SlideShare a Scribd company logo
1 of 20
Learning the skill of archery by a humanoid robot iCub Petar Kormushev,  Sylvain Calinon,  Ryo Saegusa,  Giorgio Metta Italian Institute of Technology (IIT)Advanced Robotics dept., RBCS dept. http://www.iit.it Humanoids 2010 Nashville, TN, USADecember 6-8, 2010
Motivation How a robot can learn complex motor skills? Why archery task? bi-manual coordination integration of image processing, motor control and learning parts in one coherent task using tools (bow and arrow) to affect an external object (target) appropriate task for testing different learning algorithms, because the reward is inherently defined by the goal of the task Petar Kormushev,  Italian Institute of Technology (IIT) 2/20
The archery task Different societies Different embodiments Zashikikarakuri, 18-19th century(Mechanical automatons) Kyudo(Japanese archery) Petar Kormushev,  Italian Institute of Technology (IIT) Differences in the learned skill 3/20
iCub archery skill iCub is an open-source humanoid robot with dimensions comparable to 3.5 year-old child, 104 cm tall, with 53 DOF. Static grasp of the bow Aiming skill Petar Kormushev,  Italian Institute of Technology (IIT) 4/20
Problem definition How to learn to shoot the arrowso that it hits the center of the target: ,[object Object]
recognize arrow’s position wrt. the targetAssumptions: ,[object Object]
Prior knowledge about the colors of the target and the arrowPetar Kormushev,  Italian Institute of Technology (IIT) 5/20
Proposed approach For learning bi-manual aiming: PoWER: EM-based Reinforcement Learning ARCHER: Chained vector regression algorithm For hands position/orientation control: IK motion controller for the two arms  For image recognition of the target and arrow: color-based detection based on GMM Petar Kormushev,  Italian Institute of Technology (IIT) 6/20
Learning algorithm #1: PoWER Policy learning by Weighting Exploration with the Returns (PoWER) Reasons to select PoWER: state-of-the-art EM-based RL algorithm no need of learning rate (unlike policy-gradient methods) efficient use of past experience via importance sampling single rollout enough to update policy Jens Kober and Jan Peters,  NIPS 2009 Petar Kormushev,  Italian Institute of Technology (IIT) 7/20
PoWER - implementation Policy parameters     : relative position the two hands(3D vector from right to left hand) Policy update rule: Importance sampling uses best σ rollouts so far relative exploration Petar Kormushev,  Italian Institute of Technology (IIT) 8/20
PoWER - reward function Return of an arrow shooting rollout    : Estimated target center position Estimated arrow tip position Petar Kormushev,  Italian Institute of Technology (IIT) 9/20
Learning algorithm #2: ARCHER Augmented Reward CHainEd Regression Multi-dimensional reward vector Iteratively converging process Using regression to estimate new parameters ARCHER can be viewed as a linear vector regression with a shrinking support region. Petar Kormushev,  Italian Institute of Technology (IIT) 10/20
Learning algorithm #2: ARCHER rollouts input parameters observed result target reward matrix form least-norm approximation of the weights: Petar Kormushev,  Italian Institute of Technology (IIT) 11/20
Learning algorithm #2: ARCHER ARCHER is suitable for problemsfor which: a-priori knowledge about the desired goal reward is known the reward can be decomposed into separate components the task has a smooth solution space Makes use of multi-dimensional reward, unlike standard RL, which only uses scalar reward Petar Kormushev,  Italian Institute of Technology (IIT) 12/20
Simulation experiment Convergence criteria: distance to the center < 5 cm PoWER ARCHER 19 rollouts to converge 5 rollouts to converge Petar Kormushev,  Italian Institute of Technology (IIT) 13/20
Speed of convergence Averaged over 40 runs with 60 rollouts in each run: ARCHER converges faster than PoWER due to: ,[object Object],     estimate parameters ,[object Object],     about the goal’s reward PoWER achieves reasonable performance despite using only 1D feedback information. First 3 rollouts with high random exploration Petar Kormushev,  Italian Institute of Technology (IIT) 14/20
Image recognition ,[object Object]
YUV color space (Y - luminance, UV – chrominance)
GMM for color-based detectionEstimated reward vector: Petar Kormushev,  Italian Institute of Technology (IIT) 15/20
Robot motion controller Pattacini et al, IROS 2010 Minimum-jerk IK cartesian controller Hands orientation control Posture and grasping configuration Petar Kormushev,  Italian Institute of Technology (IIT) 16/20

More Related Content

What's hot

Camouflage Color Changing Robot For Military Purpose
Camouflage Color Changing Robot For Military PurposeCamouflage Color Changing Robot For Military Purpose
Camouflage Color Changing Robot For Military PurposeHitesh Shinde
 
Simultaneous Mapping and Navigation For Rendezvous in Space Applications
Simultaneous Mapping and Navigation For Rendezvous in Space ApplicationsSimultaneous Mapping and Navigation For Rendezvous in Space Applications
Simultaneous Mapping and Navigation For Rendezvous in Space ApplicationsNandakishor Jahagirdar
 
Pandora Robotics Team - 2007 to 2015 - ECE, AUTH
Pandora Robotics Team - 2007 to 2015 - ECE, AUTHPandora Robotics Team - 2007 to 2015 - ECE, AUTH
Pandora Robotics Team - 2007 to 2015 - ECE, AUTHManos Tsardoulias
 
Camouflage Color Changing Robot
Camouflage Color Changing RobotCamouflage Color Changing Robot
Camouflage Color Changing RobotHitesh Shinde
 
Modelling of walking humanoid robot with capability of floor detection and dy...
Modelling of walking humanoid robot with capability of floor detection and dy...Modelling of walking humanoid robot with capability of floor detection and dy...
Modelling of walking humanoid robot with capability of floor detection and dy...ijfcstjournal
 
Makeblock brief presentation 2016
Makeblock brief presentation 2016Makeblock brief presentation 2016
Makeblock brief presentation 2016Tony Zheng
 
Visual pattern recognition in robotics
Visual pattern recognition in roboticsVisual pattern recognition in robotics
Visual pattern recognition in roboticsIAEME Publication
 
Robot Software Architecture (Mobile Robots)
Robot Software Architecture (Mobile Robots)Robot Software Architecture (Mobile Robots)
Robot Software Architecture (Mobile Robots)Satyanarayana Mekala
 
RGB colour detection and tracking on MATLAB
RGB colour detection and tracking on MATLABRGB colour detection and tracking on MATLAB
RGB colour detection and tracking on MATLABNirma University
 
Vision system for robotics and servo controller
Vision system for robotics and servo controllerVision system for robotics and servo controller
Vision system for robotics and servo controllerGowsick Subramaniam
 

What's hot (18)

Camouflage Color Changing Robot For Military Purpose
Camouflage Color Changing Robot For Military PurposeCamouflage Color Changing Robot For Military Purpose
Camouflage Color Changing Robot For Military Purpose
 
Simultaneous Mapping and Navigation For Rendezvous in Space Applications
Simultaneous Mapping and Navigation For Rendezvous in Space ApplicationsSimultaneous Mapping and Navigation For Rendezvous in Space Applications
Simultaneous Mapping and Navigation For Rendezvous in Space Applications
 
Pandora Robotics Team - 2007 to 2015 - ECE, AUTH
Pandora Robotics Team - 2007 to 2015 - ECE, AUTHPandora Robotics Team - 2007 to 2015 - ECE, AUTH
Pandora Robotics Team - 2007 to 2015 - ECE, AUTH
 
Unit 3 machine vision
Unit 3 machine vision Unit 3 machine vision
Unit 3 machine vision
 
Industrial robovision
Industrial robovisionIndustrial robovision
Industrial robovision
 
Camouflage Color Changing Robot
Camouflage Color Changing RobotCamouflage Color Changing Robot
Camouflage Color Changing Robot
 
Modelling of walking humanoid robot with capability of floor detection and dy...
Modelling of walking humanoid robot with capability of floor detection and dy...Modelling of walking humanoid robot with capability of floor detection and dy...
Modelling of walking humanoid robot with capability of floor detection and dy...
 
First Thesis Presentation
First Thesis PresentationFirst Thesis Presentation
First Thesis Presentation
 
Second Thesis Presentation
Second Thesis PresentationSecond Thesis Presentation
Second Thesis Presentation
 
Robot cell modeling and collision detection based on Matlab
Robot cell modeling and collision detection based on MatlabRobot cell modeling and collision detection based on Matlab
Robot cell modeling and collision detection based on Matlab
 
Makeblock brief presentation 2016
Makeblock brief presentation 2016Makeblock brief presentation 2016
Makeblock brief presentation 2016
 
Traffic Violation Detector using Object Detection
Traffic Violation Detector using Object DetectionTraffic Violation Detector using Object Detection
Traffic Violation Detector using Object Detection
 
Visual pattern recognition in robotics
Visual pattern recognition in roboticsVisual pattern recognition in robotics
Visual pattern recognition in robotics
 
Robot Software Architecture (Mobile Robots)
Robot Software Architecture (Mobile Robots)Robot Software Architecture (Mobile Robots)
Robot Software Architecture (Mobile Robots)
 
RGB colour detection and tracking on MATLAB
RGB colour detection and tracking on MATLABRGB colour detection and tracking on MATLAB
RGB colour detection and tracking on MATLAB
 
H011124050
H011124050H011124050
H011124050
 
Vision system for robotics and servo controller
Vision system for robotics and servo controllerVision system for robotics and servo controller
Vision system for robotics and servo controller
 
685 robotics.nl
685 robotics.nl685 robotics.nl
685 robotics.nl
 

Viewers also liked

Giuliano Sandini. Robotics and AI
Giuliano Sandini. Robotics and AIGiuliano Sandini. Robotics and AI
Giuliano Sandini. Robotics and AIAlbert Yefimov
 
victores2014thesis-presentation
victores2014thesis-presentationvictores2014thesis-presentation
victores2014thesis-presentationJuan G. Victores
 
Reactive Reaching and Grasping on a Humanoid: Towards Closing the Action-Perc...
Reactive Reaching and Grasping on a Humanoid: Towards Closing the Action-Perc...Reactive Reaching and Grasping on a Humanoid: Towards Closing the Action-Perc...
Reactive Reaching and Grasping on a Humanoid: Towards Closing the Action-Perc...Juxi Leitner
 
Cognitive robotics tools and technology
Cognitive robotics tools and technologyCognitive robotics tools and technology
Cognitive robotics tools and technologyMartin Peniak
 
Icub case study en
Icub case study enIcub case study en
Icub case study eneyeOS
 
Introduction to humanoid robot iCub, YARP and simulator
Introduction to humanoid robot iCub, YARP and simulatorIntroduction to humanoid robot iCub, YARP and simulator
Introduction to humanoid robot iCub, YARP and simulatorMartin Peniak
 
Aquila: An Open-Source GPU-Accelerated Toolkit for Cognitive and Neuro-Roboti...
Aquila: An Open-Source GPU-Accelerated Toolkit for Cognitive and Neuro-Roboti...Aquila: An Open-Source GPU-Accelerated Toolkit for Cognitive and Neuro-Roboti...
Aquila: An Open-Source GPU-Accelerated Toolkit for Cognitive and Neuro-Roboti...Martin Peniak
 
Artificial Intelligence Robotics (AI) PPT by Aamir Saleem Ansari
Artificial Intelligence Robotics (AI) PPT by Aamir Saleem AnsariArtificial Intelligence Robotics (AI) PPT by Aamir Saleem Ansari
Artificial Intelligence Robotics (AI) PPT by Aamir Saleem AnsariTech
 

Viewers also liked (9)

Giuliano Sandini. Robotics and AI
Giuliano Sandini. Robotics and AIGiuliano Sandini. Robotics and AI
Giuliano Sandini. Robotics and AI
 
victores2014thesis-presentation
victores2014thesis-presentationvictores2014thesis-presentation
victores2014thesis-presentation
 
Aquila 2.0
Aquila 2.0Aquila 2.0
Aquila 2.0
 
Reactive Reaching and Grasping on a Humanoid: Towards Closing the Action-Perc...
Reactive Reaching and Grasping on a Humanoid: Towards Closing the Action-Perc...Reactive Reaching and Grasping on a Humanoid: Towards Closing the Action-Perc...
Reactive Reaching and Grasping on a Humanoid: Towards Closing the Action-Perc...
 
Cognitive robotics tools and technology
Cognitive robotics tools and technologyCognitive robotics tools and technology
Cognitive robotics tools and technology
 
Icub case study en
Icub case study enIcub case study en
Icub case study en
 
Introduction to humanoid robot iCub, YARP and simulator
Introduction to humanoid robot iCub, YARP and simulatorIntroduction to humanoid robot iCub, YARP and simulator
Introduction to humanoid robot iCub, YARP and simulator
 
Aquila: An Open-Source GPU-Accelerated Toolkit for Cognitive and Neuro-Roboti...
Aquila: An Open-Source GPU-Accelerated Toolkit for Cognitive and Neuro-Roboti...Aquila: An Open-Source GPU-Accelerated Toolkit for Cognitive and Neuro-Roboti...
Aquila: An Open-Source GPU-Accelerated Toolkit for Cognitive and Neuro-Roboti...
 
Artificial Intelligence Robotics (AI) PPT by Aamir Saleem Ansari
Artificial Intelligence Robotics (AI) PPT by Aamir Saleem AnsariArtificial Intelligence Robotics (AI) PPT by Aamir Saleem Ansari
Artificial Intelligence Robotics (AI) PPT by Aamir Saleem Ansari
 

Similar to Learning the skill of archery by a humanoid robot iCub

Fuzzy-proportional-integral-derivative-based controller for object tracking i...
Fuzzy-proportional-integral-derivative-based controller for object tracking i...Fuzzy-proportional-integral-derivative-based controller for object tracking i...
Fuzzy-proportional-integral-derivative-based controller for object tracking i...IJECEIAES
 
Presentation Object Recognition And Tracking Project
Presentation Object Recognition And Tracking ProjectPresentation Object Recognition And Tracking Project
Presentation Object Recognition And Tracking ProjectPrathamesh Joshi
 
Intelligent indoor mobile robot navigation using stereo vision
Intelligent indoor mobile robot navigation using stereo visionIntelligent indoor mobile robot navigation using stereo vision
Intelligent indoor mobile robot navigation using stereo visionsipij
 
Visual pattern recognition in robotics
Visual pattern recognition in roboticsVisual pattern recognition in robotics
Visual pattern recognition in roboticsIAEME Publication
 
Tiny-YOLO distance measurement and object detection coordination system for t...
Tiny-YOLO distance measurement and object detection coordination system for t...Tiny-YOLO distance measurement and object detection coordination system for t...
Tiny-YOLO distance measurement and object detection coordination system for t...IJECEIAES
 
Control of a Movable Robot Head Using Vision-Based Object Tracking
Control of a Movable Robot Head Using Vision-Based Object TrackingControl of a Movable Robot Head Using Vision-Based Object Tracking
Control of a Movable Robot Head Using Vision-Based Object TrackingIJECEIAES
 
Trajectory reconstruction for robot programming by demonstration
Trajectory reconstruction for robot programming  by demonstration  Trajectory reconstruction for robot programming  by demonstration
Trajectory reconstruction for robot programming by demonstration IJECEIAES
 
Interactive Full-Body Motion Capture Using Infrared Sensor Network
Interactive Full-Body Motion Capture Using Infrared Sensor Network  Interactive Full-Body Motion Capture Using Infrared Sensor Network
Interactive Full-Body Motion Capture Using Infrared Sensor Network ijcga
 
[Paper research] GOSELO: for Robot navigation using Reactive neural networks
[Paper research] GOSELO: for Robot navigation using Reactive neural networks[Paper research] GOSELO: for Robot navigation using Reactive neural networks
[Paper research] GOSELO: for Robot navigation using Reactive neural networksJehong Lee
 
IEEE/RSJ IROS 2008 Real-time Tracker
IEEE/RSJ IROS 2008 Real-time TrackerIEEE/RSJ IROS 2008 Real-time Tracker
IEEE/RSJ IROS 2008 Real-time Trackerc.choi
 
Camouflafe color changing robot
Camouflafe color changing robotCamouflafe color changing robot
Camouflafe color changing robotAtharvaPathak13
 
Interfacing of MATLAB with Arduino for Object Detection Algorithm Implementat...
Interfacing of MATLAB with Arduino for Object Detection Algorithm Implementat...Interfacing of MATLAB with Arduino for Object Detection Algorithm Implementat...
Interfacing of MATLAB with Arduino for Object Detection Algorithm Implementat...Panth Shah
 
Interactive full body motion capture using infrared sensor network
Interactive full body motion capture using infrared sensor networkInteractive full body motion capture using infrared sensor network
Interactive full body motion capture using infrared sensor networkijcga
 
MediaEval 2018: Fine grained sport action recognition: Application to table t...
MediaEval 2018: Fine grained sport action recognition: Application to table t...MediaEval 2018: Fine grained sport action recognition: Application to table t...
MediaEval 2018: Fine grained sport action recognition: Application to table t...multimediaeval
 
Saksham seminar report
Saksham seminar reportSaksham seminar report
Saksham seminar reportSakshamTurki
 

Similar to Learning the skill of archery by a humanoid robot iCub (20)

Fuzzy-proportional-integral-derivative-based controller for object tracking i...
Fuzzy-proportional-integral-derivative-based controller for object tracking i...Fuzzy-proportional-integral-derivative-based controller for object tracking i...
Fuzzy-proportional-integral-derivative-based controller for object tracking i...
 
Robot vision
Robot visionRobot vision
Robot vision
 
icit
iciticit
icit
 
Presentation Object Recognition And Tracking Project
Presentation Object Recognition And Tracking ProjectPresentation Object Recognition And Tracking Project
Presentation Object Recognition And Tracking Project
 
Intelligent indoor mobile robot navigation using stereo vision
Intelligent indoor mobile robot navigation using stereo visionIntelligent indoor mobile robot navigation using stereo vision
Intelligent indoor mobile robot navigation using stereo vision
 
Visual pattern recognition in robotics
Visual pattern recognition in roboticsVisual pattern recognition in robotics
Visual pattern recognition in robotics
 
30120140506012 2
30120140506012 230120140506012 2
30120140506012 2
 
30120140506012 2
30120140506012 230120140506012 2
30120140506012 2
 
Tiny-YOLO distance measurement and object detection coordination system for t...
Tiny-YOLO distance measurement and object detection coordination system for t...Tiny-YOLO distance measurement and object detection coordination system for t...
Tiny-YOLO distance measurement and object detection coordination system for t...
 
Control of a Movable Robot Head Using Vision-Based Object Tracking
Control of a Movable Robot Head Using Vision-Based Object TrackingControl of a Movable Robot Head Using Vision-Based Object Tracking
Control of a Movable Robot Head Using Vision-Based Object Tracking
 
Trajectory reconstruction for robot programming by demonstration
Trajectory reconstruction for robot programming  by demonstration  Trajectory reconstruction for robot programming  by demonstration
Trajectory reconstruction for robot programming by demonstration
 
Interactive Full-Body Motion Capture Using Infrared Sensor Network
Interactive Full-Body Motion Capture Using Infrared Sensor Network  Interactive Full-Body Motion Capture Using Infrared Sensor Network
Interactive Full-Body Motion Capture Using Infrared Sensor Network
 
[Paper research] GOSELO: for Robot navigation using Reactive neural networks
[Paper research] GOSELO: for Robot navigation using Reactive neural networks[Paper research] GOSELO: for Robot navigation using Reactive neural networks
[Paper research] GOSELO: for Robot navigation using Reactive neural networks
 
IEEE/RSJ IROS 2008 Real-time Tracker
IEEE/RSJ IROS 2008 Real-time TrackerIEEE/RSJ IROS 2008 Real-time Tracker
IEEE/RSJ IROS 2008 Real-time Tracker
 
Camouflafe color changing robot
Camouflafe color changing robotCamouflafe color changing robot
Camouflafe color changing robot
 
Interfacing of MATLAB with Arduino for Object Detection Algorithm Implementat...
Interfacing of MATLAB with Arduino for Object Detection Algorithm Implementat...Interfacing of MATLAB with Arduino for Object Detection Algorithm Implementat...
Interfacing of MATLAB with Arduino for Object Detection Algorithm Implementat...
 
Interactive full body motion capture using infrared sensor network
Interactive full body motion capture using infrared sensor networkInteractive full body motion capture using infrared sensor network
Interactive full body motion capture using infrared sensor network
 
Color Tracking Robot
Color Tracking RobotColor Tracking Robot
Color Tracking Robot
 
MediaEval 2018: Fine grained sport action recognition: Application to table t...
MediaEval 2018: Fine grained sport action recognition: Application to table t...MediaEval 2018: Fine grained sport action recognition: Application to table t...
MediaEval 2018: Fine grained sport action recognition: Application to table t...
 
Saksham seminar report
Saksham seminar reportSaksham seminar report
Saksham seminar report
 

Recently uploaded

Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptxLBM Solutions
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2Hyundai Motor Group
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Alan Dix
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxOnBoard
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraDeakin University
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...shyamraj55
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersThousandEyes
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure servicePooja Nehwal
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 3652toLead Limited
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...HostedbyConfluent
 
Azure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAzure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAndikSusilo4
 

Recently uploaded (20)

Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptx
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptxVulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
 
Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptx
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning era
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
 
The transition to renewables in India.pdf
The transition to renewables in India.pdfThe transition to renewables in India.pdf
The transition to renewables in India.pdf
 
Azure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAzure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & Application
 

Learning the skill of archery by a humanoid robot iCub

  • 1. Learning the skill of archery by a humanoid robot iCub Petar Kormushev, Sylvain Calinon, Ryo Saegusa, Giorgio Metta Italian Institute of Technology (IIT)Advanced Robotics dept., RBCS dept. http://www.iit.it Humanoids 2010 Nashville, TN, USADecember 6-8, 2010
  • 2. Motivation How a robot can learn complex motor skills? Why archery task? bi-manual coordination integration of image processing, motor control and learning parts in one coherent task using tools (bow and arrow) to affect an external object (target) appropriate task for testing different learning algorithms, because the reward is inherently defined by the goal of the task Petar Kormushev, Italian Institute of Technology (IIT) 2/20
  • 3. The archery task Different societies Different embodiments Zashikikarakuri, 18-19th century(Mechanical automatons) Kyudo(Japanese archery) Petar Kormushev, Italian Institute of Technology (IIT) Differences in the learned skill 3/20
  • 4. iCub archery skill iCub is an open-source humanoid robot with dimensions comparable to 3.5 year-old child, 104 cm tall, with 53 DOF. Static grasp of the bow Aiming skill Petar Kormushev, Italian Institute of Technology (IIT) 4/20
  • 5.
  • 6.
  • 7. Prior knowledge about the colors of the target and the arrowPetar Kormushev, Italian Institute of Technology (IIT) 5/20
  • 8. Proposed approach For learning bi-manual aiming: PoWER: EM-based Reinforcement Learning ARCHER: Chained vector regression algorithm For hands position/orientation control: IK motion controller for the two arms For image recognition of the target and arrow: color-based detection based on GMM Petar Kormushev, Italian Institute of Technology (IIT) 6/20
  • 9. Learning algorithm #1: PoWER Policy learning by Weighting Exploration with the Returns (PoWER) Reasons to select PoWER: state-of-the-art EM-based RL algorithm no need of learning rate (unlike policy-gradient methods) efficient use of past experience via importance sampling single rollout enough to update policy Jens Kober and Jan Peters, NIPS 2009 Petar Kormushev, Italian Institute of Technology (IIT) 7/20
  • 10. PoWER - implementation Policy parameters : relative position the two hands(3D vector from right to left hand) Policy update rule: Importance sampling uses best σ rollouts so far relative exploration Petar Kormushev, Italian Institute of Technology (IIT) 8/20
  • 11. PoWER - reward function Return of an arrow shooting rollout : Estimated target center position Estimated arrow tip position Petar Kormushev, Italian Institute of Technology (IIT) 9/20
  • 12. Learning algorithm #2: ARCHER Augmented Reward CHainEd Regression Multi-dimensional reward vector Iteratively converging process Using regression to estimate new parameters ARCHER can be viewed as a linear vector regression with a shrinking support region. Petar Kormushev, Italian Institute of Technology (IIT) 10/20
  • 13. Learning algorithm #2: ARCHER rollouts input parameters observed result target reward matrix form least-norm approximation of the weights: Petar Kormushev, Italian Institute of Technology (IIT) 11/20
  • 14. Learning algorithm #2: ARCHER ARCHER is suitable for problemsfor which: a-priori knowledge about the desired goal reward is known the reward can be decomposed into separate components the task has a smooth solution space Makes use of multi-dimensional reward, unlike standard RL, which only uses scalar reward Petar Kormushev, Italian Institute of Technology (IIT) 12/20
  • 15. Simulation experiment Convergence criteria: distance to the center < 5 cm PoWER ARCHER 19 rollouts to converge 5 rollouts to converge Petar Kormushev, Italian Institute of Technology (IIT) 13/20
  • 16.
  • 17.
  • 18. YUV color space (Y - luminance, UV – chrominance)
  • 19. GMM for color-based detectionEstimated reward vector: Petar Kormushev, Italian Institute of Technology (IIT) 15/20
  • 20. Robot motion controller Pattacini et al, IROS 2010 Minimum-jerk IK cartesian controller Hands orientation control Posture and grasping configuration Petar Kormushev, Italian Institute of Technology (IIT) 16/20
  • 21. Real-world experiment Petar Kormushev, Italian Institute of Technology (IIT) 17/20
  • 22.
  • 23.
  • 24. Two learning algorithms were used to coordinate the posture of the hands:
  • 26. ARCHER: local vector regression with shrinking support region
  • 27. Reward was extracted autonomously from visual feedback via colored-basedimage processing using GMM
  • 28. ARCHER converges faster than PoWER due to:
  • 32. Future work: use imitation learning to teach the robot the whole movement for grasping and pulling the arrowPetar Kormushev, Italian Institute of Technology (IIT) 19/20
  • 33. Thank you for your kind attention! Petar Kormushev, Italian Institute of Technology (IIT) More information: http://kormushev.com/ 20/20

Editor's Notes

  1. The problem of detecting where the target is, and what isthe relative position of the arrow with respect to the centerof the target, is solved by image processing. We use colorbaseddetection of the target and the tip of the arrow basedon Gaussian Mixture Model (GMM). The color detection isdone in YUV color space, where Y is the luminance, andUV is the chrominance. Only U and V components are usedto ensure robustness to changes in luminosity.In a calibration phase, prior to conducting an archeryexperiment, the user explicitly defines on a camera imagethe position and size of the target and the position of thearrow’s tip. Then, the user manually selects NT pixels lyinginside the target in the image, and NA pixels from the arrow’stip in the image. The selected points produce two datasets:cT 2 R2NT and cA 2 R2NA respectively.From the two datasets cT and cA, a Gaussian MixtureModel (GMM) is used to learn a compact model of the colorcharacteristics in UV space of the relevant objects. EachGMM is described by the set of parameters fk; k;kgKk=1,representing respectively the prior probabilities, centers andcovariance matrices of the model (full covariances are consideredhere). The prior probabilities k satisfy k 2 R[0;1]andPKk=1 k = 1. A Bayesian Information Criterion (BIC)[13] is used to select the appropriate number of GaussiansKT and KA to represent effectively the features to track.After each reproduction attempt, a camera snapshot istaken to re-estimate the position of the arrow and the target.2From the image cI 2 R2NxNy of NxNy pixels in UVcolor space, the center m of each object on the image isestimated through the weighted sum