Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Swarm robotics

Selected topics in Mechatronics Engineering
by

mostafa arafa

on 6 October 2013

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Swarm robotics

Swarm Robotics Definition Definition Swarm Robotics Robot s Number of LARGE Collective Behavior Main Characteristics Cost Decentralization Self-Organization Robustness Flexibility Scalability Autonomous e.g. M-Tran Robot Homogeneity Communication Objective Introduce "SWARM ROBOTICS" as a field of research with an application and methodologies to researchers interested in such a field. Contents Definition Characteristics Design Methods Collective Behaviors Case Study Design Methods Behavior Based Design Automatic Design Behavior-Based Design A trial and error process. Bottom-up process Behavior Tune iteratively adjust and PFSM
(Probabilistic finite state machine) Virtual Physics-based design Decision Based on: Sensor Inputs Internal Memory with transition probability between states. Virtual Attraction/Repulsion Virtual Repulsion Automatic Design Generation of Behaviors -> without any intervention from the developer. Reinforcement Learning Evolutionary Robotics Collective Behaviors Navigation behaviors Spatially organizing behaviors Collective decision-making behaviors Spatially organizing behaviors To organize robots in space. Aggregation Aggregation allows a swarm of robots to get sufficiently close one another so that they can interact. •Aggregation is to group all the robots of a swarm in a region of the environment. Inspired by: Aggregation is usually approached in two ways: probabilistic finite state machines (PFSMs) or artificial evolution. Design Method: Pattern Formation •Robots usually need to keep specific distances between each other in order to create a desired pattern. Inspired by: •Virtual physics-based design uses virtual forces to coordinate the movements of robots. Design Method: Molecules
Crystal Chain formation •In the chain formation behavior, robots have to position themselves in order to connect two points. The chain that they form can then be used as a guide for navigation or for surveillance. Inspired by: Foraging Ants Self-assembly Self-assembly is the process by which robots physically connect to each other. Physical Connection Morphogenesis The process that leads a swarm of robots to self-assemble following a particular pattern, and can be used by the swarm to self-assemble into a structure that is particularly appropriate for a given task. Behaviors that focus on how to organize and coordinate the movements of a swarm of robots. Navigational Behaviors Collective decision-making behaviors •Behaviors that focus on letting a group of robots agree on a common decision or allocate among different parallel tasks, or it deals with how robots influence each other when making choices Consensus Agreement Vs. Specialized task allocation Allows a swarm of robots to reach consensus on one choice among different alternatives. The choice is usually the one that maximize the performance of the system. Source of Inspiration Foraging
Bees •Task allocation is a collective behavior in which robots distribute themselves over different tasks. The goal is to maximize the performance of the system by letting the robots dynamically choose which task to perform. Source of Inspiration Bees' Colony Case Study Problem Statement The specific objective is to address the task of swarm navigation through a field of obstacles to get to a goal location while maintaining a cohesive formation under difficult conditions. Mythology Behavior based design method.
Inspired from physics and controlled using the Lennard-Jones force law.
The behavior of the swarm can be improved via offline optimization of the Lennard-Jones force law parameters using GA. Swarm offline learning GA Technique is used.
The goal is to have the robots learn the optimal parameter settings for the force laws; thus they can successfully maintain a formation while both avoiding obstacles and getting to a goal location in a complex environment. Fitness Function
•Avoid obstacles
•Maintain Formation
•Reach a goal Results "Genetic Algorithm" Individual 1.Aggregation
2.chain formation
3.and task allocation
Applications Virtual Attraction 1.Pattern Formation
2.Collective exploration
3.Cordinated motion
Applications Learn Trial & Error Individual Action Collective Behavior Initial Random Behaviors Behavior Behavior Behavior Behavior Behavior Behavior Behavior Behavior Behavior Behavior Fitness Function Experiment Behavior Experiment Experiment Experiment Selection Generate New Behaviors Score Local Communication LENNARD-JONES FORCE LAW Random Search Space
Full transcript