SlideShare a Scribd company logo
1 of 32
Multi-Robot Systems CSCI 7000-006 Monday, November 16, 2009 NikolausCorrell
Course summary What are multi-robot systems and when to use them Reactive algorithms for multi-robot swarms Deliberative algorithms for multi-robot teams Gradient-based modeling and control Probabilistic modeling and control Optimization Learning (today)
Upcoming Fall break November 30-December 11: project presentations Teach your peers about a specific aspect of multi-robot systems Recall background and theory from the class Present your project and results Final reports due December 18
Presentations Particlefilters Gradient-based approaches Large-scale distributed systems Reactive Swarms Swarm Intelligence Multi-Robot Teams You are giving the lecture this day! Coordinate among yourselves to present common material! We want to recall what we have seen in the course and learn something!
Today Learning in multi-robot systems Genetic algorithms and Particle Swarm Optimization Advantages of GA and PSO in distributed systems
Encode controllers parametrically (e.g.,Braitenberg parameters) into strings (chromosomes) Evaluate with robot test runs Cross-over and mutatechromosomes Repeat until end criterion met Genetic Algorithms phenotype http://en.wikipedia.org/wiki/Genetic_algorithm
Particle Swarm Optimization Controller parameters span search space Instances of controllers are particles in search space Particles fly through search space Direction Velocity Inertia Attraction to positions with best results, both for the individual particle and for neighborhoods Optimization algorithm Evaluate controllers Update particles Continue Fitness Parameter 2 Parameter 1 Current speed Next best solution Neighbors’s best solution Current position Own best solution Swarm Intelligence (The Morgan Kaufmann Series in Artificial Intelligence) by Russell C. Eberhart, Yuhui Shi, and James Kennedy, 2001.
Single robot learning: Example Modular Robots Gait generated by a Central Pattern Generator (CPG) Find parameters for CPGthat maximize forward motion YvanBourquin, Self-Organization of Locomotion in Modular Robots, M.Sc. Thesis, University of Sussex & EPFL
Gait optimization results YvanBourquin, Self-Organization of Locomotion in Modular Robots, M.Sc. Thesis, University of Sussex & EPFL
Parallel Learning withMulti-Agent Optimization Standard technique with multi-agent optimization: evaluate in serial at each iteration Very slow evolution In multi-robot systems, can perform parallel evaluations J. Pugh and A. Martinoli. Multi-Robot Learning with Particle Swarm Optimization. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 441 - 448, 2006.
Parallel Learning withMulti-Agent Optimization Standard technique with multi-agent optimization: evaluate in serial at each iteration Very slow evolution In multi-robot systems, can perform parallel evaluations J. Pugh and A. Martinoli. Multi-Robot Learning with Particle Swarm Optimization. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 441 - 448, 2006.
Parallel Learning withMulti-Agent Optimization Standard technique with multi-agent optimization: evaluate in serial at each iteration Very slow evolution In multi-robot systems, can perform parallel evaluations J. Pugh and A. Martinoli. Multi-Robot Learning with Particle Swarm Optimization. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 441 - 448, 2006.
Parallel Learning withMulti-Agent Optimization Standard technique with multi-agent optimization: evaluate in serial at each iteration Very slow evolution In multi-robot systems, can perform parallel evaluations J. Pugh and A. Martinoli. Multi-Robot Learning with Particle Swarm Optimization. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 441 - 448, 2006.
Example 2: Obstacle Avoidance – Group learning, individual fitness Artificial Neural Network Control Fitness function* rewards speed, straight movement, and avoiding obstacles: ,[object Object],*Floreano, D. and Mondada, F. (1996) Evolution of Homing Navigation in a Real Mobile Robot. IEEE Transactions on Systems, Man, and Cybernetics--Part B: Cybernetics, 26(3), 396-407.
Parallel Learning Results ,[object Object]
 Results averaged over 100 trialsAverage Performance Throughout Evolution Performance of Best Evolved Controllers J. Pugh and A. Martinoli. Multi-Robot Learning with Particle Swarm Optimization. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 441 - 448, 2006. “Best-effort comparison”
Communication-Based Neighborhoods Ring Topology - Standard
Communication-Based Neighborhoods 2-Closest – Model 1
Communication-Based Neighborhoods Radius r (40 cm) – Model 2
Communication-Based Neighborhoods Performance of best controllers after evolution ,[object Object]
Difficult to compare and to design without analytical foundations
Relation between embodiment, learning algorithm parameters, and fitness? Topology Range J. Pugh and A. Martinoli. Multi-Robot Learning with Particle Swarm Optimization. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 441 - 448, 2006.
Varying CommunicationRange - Results Average swarm performance during evolution J. Pugh and A. Martinoli. Multi-Robot Learning with Particle Swarm Optimization. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 441 - 448, 2006.
Example 3: Aggregation – Group learning, group fitness Same neural network setup as in obstacle avoidance Additional capability – sense relative positions of other nearby robots Additional inputs to neural network – center of mass (x,y) of detected robots Fitness function: where robRP(i) is number of robots in range of robot i J. Pugh and A. Martinoli. Multi-Robot Learning with Particle Swarm Optimization. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 441 - 448, 2006.
Group Learning andCredit Assignment - Results Performance of best controllers after evolution
Search Scenario Use team of e-pucks (mobile robot with 7 cm diameter)  Robots must find (within 10 cm) targets in 4 mx 4 marena Robots can sense “intensity”, e.g. loudness of an audio source Once found, targets are instantly moved to new location Search continues indefinitely, though controller parameters may be changed
Example 4: Bacteria-InspiredSearch Algorithm E. coli chemotaxis: Move Check gradient If positive, keep direction If negative, tumble Replicate approach for searching robots Add collaboration – instead of tumble, go towards nearby robot with strongest detection J. Pugh and A. Martinoli. Distributed Adaptation in Multi-Robot Search using Particle Swarm Optimization. In Proceedings of the 10th International Conference on the Simulation of Adaptive Behavior, Lecture Notes in Computer Science, pages 393-402, 2008.
Improved search performance through parameter optimization Adaptable parameters: STEP_SIZE Bacteria-InspiredSearch Algorithm
Improved search performance through parameter optimization Adaptable parameters: STEP_SIZE RL_RANGE Bacteria-InspiredSearch Algorithm
Improved search performance through parameter optimization Adaptable parameters: STEP_SIZE RL_RANGE CW_LIMIT Bacteria-InspiredSearch Algorithm
Improved search performance through parameter optimization Adaptable parameters: STEP_SIZE RL_RANGE CW_LIMIT CCW_LIMIT Bacteria-InspiredSearch Algorithm
Group Performance: number of targets found (within 10 cm) in evaluation span Individual Fitness: average detected power intensity – used for controller evaluation Detected intensity for robot iof all targets j: Distance detections inaccurate due to background noise Optimal parameter set affected by number of targets, power of targets Search Experiments

More Related Content

Viewers also liked

Viewers also liked (9)

October 5, Probabilistic Modeling II
October 5, Probabilistic Modeling IIOctober 5, Probabilistic Modeling II
October 5, Probabilistic Modeling II
 
Seminar
SeminarSeminar
Seminar
 
Multi Robot Swarm Systems
Multi Robot Swarm SystemsMulti Robot Swarm Systems
Multi Robot Swarm Systems
 
Ai swarm intelligence
Ai   swarm intelligenceAi   swarm intelligence
Ai swarm intelligence
 
SWARM ROBOTICS25
SWARM ROBOTICS25SWARM ROBOTICS25
SWARM ROBOTICS25
 
Seminar
SeminarSeminar
Seminar
 
Swarm intelligence
Swarm intelligenceSwarm intelligence
Swarm intelligence
 
Swarm intelligence
Swarm intelligenceSwarm intelligence
Swarm intelligence
 
Swarm Intelligence - An Introduction
Swarm Intelligence - An IntroductionSwarm Intelligence - An Introduction
Swarm Intelligence - An Introduction
 

Similar to Multi-Robot Learning with Genetic Algorithms and Particle Swarm Optimization

nature inspired algorithms
nature inspired algorithmsnature inspired algorithms
nature inspired algorithmsGaurav Goel
 
Kernel based swarm optimization for renewable energy application
Kernel based swarm optimization  for renewable energy applicationKernel based swarm optimization  for renewable energy application
Kernel based swarm optimization for renewable energy applicationAboul Ella Hassanien
 
PSO APPLIED TO DESIGN OPTIMAL PD CONTROL FOR A UNICYCLE MOBILE ROBOT
PSO APPLIED TO DESIGN OPTIMAL PD CONTROL FOR A UNICYCLE MOBILE ROBOTPSO APPLIED TO DESIGN OPTIMAL PD CONTROL FOR A UNICYCLE MOBILE ROBOT
PSO APPLIED TO DESIGN OPTIMAL PD CONTROL FOR A UNICYCLE MOBILE ROBOTJaresJournal
 
Particle Swarm Optimization: The Algorithm and Its Applications
Particle Swarm Optimization: The Algorithm and Its ApplicationsParticle Swarm Optimization: The Algorithm and Its Applications
Particle Swarm Optimization: The Algorithm and Its Applicationsadil raja
 
IRJET- PSO based PID Controller for Bidirectional Inductive Power Transfer Sy...
IRJET- PSO based PID Controller for Bidirectional Inductive Power Transfer Sy...IRJET- PSO based PID Controller for Bidirectional Inductive Power Transfer Sy...
IRJET- PSO based PID Controller for Bidirectional Inductive Power Transfer Sy...IRJET Journal
 
Ontology based clustering algorithms
Ontology based clustering algorithmsOntology based clustering algorithms
Ontology based clustering algorithmsIkutwa
 
An innovative approach for feature selection based on chicken swarm optimization
An innovative approach for feature selection based on chicken swarm optimizationAn innovative approach for feature selection based on chicken swarm optimization
An innovative approach for feature selection based on chicken swarm optimizationAboul Ella Hassanien
 
Filter-Wrapper Approach to Feature Selection Using PSO-GA for Arabic Document...
Filter-Wrapper Approach to Feature Selection Using PSO-GA for Arabic Document...Filter-Wrapper Approach to Feature Selection Using PSO-GA for Arabic Document...
Filter-Wrapper Approach to Feature Selection Using PSO-GA for Arabic Document...iosrjce
 
Feature Extraction for Large-Scale Text Collections
Feature Extraction for Large-Scale Text CollectionsFeature Extraction for Large-Scale Text Collections
Feature Extraction for Large-Scale Text CollectionsSease
 
Bat algorithm and applications
Bat algorithm and applicationsBat algorithm and applications
Bat algorithm and applicationsMd.Al-imran Roton
 
Learning of robot navigation tasks by
Learning of robot navigation tasks byLearning of robot navigation tasks by
Learning of robot navigation tasks bycsandit
 
LEARNING OF ROBOT NAVIGATION TASKS BY PROBABILISTIC NEURAL NETWORK
LEARNING OF ROBOT NAVIGATION TASKS BY PROBABILISTIC NEURAL NETWORKLEARNING OF ROBOT NAVIGATION TASKS BY PROBABILISTIC NEURAL NETWORK
LEARNING OF ROBOT NAVIGATION TASKS BY PROBABILISTIC NEURAL NETWORKcsandit
 
Artificial Intelligence in Robot Path Planning
Artificial Intelligence in Robot Path PlanningArtificial Intelligence in Robot Path Planning
Artificial Intelligence in Robot Path Planningiosrjce
 
Evolutionary Design of Swarms (SSCI 2014)
Evolutionary Design of Swarms (SSCI 2014)Evolutionary Design of Swarms (SSCI 2014)
Evolutionary Design of Swarms (SSCI 2014)Benjamin Bengfort
 

Similar to Multi-Robot Learning with Genetic Algorithms and Particle Swarm Optimization (20)

nature inspired algorithms
nature inspired algorithmsnature inspired algorithms
nature inspired algorithms
 
Kernel based swarm optimization for renewable energy application
Kernel based swarm optimization  for renewable energy applicationKernel based swarm optimization  for renewable energy application
Kernel based swarm optimization for renewable energy application
 
PSO APPLIED TO DESIGN OPTIMAL PD CONTROL FOR A UNICYCLE MOBILE ROBOT
PSO APPLIED TO DESIGN OPTIMAL PD CONTROL FOR A UNICYCLE MOBILE ROBOTPSO APPLIED TO DESIGN OPTIMAL PD CONTROL FOR A UNICYCLE MOBILE ROBOT
PSO APPLIED TO DESIGN OPTIMAL PD CONTROL FOR A UNICYCLE MOBILE ROBOT
 
October 26, Optimization
October 26, OptimizationOctober 26, Optimization
October 26, Optimization
 
Particle Swarm Optimization: The Algorithm and Its Applications
Particle Swarm Optimization: The Algorithm and Its ApplicationsParticle Swarm Optimization: The Algorithm and Its Applications
Particle Swarm Optimization: The Algorithm and Its Applications
 
September 2, Reactive Algorithms II
September 2, Reactive Algorithms IISeptember 2, Reactive Algorithms II
September 2, Reactive Algorithms II
 
IRJET- PSO based PID Controller for Bidirectional Inductive Power Transfer Sy...
IRJET- PSO based PID Controller for Bidirectional Inductive Power Transfer Sy...IRJET- PSO based PID Controller for Bidirectional Inductive Power Transfer Sy...
IRJET- PSO based PID Controller for Bidirectional Inductive Power Transfer Sy...
 
Ontology based clustering algorithms
Ontology based clustering algorithmsOntology based clustering algorithms
Ontology based clustering algorithms
 
An innovative approach for feature selection based on chicken swarm optimization
An innovative approach for feature selection based on chicken swarm optimizationAn innovative approach for feature selection based on chicken swarm optimization
An innovative approach for feature selection based on chicken swarm optimization
 
G017664551
G017664551G017664551
G017664551
 
Filter-Wrapper Approach to Feature Selection Using PSO-GA for Arabic Document...
Filter-Wrapper Approach to Feature Selection Using PSO-GA for Arabic Document...Filter-Wrapper Approach to Feature Selection Using PSO-GA for Arabic Document...
Filter-Wrapper Approach to Feature Selection Using PSO-GA for Arabic Document...
 
Swarm intel
Swarm intelSwarm intel
Swarm intel
 
Feature Extraction for Large-Scale Text Collections
Feature Extraction for Large-Scale Text CollectionsFeature Extraction for Large-Scale Text Collections
Feature Extraction for Large-Scale Text Collections
 
Bat algorithm and applications
Bat algorithm and applicationsBat algorithm and applications
Bat algorithm and applications
 
Learning of robot navigation tasks by
Learning of robot navigation tasks byLearning of robot navigation tasks by
Learning of robot navigation tasks by
 
LEARNING OF ROBOT NAVIGATION TASKS BY PROBABILISTIC NEURAL NETWORK
LEARNING OF ROBOT NAVIGATION TASKS BY PROBABILISTIC NEURAL NETWORKLEARNING OF ROBOT NAVIGATION TASKS BY PROBABILISTIC NEURAL NETWORK
LEARNING OF ROBOT NAVIGATION TASKS BY PROBABILISTIC NEURAL NETWORK
 
Artificial Intelligence in Robot Path Planning
Artificial Intelligence in Robot Path PlanningArtificial Intelligence in Robot Path Planning
Artificial Intelligence in Robot Path Planning
 
T01732115119
T01732115119T01732115119
T01732115119
 
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
 
Evolutionary Design of Swarms (SSCI 2014)
Evolutionary Design of Swarms (SSCI 2014)Evolutionary Design of Swarms (SSCI 2014)
Evolutionary Design of Swarms (SSCI 2014)
 

More from 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
 

More from 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
 

Recently uploaded

Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxOnBoard
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphNeo4j
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
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
 
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
 
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
 
Snow Chain-Integrated Tire for a Safe Drive on Winter Roads
Snow Chain-Integrated Tire for a Safe Drive on Winter RoadsSnow Chain-Integrated Tire for a Safe Drive on Winter Roads
Snow Chain-Integrated Tire for a Safe Drive on Winter RoadsHyundai Motor Group
 
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
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhisoniya singh
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxMalak Abu Hammad
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
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
 
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
 
How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?XfilesPro
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024Scott Keck-Warren
 
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
 
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
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 

Recently uploaded (20)

Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptx
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
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
 
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...
 
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
 
Snow Chain-Integrated Tire for a Safe Drive on Winter Roads
Snow Chain-Integrated Tire for a Safe Drive on Winter RoadsSnow Chain-Integrated Tire for a Safe Drive on Winter Roads
Snow Chain-Integrated Tire for a Safe Drive on Winter Roads
 
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
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
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
 
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
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024
 
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
 
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
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 

Multi-Robot Learning with Genetic Algorithms and Particle Swarm Optimization

  • 1. Multi-Robot Systems CSCI 7000-006 Monday, November 16, 2009 NikolausCorrell
  • 2. Course summary What are multi-robot systems and when to use them Reactive algorithms for multi-robot swarms Deliberative algorithms for multi-robot teams Gradient-based modeling and control Probabilistic modeling and control Optimization Learning (today)
  • 3. Upcoming Fall break November 30-December 11: project presentations Teach your peers about a specific aspect of multi-robot systems Recall background and theory from the class Present your project and results Final reports due December 18
  • 4. Presentations Particlefilters Gradient-based approaches Large-scale distributed systems Reactive Swarms Swarm Intelligence Multi-Robot Teams You are giving the lecture this day! Coordinate among yourselves to present common material! We want to recall what we have seen in the course and learn something!
  • 5. Today Learning in multi-robot systems Genetic algorithms and Particle Swarm Optimization Advantages of GA and PSO in distributed systems
  • 6. Encode controllers parametrically (e.g.,Braitenberg parameters) into strings (chromosomes) Evaluate with robot test runs Cross-over and mutatechromosomes Repeat until end criterion met Genetic Algorithms phenotype http://en.wikipedia.org/wiki/Genetic_algorithm
  • 7. Particle Swarm Optimization Controller parameters span search space Instances of controllers are particles in search space Particles fly through search space Direction Velocity Inertia Attraction to positions with best results, both for the individual particle and for neighborhoods Optimization algorithm Evaluate controllers Update particles Continue Fitness Parameter 2 Parameter 1 Current speed Next best solution Neighbors’s best solution Current position Own best solution Swarm Intelligence (The Morgan Kaufmann Series in Artificial Intelligence) by Russell C. Eberhart, Yuhui Shi, and James Kennedy, 2001.
  • 8. Single robot learning: Example Modular Robots Gait generated by a Central Pattern Generator (CPG) Find parameters for CPGthat maximize forward motion YvanBourquin, Self-Organization of Locomotion in Modular Robots, M.Sc. Thesis, University of Sussex & EPFL
  • 9. Gait optimization results YvanBourquin, Self-Organization of Locomotion in Modular Robots, M.Sc. Thesis, University of Sussex & EPFL
  • 10. Parallel Learning withMulti-Agent Optimization Standard technique with multi-agent optimization: evaluate in serial at each iteration Very slow evolution In multi-robot systems, can perform parallel evaluations J. Pugh and A. Martinoli. Multi-Robot Learning with Particle Swarm Optimization. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 441 - 448, 2006.
  • 11. Parallel Learning withMulti-Agent Optimization Standard technique with multi-agent optimization: evaluate in serial at each iteration Very slow evolution In multi-robot systems, can perform parallel evaluations J. Pugh and A. Martinoli. Multi-Robot Learning with Particle Swarm Optimization. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 441 - 448, 2006.
  • 12. Parallel Learning withMulti-Agent Optimization Standard technique with multi-agent optimization: evaluate in serial at each iteration Very slow evolution In multi-robot systems, can perform parallel evaluations J. Pugh and A. Martinoli. Multi-Robot Learning with Particle Swarm Optimization. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 441 - 448, 2006.
  • 13. Parallel Learning withMulti-Agent Optimization Standard technique with multi-agent optimization: evaluate in serial at each iteration Very slow evolution In multi-robot systems, can perform parallel evaluations J. Pugh and A. Martinoli. Multi-Robot Learning with Particle Swarm Optimization. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 441 - 448, 2006.
  • 14.
  • 15.
  • 16. Results averaged over 100 trialsAverage Performance Throughout Evolution Performance of Best Evolved Controllers J. Pugh and A. Martinoli. Multi-Robot Learning with Particle Swarm Optimization. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 441 - 448, 2006. “Best-effort comparison”
  • 20.
  • 21. Difficult to compare and to design without analytical foundations
  • 22. Relation between embodiment, learning algorithm parameters, and fitness? Topology Range J. Pugh and A. Martinoli. Multi-Robot Learning with Particle Swarm Optimization. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 441 - 448, 2006.
  • 23. Varying CommunicationRange - Results Average swarm performance during evolution J. Pugh and A. Martinoli. Multi-Robot Learning with Particle Swarm Optimization. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 441 - 448, 2006.
  • 24. Example 3: Aggregation – Group learning, group fitness Same neural network setup as in obstacle avoidance Additional capability – sense relative positions of other nearby robots Additional inputs to neural network – center of mass (x,y) of detected robots Fitness function: where robRP(i) is number of robots in range of robot i J. Pugh and A. Martinoli. Multi-Robot Learning with Particle Swarm Optimization. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 441 - 448, 2006.
  • 25. Group Learning andCredit Assignment - Results Performance of best controllers after evolution
  • 26. Search Scenario Use team of e-pucks (mobile robot with 7 cm diameter) Robots must find (within 10 cm) targets in 4 mx 4 marena Robots can sense “intensity”, e.g. loudness of an audio source Once found, targets are instantly moved to new location Search continues indefinitely, though controller parameters may be changed
  • 27. Example 4: Bacteria-InspiredSearch Algorithm E. coli chemotaxis: Move Check gradient If positive, keep direction If negative, tumble Replicate approach for searching robots Add collaboration – instead of tumble, go towards nearby robot with strongest detection J. Pugh and A. Martinoli. Distributed Adaptation in Multi-Robot Search using Particle Swarm Optimization. In Proceedings of the 10th International Conference on the Simulation of Adaptive Behavior, Lecture Notes in Computer Science, pages 393-402, 2008.
  • 28. Improved search performance through parameter optimization Adaptable parameters: STEP_SIZE Bacteria-InspiredSearch Algorithm
  • 29. Improved search performance through parameter optimization Adaptable parameters: STEP_SIZE RL_RANGE Bacteria-InspiredSearch Algorithm
  • 30. Improved search performance through parameter optimization Adaptable parameters: STEP_SIZE RL_RANGE CW_LIMIT Bacteria-InspiredSearch Algorithm
  • 31. Improved search performance through parameter optimization Adaptable parameters: STEP_SIZE RL_RANGE CW_LIMIT CCW_LIMIT Bacteria-InspiredSearch Algorithm
  • 32. Group Performance: number of targets found (within 10 cm) in evaluation span Individual Fitness: average detected power intensity – used for controller evaluation Detected intensity for robot iof all targets j: Distance detections inaccurate due to background noise Optimal parameter set affected by number of targets, power of targets Search Experiments
  • 33.
  • 34. Compare small, medium, and large PSO neighborhoods
  • 35. Results averaged over 250 trialsAverage Individual Fitness Average Group Performance J. Pugh and A. Martinoli. Distributed Adaptation in Multi-Robot Search using Particle Swarm Optimization. In Proceedings of the 10th International Conference on the Simulation of Adaptive Behavior, Lecture Notes in Computer Science, pages 393-402, 2008.
  • 36. Simulation vs. Real robots Number of performance evaluations usually very high -> infeasible on real robots Simulation is an abstraction Might not model noise accurately Might not model inter-robot variations accurately Solution: multi-level modeling 90% of the evaluations using model/simulation 10% using real hardware
  • 37. Summary Population-based optimization algorithms are well suited for learning in multi-robot systems (parallelization) Main difficulty: selection of an appropriate fitness function GA and PSO are heuristics, are not guaranteed to perform, and are highly susceptive to parameter choice and algorithmic variations This is in contrast to analytical optimization