
sudarmani rajagopal
 
Unit 2 ai
Unit 2 aiUnit 2 ai
Unit 2 ai
Jeevan Chapagain
 
10833762.ppt
10833762.ppt10833762.ppt
10833762.ppt
shohel rana
 
SANG AI 1.pptx
SANG AI 1.pptxSANG AI 1.pptx
SANG AI 1.pptx
SanGeet25
 
Deep learning introduction
Deep learning introductionDeep learning introduction
Deep learning introduction
Adwait Bhave
 
AI CH 1d.pptx
AI CH 1d.pptxAI CH 1d.pptx
AI CH 1d.pptx
PriyankaJadhav218236
 
Machine-Learning-and-Robotics.pptx
Machine-Learning-and-Robotics.pptxMachine-Learning-and-Robotics.pptx
Machine-Learning-and-Robotics.pptx
shohel rana
 
Sixth sense technology ppt
Sixth sense technology pptSixth sense technology ppt
Sixth sense technology ppt
OECLIB Odisha Electronics Control Library
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
Bharath Palaksha
 
Introduction to Artificial Intelligence
Introduction to Artificial IntelligenceIntroduction to Artificial Intelligence
Introduction to Artificial Intelligence
ananth
 
Hci and psychology
Hci and psychologyHci and psychology
Hci and psychology
Dr. Shaukat Wasi
 
Mind reading
Mind readingMind reading
Mind reading
Shalu Jain
 
PLANNING & PERCEPTION.pptx
PLANNING & PERCEPTION.pptxPLANNING & PERCEPTION.pptx
PLANNING & PERCEPTION.pptx
Yash59268
 
Eye Tracking Based Human - Computer Interaction
Eye Tracking Based Human - Computer InteractionEye Tracking Based Human - Computer Interaction
Eye Tracking Based Human - Computer Interaction
Sharath Raj
 
Intelligent image processing
Intelligent image processingIntelligent image processing
Intelligent image processing
Andrew Stewart
 
Closing the gap between neuroscience and machine learning
Closing the gap between neuroscience and machine learningClosing the gap between neuroscience and machine learning
Closing the gap between neuroscience and machine learning
jtoy
 
Facial emotion detection on babies' emotional face using Deep Learning.
Facial emotion detection on babies' emotional face using Deep Learning.Facial emotion detection on babies' emotional face using Deep Learning.
Facial emotion detection on babies' emotional face using Deep Learning.
Takrim Ul Islam Laskar
 
Elderly Assistance- Deep Learning Theme detection
Elderly Assistance- Deep Learning Theme detectionElderly Assistance- Deep Learning Theme detection
Elderly Assistance- Deep Learning Theme detection
Tanvi Mittal
 
Introduction to Robotics
Introduction to RoboticsIntroduction to Robotics
Introduction to Robotics
UDITMODI5
 
Unit 1.ppt
Unit 1.pptUnit 1.ppt
Unit 1.ppt
GEETHAS668001
 

Similar to Grasp slides pptx (20)

What is Artificial intelligence
What is Artificial intelligenceWhat is Artificial intelligence
What is Artificial intelligence
 
Unit 2 ai
Unit 2 aiUnit 2 ai
Unit 2 ai
 
10833762.ppt
10833762.ppt10833762.ppt
10833762.ppt
 
SANG AI 1.pptx
SANG AI 1.pptxSANG AI 1.pptx
SANG AI 1.pptx
 
Deep learning introduction
Deep learning introductionDeep learning introduction
Deep learning introduction
 
AI CH 1d.pptx
AI CH 1d.pptxAI CH 1d.pptx
AI CH 1d.pptx
 
Machine-Learning-and-Robotics.pptx
Machine-Learning-and-Robotics.pptxMachine-Learning-and-Robotics.pptx
Machine-Learning-and-Robotics.pptx
 
Sixth sense technology ppt
Sixth sense technology pptSixth sense technology ppt
Sixth sense technology ppt
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
 
Introduction to Artificial Intelligence
Introduction to Artificial IntelligenceIntroduction to Artificial Intelligence
Introduction to Artificial Intelligence
 
Hci and psychology
Hci and psychologyHci and psychology
Hci and psychology
 
Mind reading
Mind readingMind reading
Mind reading
 
PLANNING & PERCEPTION.pptx
PLANNING & PERCEPTION.pptxPLANNING & PERCEPTION.pptx
PLANNING & PERCEPTION.pptx
 
Eye Tracking Based Human - Computer Interaction
Eye Tracking Based Human - Computer InteractionEye Tracking Based Human - Computer Interaction
Eye Tracking Based Human - Computer Interaction
 
Intelligent image processing
Intelligent image processingIntelligent image processing
Intelligent image processing
 
Closing the gap between neuroscience and machine learning
Closing the gap between neuroscience and machine learningClosing the gap between neuroscience and machine learning
Closing the gap between neuroscience and machine learning
 
Facial emotion detection on babies' emotional face using Deep Learning.
Facial emotion detection on babies' emotional face using Deep Learning.Facial emotion detection on babies' emotional face using Deep Learning.
Facial emotion detection on babies' emotional face using Deep Learning.
 
Elderly Assistance- Deep Learning Theme detection
Elderly Assistance- Deep Learning Theme detectionElderly Assistance- Deep Learning Theme detection
Elderly Assistance- Deep Learning Theme detection
 
Introduction to Robotics
Introduction to RoboticsIntroduction to Robotics
Introduction to Robotics
 
Unit 1.ppt
Unit 1.pptUnit 1.ppt
Unit 1.ppt
 

Recently uploaded

一比一原版(uob毕业证书)伯明翰大学毕业证如何办理
一比一原版(uob毕业证书)伯明翰大学毕业证如何办理一比一原版(uob毕业证书)伯明翰大学毕业证如何办理
一比一原版(uob毕业证书)伯明翰大学毕业证如何办理
9gr6pty
 
一比一原版(UofT毕业证)多伦多大学毕业证如何办理
一比一原版(UofT毕业证)多伦多大学毕业证如何办理一比一原版(UofT毕业证)多伦多大学毕业证如何办理
一比一原版(UofT毕业证)多伦多大学毕业证如何办理
exukyp
 
一比一原版爱尔兰都柏林大学毕业证(本硕)ucd学位证书如何办理
一比一原版爱尔兰都柏林大学毕业证(本硕)ucd学位证书如何办理一比一原版爱尔兰都柏林大学毕业证(本硕)ucd学位证书如何办理
一比一原版爱尔兰都柏林大学毕业证(本硕)ucd学位证书如何办理
hqfek
 
一比一原版南十字星大学毕业证(SCU毕业证书)学历如何办理
一比一原版南十字星大学毕业证(SCU毕业证书)学历如何办理一比一原版南十字星大学毕业证(SCU毕业证书)学历如何办理
一比一原版南十字星大学毕业证(SCU毕业证书)学历如何办理
slg6lamcq
 
一比一原版美国帕森斯设计学院毕业证(parsons毕业证书)如何办理
一比一原版美国帕森斯设计学院毕业证(parsons毕业证书)如何办理一比一原版美国帕森斯设计学院毕业证(parsons毕业证书)如何办理
一比一原版美国帕森斯设计学院毕业证(parsons毕业证书)如何办理
asyed10
 
一比一原版悉尼大学毕业证如何办理
一比一原版悉尼大学毕业证如何办理一比一原版悉尼大学毕业证如何办理
一比一原版悉尼大学毕业证如何办理
keesa2
 
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
mkkikqvo
 
一比一原版加拿大麦吉尔大学毕业证(mcgill毕业证书)如何办理
一比一原版加拿大麦吉尔大学毕业证(mcgill毕业证书)如何办理一比一原版加拿大麦吉尔大学毕业证(mcgill毕业证书)如何办理
一比一原版加拿大麦吉尔大学毕业证(mcgill毕业证书)如何办理
agdhot
 
Data Scientist Machine Learning Profiles .pdf
Data Scientist Machine Learning  Profiles .pdfData Scientist Machine Learning  Profiles .pdf
Data Scientist Machine Learning Profiles .pdf
Vineet
 
Discovering Digital Process Twins for What-if Analysis: a Process Mining Appr...
Discovering Digital Process Twins for What-if Analysis: a Process Mining Appr...Discovering Digital Process Twins for What-if Analysis: a Process Mining Appr...
Discovering Digital Process Twins for What-if Analysis: a Process Mining Appr...
Marlon Dumas
 
一比一原版英属哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
一比一原版英属哥伦比亚大学毕业证(UBC毕业证书)学历如何办理一比一原版英属哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
一比一原版英属哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
z6osjkqvd
 
一比一原版多伦多大学毕业证(UofT毕业证书)学历如何办理
一比一原版多伦多大学毕业证(UofT毕业证书)学历如何办理一比一原版多伦多大学毕业证(UofT毕业证书)学历如何办理
一比一原版多伦多大学毕业证(UofT毕业证书)学历如何办理
eoxhsaa
 
一比一原版加拿大渥太华大学毕业证(uottawa毕业证书)如何办理
一比一原版加拿大渥太华大学毕业证(uottawa毕业证书)如何办理一比一原版加拿大渥太华大学毕业证(uottawa毕业证书)如何办理
一比一原版加拿大渥太华大学毕业证(uottawa毕业证书)如何办理
uevausa
 
Econ3060_Screen Time and Success_ final_GroupProject.pdf
Econ3060_Screen Time and Success_ final_GroupProject.pdfEcon3060_Screen Time and Success_ final_GroupProject.pdf
Econ3060_Screen Time and Success_ final_GroupProject.pdf
blueshagoo1
 
ML-PPT-UNIT-2 Generative Classifiers Discriminative Classifiers
ML-PPT-UNIT-2 Generative Classifiers Discriminative ClassifiersML-PPT-UNIT-2 Generative Classifiers Discriminative Classifiers
ML-PPT-UNIT-2 Generative Classifiers Discriminative Classifiers
MastanaihnaiduYasam
 
一比一原版(Sheffield毕业证书)谢菲尔德大学毕业证如何办理
一比一原版(Sheffield毕业证书)谢菲尔德大学毕业证如何办理一比一原版(Sheffield毕业证书)谢菲尔德大学毕业证如何办理
一比一原版(Sheffield毕业证书)谢菲尔德大学毕业证如何办理
1tyxnjpia
 
Build applications with generative AI on Google Cloud
Build applications with generative AI on Google CloudBuild applications with generative AI on Google Cloud
Build applications with generative AI on Google Cloud
Márton Kodok
 
Cell The Unit of Life for NEET Multiple Choice Questions.docx
Cell The Unit of Life for NEET Multiple Choice Questions.docxCell The Unit of Life for NEET Multiple Choice Questions.docx
Cell The Unit of Life for NEET Multiple Choice Questions.docx
vasanthatpuram
 
How To Control IO Usage using Resource Manager
How To Control IO Usage using Resource ManagerHow To Control IO Usage using Resource Manager
How To Control IO Usage using Resource Manager
Alireza Kamrani
 
一比一原版斯威本理工大学毕业证(swinburne毕业证)如何办理
一比一原版斯威本理工大学毕业证(swinburne毕业证)如何办理一比一原版斯威本理工大学毕业证(swinburne毕业证)如何办理
一比一原版斯威本理工大学毕业证(swinburne毕业证)如何办理
actyx
 

Recently uploaded (20)

一比一原版(uob毕业证书)伯明翰大学毕业证如何办理
一比一原版(uob毕业证书)伯明翰大学毕业证如何办理一比一原版(uob毕业证书)伯明翰大学毕业证如何办理
一比一原版(uob毕业证书)伯明翰大学毕业证如何办理
 
一比一原版(UofT毕业证)多伦多大学毕业证如何办理
一比一原版(UofT毕业证)多伦多大学毕业证如何办理一比一原版(UofT毕业证)多伦多大学毕业证如何办理
一比一原版(UofT毕业证)多伦多大学毕业证如何办理
 
一比一原版爱尔兰都柏林大学毕业证(本硕)ucd学位证书如何办理
一比一原版爱尔兰都柏林大学毕业证(本硕)ucd学位证书如何办理一比一原版爱尔兰都柏林大学毕业证(本硕)ucd学位证书如何办理
一比一原版爱尔兰都柏林大学毕业证(本硕)ucd学位证书如何办理
 
一比一原版南十字星大学毕业证(SCU毕业证书)学历如何办理
一比一原版南十字星大学毕业证(SCU毕业证书)学历如何办理一比一原版南十字星大学毕业证(SCU毕业证书)学历如何办理
一比一原版南十字星大学毕业证(SCU毕业证书)学历如何办理
 
一比一原版美国帕森斯设计学院毕业证(parsons毕业证书)如何办理
一比一原版美国帕森斯设计学院毕业证(parsons毕业证书)如何办理一比一原版美国帕森斯设计学院毕业证(parsons毕业证书)如何办理
一比一原版美国帕森斯设计学院毕业证(parsons毕业证书)如何办理
 
一比一原版悉尼大学毕业证如何办理
一比一原版悉尼大学毕业证如何办理一比一原版悉尼大学毕业证如何办理
一比一原版悉尼大学毕业证如何办理
 
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
 
一比一原版加拿大麦吉尔大学毕业证(mcgill毕业证书)如何办理
一比一原版加拿大麦吉尔大学毕业证(mcgill毕业证书)如何办理一比一原版加拿大麦吉尔大学毕业证(mcgill毕业证书)如何办理
一比一原版加拿大麦吉尔大学毕业证(mcgill毕业证书)如何办理
 
Data Scientist Machine Learning Profiles .pdf
Data Scientist Machine Learning  Profiles .pdfData Scientist Machine Learning  Profiles .pdf
Data Scientist Machine Learning Profiles .pdf
 
Discovering Digital Process Twins for What-if Analysis: a Process Mining Appr...
Discovering Digital Process Twins for What-if Analysis: a Process Mining Appr...Discovering Digital Process Twins for What-if Analysis: a Process Mining Appr...
Discovering Digital Process Twins for What-if Analysis: a Process Mining Appr...
 
一比一原版英属哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
一比一原版英属哥伦比亚大学毕业证(UBC毕业证书)学历如何办理一比一原版英属哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
一比一原版英属哥伦比亚大学毕业证(UBC毕业证书)学历如何办理
 
一比一原版多伦多大学毕业证(UofT毕业证书)学历如何办理
一比一原版多伦多大学毕业证(UofT毕业证书)学历如何办理一比一原版多伦多大学毕业证(UofT毕业证书)学历如何办理
一比一原版多伦多大学毕业证(UofT毕业证书)学历如何办理
 
一比一原版加拿大渥太华大学毕业证(uottawa毕业证书)如何办理
一比一原版加拿大渥太华大学毕业证(uottawa毕业证书)如何办理一比一原版加拿大渥太华大学毕业证(uottawa毕业证书)如何办理
一比一原版加拿大渥太华大学毕业证(uottawa毕业证书)如何办理
 
Econ3060_Screen Time and Success_ final_GroupProject.pdf
Econ3060_Screen Time and Success_ final_GroupProject.pdfEcon3060_Screen Time and Success_ final_GroupProject.pdf
Econ3060_Screen Time and Success_ final_GroupProject.pdf
 
ML-PPT-UNIT-2 Generative Classifiers Discriminative Classifiers
ML-PPT-UNIT-2 Generative Classifiers Discriminative ClassifiersML-PPT-UNIT-2 Generative Classifiers Discriminative Classifiers
ML-PPT-UNIT-2 Generative Classifiers Discriminative Classifiers
 
一比一原版(Sheffield毕业证书)谢菲尔德大学毕业证如何办理
一比一原版(Sheffield毕业证书)谢菲尔德大学毕业证如何办理一比一原版(Sheffield毕业证书)谢菲尔德大学毕业证如何办理
一比一原版(Sheffield毕业证书)谢菲尔德大学毕业证如何办理
 
Build applications with generative AI on Google Cloud
Build applications with generative AI on Google CloudBuild applications with generative AI on Google Cloud
Build applications with generative AI on Google Cloud
 
Cell The Unit of Life for NEET Multiple Choice Questions.docx
Cell The Unit of Life for NEET Multiple Choice Questions.docxCell The Unit of Life for NEET Multiple Choice Questions.docx
Cell The Unit of Life for NEET Multiple Choice Questions.docx
 
How To Control IO Usage using Resource Manager
How To Control IO Usage using Resource ManagerHow To Control IO Usage using Resource Manager
How To Control IO Usage using Resource Manager
 
一比一原版斯威本理工大学毕业证(swinburne毕业证)如何办理
一比一原版斯威本理工大学毕业证(swinburne毕业证)如何办理一比一原版斯威本理工大学毕业证(swinburne毕业证)如何办理
一比一原版斯威本理工大学毕业证(swinburne毕业证)如何办理
 

Grasp slides pptx

  • 1. Learning to grasp without human supervision
  • 2. Motivation • Current methods in grasp learning for previously unseen objects involve the transfer of features and primitives from humans to robots. • These transferred knowledge includes memory of previous grasps[], human labelled datasets[], pre-defined visual/depth features[] • But these previous methods are inherently biased towards a human’s knowledge and intuition • For truly autonomous manipulators, we need a framework that allows the robot itself to learn the knowledge and understanding for grasping
  • 3. Our Approach • We follow a learning by training approach where we have a dataset of images (and depth point clouds) of objects along with positive and negative grasp points • Since we need to eliminate the human in the loop, the robot itself should be able to collect training data • For this we have a robot execute random grasps on a wide variety of objects. The robot recognizes successful grasps using its inbuilt gripper force sensors
  • 4. Grasp Data collected • Currently our robot is capable of executing about 80 random grasps an hour per arm. Which on a typical day(running for about 8 hours) yields about 80*8*2 = 1280 grasps a day. • As of now, the robot has executed about 17,000 random grasps and has around 1300 successful grasps. This is already larger than Cornell Grasp Dataset that is hand labelled and doesn't contain negative examples (failure grasps) • Associated with each grasp we record data from 2 RGB image cameras on the arm, 1 Depth camera (Creative Senz3D) and Kinect V2 attached to the head of the robot. The recorded streams include the entire motion of the arm in the grasp sequence