SlideShare una empresa de Scribd logo
1 de 24
Multi-Robot Systems CSCI 7000-006 Wednesday, September 9, 2009 NikolausCorrell
So far Reactive algorithms, robotic swarms Limited number of internal states Direct coupling between perception and action Threshold-based algorithms are a powerful method for task allocation Coordination Implicit by modifiying the environment Explicit by local communication Propagating directional information are a powerful method for navigation
Today Deliberative algorithms Planning vs. reacting? Computational vs. Robotic algorithms
Deliberation Computational representation of the problem (model, e.g. map or graph) Reasoning on representation Robot: Sensors to determine world-state Mapping algorithmic solution into action
“Why is robotics hard?” (again) Sensors are flaky Internal representation not accurate Planning becomes suboptimal or wrong Actuators are unreliable Mismatch between states in the plan and the world Course question: How do YOU resolve an everyday navigation problem?
Making robots more robust Adding sensors (allows cross-validation) But: sensors again unreliable Bayesian approach Maintain probability distribution over belief states and use sensors to update beliefs Redundancy 50% 50% 5% 95%
Example: Deliberation and Uncertainty Scenario: visit and circumnavigate every blade at least once Environment unknown Course question Computational representation Algorithm for complete coverage Potential problems?
Computational representation Graph Vertices: blades Edges: routes between blades  Depth-First-Search “Count blades” Minimal spanning tree Use A* for moving toward nearest unexplored edge
From planning to action Sensors: distance sensor/odometer Wall following Detect round and sharp tip Controller Detect waypoint (probabilistic) Launch to neighbor (open-loop) Until blade is hit Problems Wrong waypoint Wheel-slip N. Correll, S. Rutishauser, and A. Martinoli. Comparing Coordination Schemes for Miniature Robotic Swarms: A Case Study in Boundary Coverage of Regular Structures. In The 10th International Symposium on Experimental Robotics (ISER), Rio de Janeiro, 2006. Springer Tracts in Advanced Robotics, volume 38, pages 471-480, 2008
Basic Navigation Behaviors 9/20/2007 Nikolaus Correll 10
Analysis Complete algorithm becomes probabilistic Starting over when lost Implicit collaboration 10% wheel-slip 50% wheel-slip 6000 experiments in Webots, 10% wheel-slip Time for covering one blade Probability of no navigation error
Debate Statement: Deterministic algorithms become probabilistic due to noise What if the sensors and controllers would be more precise? Can you find counter examples? Does planning always make sense? Why wouldn’t it?
Adding sensors Localization offers chance to recover Failure can be detected and robot can re-plan Problem: Noise on localization 95% successful detection
Algorithm Initialize new cells with p=95% Initialize unexplored neighbors with p=0% Use Dijkstra’s algorithm to move towards cell with lowest likelihood of coverage After n-th visit update cells with posterior CQ: Termination criteria? S. Rutishauser, N. Correll, and A. Martinoli. Collaborative Coverage using a Swarm of Networked Miniature Robots. Robotics & Autonomous Systems, 57(5):517-525, 2009
Analysis Additional sensors provide additional confidence But: Solution remains probabilistic This example: expected runtime is a function of inspected confidence
Explicit Collaboration Share progress via radio (broadcast) Stitch maps together using global coordinates Update coverage probabilities New Problem: communication failure 16 j i
9/20/2007 Nikolaus Correll 17
Analysis Communication reliability impacts collaboration efficiency Communication content “deterministic” due to error correction Algorithm: non-optimal collaboration No Comm. Comm. Termination Criterion: 99% coverage
Summary Deliberative planning produces superior performance over reactive algorithms Both approaches are probabilistic due to real-world noise Deliberation and communication comes at cost! Find ways to recover / correct errors by adding Sensors redundancy Exchange information to strengthen hypothesises
State-of-the Art Example: Multi-Robot Exploration and Mapping Maps generated by laser-scan and odometry Robots drive toward unexplored frontiers Robots actively validate relative localization Relative position of team unknown initially Robots share maps Fox, D.   Ko, J.   Konolige, K.   Limketkai, B.   Schulz, D.   Stewart, B.  Distributed Multi-robot Exploration and Mapping. Proceedings of the IEEE, 94:7:1325-1339.
Map Sharing Find best match for other robot’s position given its Map Trajectory Initialize with uniform belief distribution Prune estimates as the robot moves Continue exploration together from thereon Fox, D.   Ko, J.   Konolige, K.   Limketkai, B.   Schulz, D.   Stewart, B.  Distributed Multi-robot Exploration and Mapping. Proceedings of the IEEE, 94:7:1325-1339.
Robot Coordination Trade off between exploration and exploitation Move towards unexplored frontiers Validate other robots’ positions
Friday No lab More deliberative algorithms: optimal coordination
Organization Traveling on Monday, September 14-16 Localization sensor and scanner are late Next week: Building-Week Putting together robots Commissioning laser scanner and localization system

Más contenido relacionado

Similar a September 9, Deliberative Algorithms I

LRC Presentation
LRC PresentationLRC Presentation
LRC PresentationMonolithix
 
November 9, Planning and Control of Unmanned Aircraft Systems in Realistic C...
November 9, Planning and Control of Unmanned Aircraft Systems  in Realistic C...November 9, Planning and Control of Unmanned Aircraft Systems  in Realistic C...
November 9, Planning and Control of Unmanned Aircraft Systems in Realistic C...University of Colorado at Boulder
 
Automatic Differentiation and SciML in Reality: What can go wrong, and what t...
Automatic Differentiation and SciML in Reality: What can go wrong, and what t...Automatic Differentiation and SciML in Reality: What can go wrong, and what t...
Automatic Differentiation and SciML in Reality: What can go wrong, and what t...Chris Rackauckas
 
"An adaptive modular approach to the mining of sensor network ...
"An adaptive modular approach to the mining of sensor network ..."An adaptive modular approach to the mining of sensor network ...
"An adaptive modular approach to the mining of sensor network ...butest
 
Project on collision avoidance in static and dynamic environment
Project on collision avoidance in static and dynamic environmentProject on collision avoidance in static and dynamic environment
Project on collision avoidance in static and dynamic environmentgopaljee1989
 
Self-Flying Drones: On a Mission to Navigate Dark, Dangerous and Unknown Worlds
Self-Flying Drones: On a Mission to Navigate Dark, Dangerous and Unknown WorldsSelf-Flying Drones: On a Mission to Navigate Dark, Dangerous and Unknown Worlds
Self-Flying Drones: On a Mission to Navigate Dark, Dangerous and Unknown WorldsTahoe Silicon Mountain
 
Quantum computing and machine learning overview
Quantum computing and machine learning overviewQuantum computing and machine learning overview
Quantum computing and machine learning overviewColleen Farrelly
 
Recent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesRecent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesNamkug Kim
 
A study on data fusion techniques used in multiple radar tracking
A study on data fusion techniques used in multiple radar trackingA study on data fusion techniques used in multiple radar tracking
A study on data fusion techniques used in multiple radar trackingTBSS Group
 
Interactive Wall (Multi Touch Interactive Surface)
Interactive Wall (Multi Touch Interactive Surface)Interactive Wall (Multi Touch Interactive Surface)
Interactive Wall (Multi Touch Interactive Surface)alaxandre
 
Enhancing indoor localization using IoT techniques
Enhancing indoor localization using IoT techniquesEnhancing indoor localization using IoT techniques
Enhancing indoor localization using IoT techniquesMohamed Nabil, MSc.
 

Similar a September 9, Deliberative Algorithms I (20)

September 28, Course Projects
September 28, Course ProjectsSeptember 28, Course Projects
September 28, Course Projects
 
Deep learning and computer vision
Deep learning and computer visionDeep learning and computer vision
Deep learning and computer vision
 
LRC Presentation
LRC PresentationLRC Presentation
LRC Presentation
 
November 9, Planning and Control of Unmanned Aircraft Systems in Realistic C...
November 9, Planning and Control of Unmanned Aircraft Systems  in Realistic C...November 9, Planning and Control of Unmanned Aircraft Systems  in Realistic C...
November 9, Planning and Control of Unmanned Aircraft Systems in Realistic C...
 
Research Poster_3
Research Poster_3Research Poster_3
Research Poster_3
 
Automatic Differentiation and SciML in Reality: What can go wrong, and what t...
Automatic Differentiation and SciML in Reality: What can go wrong, and what t...Automatic Differentiation and SciML in Reality: What can go wrong, and what t...
Automatic Differentiation and SciML in Reality: What can go wrong, and what t...
 
September 21, Modeling of Gradient-Based Controllers I
September 21, Modeling of Gradient-Based Controllers ISeptember 21, Modeling of Gradient-Based Controllers I
September 21, Modeling of Gradient-Based Controllers I
 
"An adaptive modular approach to the mining of sensor network ...
"An adaptive modular approach to the mining of sensor network ..."An adaptive modular approach to the mining of sensor network ...
"An adaptive modular approach to the mining of sensor network ...
 
Project on collision avoidance in static and dynamic environment
Project on collision avoidance in static and dynamic environmentProject on collision avoidance in static and dynamic environment
Project on collision avoidance in static and dynamic environment
 
Self-Flying Drones: On a Mission to Navigate Dark, Dangerous and Unknown Worlds
Self-Flying Drones: On a Mission to Navigate Dark, Dangerous and Unknown WorldsSelf-Flying Drones: On a Mission to Navigate Dark, Dangerous and Unknown Worlds
Self-Flying Drones: On a Mission to Navigate Dark, Dangerous and Unknown Worlds
 
Quantum computing and machine learning overview
Quantum computing and machine learning overviewQuantum computing and machine learning overview
Quantum computing and machine learning overview
 
Recent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesRecent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectives
 
A study on data fusion techniques used in multiple radar tracking
A study on data fusion techniques used in multiple radar trackingA study on data fusion techniques used in multiple radar tracking
A study on data fusion techniques used in multiple radar tracking
 
Interactive Wall (Multi Touch Interactive Surface)
Interactive Wall (Multi Touch Interactive Surface)Interactive Wall (Multi Touch Interactive Surface)
Interactive Wall (Multi Touch Interactive Surface)
 
Myung - Computational Cognition and Robust Decision Making - Spring Review 2013
Myung - Computational Cognition and Robust Decision Making - Spring Review 2013Myung - Computational Cognition and Robust Decision Making - Spring Review 2013
Myung - Computational Cognition and Robust Decision Making - Spring Review 2013
 
Enhancing indoor localization using IoT techniques
Enhancing indoor localization using IoT techniquesEnhancing indoor localization using IoT techniques
Enhancing indoor localization using IoT techniques
 
August 31, Reactive Algorithms I
August 31, Reactive Algorithms IAugust 31, Reactive Algorithms I
August 31, Reactive Algorithms I
 
November 30, Projects
November 30, ProjectsNovember 30, Projects
November 30, Projects
 
Space Tug Rendezvous
Space Tug RendezvousSpace Tug Rendezvous
Space Tug Rendezvous
 
The Allosphere
The AllosphereThe Allosphere
The Allosphere
 

Más de University of Colorado at Boulder

Three-dimensional construction with mobile robots and modular blocks
 Three-dimensional construction with mobile robots and modular blocks Three-dimensional construction with mobile robots and modular blocks
Three-dimensional construction with mobile robots and modular blocksUniversity of Colorado at Boulder
 

Más de University of Colorado at Boulder (20)

Three-dimensional construction with mobile robots and modular blocks
 Three-dimensional construction with mobile robots and modular blocks Three-dimensional construction with mobile robots and modular blocks
Three-dimensional construction with mobile robots and modular blocks
 
Template classes and ROS messages
Template classes and ROS messagesTemplate classes and ROS messages
Template classes and ROS messages
 
NLP for Robotics
NLP for RoboticsNLP for Robotics
NLP for Robotics
 
Indoor Localization Systems
Indoor Localization SystemsIndoor Localization Systems
Indoor Localization Systems
 
Vishal Verma: Rapidly Exploring Random Trees
Vishal Verma: Rapidly Exploring Random TreesVishal Verma: Rapidly Exploring Random Trees
Vishal Verma: Rapidly Exploring Random Trees
 
Lecture 10: Summary
Lecture 10: SummaryLecture 10: Summary
Lecture 10: Summary
 
Lecture 09: SLAM
Lecture 09: SLAMLecture 09: SLAM
Lecture 09: SLAM
 
Lecture 08: Localization and Mapping II
Lecture 08: Localization and Mapping IILecture 08: Localization and Mapping II
Lecture 08: Localization and Mapping II
 
Lecture 07: Localization and Mapping I
Lecture 07: Localization and Mapping ILecture 07: Localization and Mapping I
Lecture 07: Localization and Mapping I
 
Lecture 06: Features and Uncertainty
Lecture 06: Features and UncertaintyLecture 06: Features and Uncertainty
Lecture 06: Features and Uncertainty
 
Lecture 05
Lecture 05Lecture 05
Lecture 05
 
Lecture 04
Lecture 04Lecture 04
Lecture 04
 
Lecture 03 - Kinematics and Control
Lecture 03 - Kinematics and ControlLecture 03 - Kinematics and Control
Lecture 03 - Kinematics and Control
 
Lecture 02: Locomotion
Lecture 02: LocomotionLecture 02: Locomotion
Lecture 02: Locomotion
 
Lecture 01
Lecture 01Lecture 01
Lecture 01
 
Lectures 11+12: Debates
Lectures 11+12: DebatesLectures 11+12: Debates
Lectures 11+12: Debates
 
Lecture 09: Localization and Mapping III
Lecture 09: Localization and Mapping IIILecture 09: Localization and Mapping III
Lecture 09: Localization and Mapping III
 
Lecture 10: Navigation
Lecture 10: NavigationLecture 10: Navigation
Lecture 10: Navigation
 
Lecture 08: Localization and Mapping II
Lecture 08: Localization and Mapping IILecture 08: Localization and Mapping II
Lecture 08: Localization and Mapping II
 
Lecture 07: Localization and Mapping I
Lecture 07: Localization and Mapping ILecture 07: Localization and Mapping I
Lecture 07: Localization and Mapping I
 

Último

GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
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
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processorsdebabhi2
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEarley Information Science
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
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
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 

Último (20)

GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
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
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
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
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 

September 9, Deliberative Algorithms I

  • 1. Multi-Robot Systems CSCI 7000-006 Wednesday, September 9, 2009 NikolausCorrell
  • 2. So far Reactive algorithms, robotic swarms Limited number of internal states Direct coupling between perception and action Threshold-based algorithms are a powerful method for task allocation Coordination Implicit by modifiying the environment Explicit by local communication Propagating directional information are a powerful method for navigation
  • 3. Today Deliberative algorithms Planning vs. reacting? Computational vs. Robotic algorithms
  • 4. Deliberation Computational representation of the problem (model, e.g. map or graph) Reasoning on representation Robot: Sensors to determine world-state Mapping algorithmic solution into action
  • 5. “Why is robotics hard?” (again) Sensors are flaky Internal representation not accurate Planning becomes suboptimal or wrong Actuators are unreliable Mismatch between states in the plan and the world Course question: How do YOU resolve an everyday navigation problem?
  • 6. Making robots more robust Adding sensors (allows cross-validation) But: sensors again unreliable Bayesian approach Maintain probability distribution over belief states and use sensors to update beliefs Redundancy 50% 50% 5% 95%
  • 7. Example: Deliberation and Uncertainty Scenario: visit and circumnavigate every blade at least once Environment unknown Course question Computational representation Algorithm for complete coverage Potential problems?
  • 8. Computational representation Graph Vertices: blades Edges: routes between blades Depth-First-Search “Count blades” Minimal spanning tree Use A* for moving toward nearest unexplored edge
  • 9. From planning to action Sensors: distance sensor/odometer Wall following Detect round and sharp tip Controller Detect waypoint (probabilistic) Launch to neighbor (open-loop) Until blade is hit Problems Wrong waypoint Wheel-slip N. Correll, S. Rutishauser, and A. Martinoli. Comparing Coordination Schemes for Miniature Robotic Swarms: A Case Study in Boundary Coverage of Regular Structures. In The 10th International Symposium on Experimental Robotics (ISER), Rio de Janeiro, 2006. Springer Tracts in Advanced Robotics, volume 38, pages 471-480, 2008
  • 10. Basic Navigation Behaviors 9/20/2007 Nikolaus Correll 10
  • 11. Analysis Complete algorithm becomes probabilistic Starting over when lost Implicit collaboration 10% wheel-slip 50% wheel-slip 6000 experiments in Webots, 10% wheel-slip Time for covering one blade Probability of no navigation error
  • 12. Debate Statement: Deterministic algorithms become probabilistic due to noise What if the sensors and controllers would be more precise? Can you find counter examples? Does planning always make sense? Why wouldn’t it?
  • 13. Adding sensors Localization offers chance to recover Failure can be detected and robot can re-plan Problem: Noise on localization 95% successful detection
  • 14. Algorithm Initialize new cells with p=95% Initialize unexplored neighbors with p=0% Use Dijkstra’s algorithm to move towards cell with lowest likelihood of coverage After n-th visit update cells with posterior CQ: Termination criteria? S. Rutishauser, N. Correll, and A. Martinoli. Collaborative Coverage using a Swarm of Networked Miniature Robots. Robotics & Autonomous Systems, 57(5):517-525, 2009
  • 15. Analysis Additional sensors provide additional confidence But: Solution remains probabilistic This example: expected runtime is a function of inspected confidence
  • 16. Explicit Collaboration Share progress via radio (broadcast) Stitch maps together using global coordinates Update coverage probabilities New Problem: communication failure 16 j i
  • 18. Analysis Communication reliability impacts collaboration efficiency Communication content “deterministic” due to error correction Algorithm: non-optimal collaboration No Comm. Comm. Termination Criterion: 99% coverage
  • 19. Summary Deliberative planning produces superior performance over reactive algorithms Both approaches are probabilistic due to real-world noise Deliberation and communication comes at cost! Find ways to recover / correct errors by adding Sensors redundancy Exchange information to strengthen hypothesises
  • 20. State-of-the Art Example: Multi-Robot Exploration and Mapping Maps generated by laser-scan and odometry Robots drive toward unexplored frontiers Robots actively validate relative localization Relative position of team unknown initially Robots share maps Fox, D. Ko, J. Konolige, K. Limketkai, B. Schulz, D. Stewart, B. Distributed Multi-robot Exploration and Mapping. Proceedings of the IEEE, 94:7:1325-1339.
  • 21. Map Sharing Find best match for other robot’s position given its Map Trajectory Initialize with uniform belief distribution Prune estimates as the robot moves Continue exploration together from thereon Fox, D. Ko, J. Konolige, K. Limketkai, B. Schulz, D. Stewart, B. Distributed Multi-robot Exploration and Mapping. Proceedings of the IEEE, 94:7:1325-1339.
  • 22. Robot Coordination Trade off between exploration and exploitation Move towards unexplored frontiers Validate other robots’ positions
  • 23. Friday No lab More deliberative algorithms: optimal coordination
  • 24. Organization Traveling on Monday, September 14-16 Localization sensor and scanner are late Next week: Building-Week Putting together robots Commissioning laser scanner and localization system

Notas del editor

  1. I will now demonstrate you the modeling methodology using the application that has motivated my PhD thesis work. The scenario is jet turbine inspection, that is releasing a swarm of robots into a piece of machinery for inspecting its inside.I abstracted this task to a 2D environment where robots need to circumnavigate a set of blades, which can be casted as a generic graph coverage problem.I am interested to model a system as a function of its algorithm and its resources using a common method. I therefore implemented a series of algorithms ranging from very simple reactive ones to NP hard deliberative algorithms. I consider two different scenarios, with and without localization and robots with different capabilities. At the top right you see an Alice robot that has been developed at EPFL. The robot fits into a square of 2 by 2 cm and is extremely simple: it has a small microcontroller, watch motors and can communicate up to 3cm using infrared. For running all the algorithms I was interested in, I equipped the robot with two additional modules. A radio module running TinyOS and a 30 by 30 pixel color camera. The camera is actually used for localization and together with the radio, I can transmit images back to a base station.