Page 1 of 5 123 ... LastLast
Results 1 to 10 of 44

Thread: Miscellaneous

  1. #1

    Miscellaneous



    Artificial Intelligence in Swarms

    Published on Mar 29, 2012

    MY APOLOGIES FOR THE QUALITY OF THE RECORDING. My microphone's very bad quality and didn't record my narration loud enough. Here's the dialogue in case you can't hear...

    This is a leaf cutter ant. Alone, it cannot build a home for itself, sustain itself, nor does it even have reason to live. However, if we group these ants together, they become much more useful and much more efficient. In numbers, they're able to dig a network of organized tunnels while providing plentiful food for their own colony.
    Now "How may this apply to an artificial intelligence project?", you might ask.
    Since the early 1990s, software engineers have been interested in the effectiveness of ant colonies. The ants' ability to cooperate among hundreds (if not thousands) of other ants in the same colony surely make it an interesting topic of study.
    In 1992, a man by the name of Marco Dorigo (along with other software engineers) discovered that he could develop an algorithm to find solutions to a problem by "laying down pheromones in a simulated ant environment". The algorithm turned out to be very successful, especially in logistics.
    Named the ACO (short for Ant Colony Optimisation), it also proved to be very useful when mapping out delivery routes. Today, several companies use the algorithm to route complicated deliveries for maximum efficiency. The ACO takes only 15 minutes to plan a delivery route for 1,200 trucks.
    So as we can see, awareness of our environment continues to inspire us; even in the digital age.

  2. #2


    Core Magazine @ Gadget Show 2013 [Swarm Robots]

    Published on Aug 12, 2014

    [IEEE CSS Video Clip Contest 2014 Submission]
    This video highlights the work on multi-agent robotics at the GRITSLab at the Georgia Institute of Technology. By drawing inspiration from the world around us, different ways of interacting with the robots are discussed, with control theory playing a key role for making the human-swarm interactions happen.

  3. #3


    Robot Swarm - University of Sheffield

    Published on Mar 28, 2013

    Head of the Natural Robotics Lab, Dr Roderich Gross, demonstrates artificial intelligence and swarm robotics

  4. #4


    Control-Theoretic Swarm Joysticks

    Published on Aug 12, 2014

    [IEEE CSS Video Clip Contest 2014 Submission]
    This video highlights the work on multi-agent robotics at the GRITSLab at the Georgia Institute of Technology. By drawing inspiration from the world around us, different ways of interacting with the robots are discussed, with control theory playing a key role for making the human-swarm interactions happen.

  5. #5


    Group genius: Why fish are smarter in swarms

    Published on Feb 4, 2014

    When animals swarm they exhibit a complex collective intelligence that could help us build robots, heal wounds and understand the brain
    Read more:

    "Mind meld: The genius of swarm thinking"
    When animals swarm they exhibit a complex collective intelligence that could help us build robots, heal wounds and understand the brain

    January 29, 2014

  6. #6


    MakerSwarm Robot Hive
    September 26, 2013

    This video shows an example of wiring up a Robot Hive member to the swarm. Controlling servos and alpha numeric displays is shown, as is getting a button press event from the hive.

  7. #7


    Swarm robots cooperate with AR drone

    Published on Oct 23, 2012

    "Spatially Targeted Communication and Self-Assembly," by Nithin Mathews, Anders Lyhne Christensen, Rehan O'Grady, and Marco Dorigo, from Universite Libre de Bruxelles and Instituto Universitario de Lisboa, was presented at IROS 2012 in Vilamoura, Portugal.

  8. #8


    ChIRP Box Pushing Demo

    ChIRP robots performing a simple box pushing task, inspired by foraging ants. The objective of the experiment is to have a swarm of robots collectively push a box without using any communication.
    The box is emitting IR-light that the robots can detect and therefore distinguish the box from other obstacles. It is too heavy for a single robot to push alone, meaning that the robots need to cooperate in order to push it. Each robot only knows that other robots and a box may be present, but has no notion of where they can be situated in the environment. Moreover no direct communication is allowed between the robots. The robots have to search for the box, and at the same time avoid other robots and obstacles they may encounter.
    If the box is detected, the robot starts pushing for a predefined time. This time depends on how many neighbouring robots are assumed to be pushing the box. If a robot detects that it cannot move the box, it tries to reposition to another side of the box. Multiple robots pushing on the same side are thus more inclined to continue pushing instead of reposition to another side, and this will eventually converge enough robots pushing on the same side of the box, resulting in a force sufficient to move the box.
    chirp.idi.ntnu.no

  9. #9


    Vito Trianni - Swarm Cognition, from natural to artificial systems (and back)

    Abstract: The seminar presents an approach to the study of cognition in collective, swarm-like systems (referred to as the "swarm cognition" approach).
    This approach has two main objectives: on the one hand, the theoretical understanding of the mechanisms that support cognitive processing and behavioural optimality in animal swarms; on the other hand, the definition of an engineering methodology that provides formal methods and tools for the design of cognitive capabilities in distributed multi-robot systems. These two objectives are deeply intertwined. The theoretical understanding will support the definition of a suitable engineering methodology for cognitive systems through the identification of the basic mechanisms used in cognitive processing, which must be translated into formal methods and guidelines for engineering artificial systems (e.g., the interactions observed between bees during nest site selection can be distilled into design patterns leading to an optimal decision making process). Similarly, the requirements for a suitable engineering methodology can support the identification of general mechanisms used in cognitive processes (e.g., the need to provide robustness to an engineered system could point to more detailed models which could be tested against the biological system). I will present the studies of biological systems that constitute the background of the swarm cognition approach, and discuss the work-in-progress for the definition of an engineering methodology for distributed cognitive systems.

  10. #10
    TERMES Project, Self-organizing Systems Research Group, Harvard University, Cambridge, Massachusetts, USA

Page 1 of 5 123 ... LastLast

Социальные закладки

Социальные закладки

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •