1 / 10

An Agent-Oriented Software Architecture for Teams of Robots.

An Agent-Oriented Software Architecture for Teams of Robots. RESCUE PROJECT João Frazão. Context. A team of heterogeneous robots Rescue and Search Outdoor environments Multidisciplinary project that joins the following research groups: Intelligent Systems Lab Mobile Robotics Lab VisLab.

dgallegos
Download Presentation

An Agent-Oriented Software Architecture for Teams of Robots.

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. An Agent-Oriented Software Architecture for Teams of Robots. RESCUE PROJECT João Frazão João Frazão

  2. Context • A team of heterogeneous robots • Rescue and Search • Outdoor environments • Multidisciplinary project that joins the following research groups: • Intelligent Systems Lab • Mobile Robotics Lab • VisLab João Frazão

  3. Agent Hierarchy João Frazão

  4. Architecture Elements • Agents • Live objects • Memory • Hierarchy • Blackboard • Standard Communication • Ports • Well defined functions João Frazão

  5. Agent Types The supported agents are: • Concurrent Agent • Planning Agent • Agent guided by a state machine • Agent guided by table • Control loop • Team Agent • Robot Agent • Cooperative Agent • Custom Agents • Sensor Agent • Actuator Agent • Sensor Fusion Agents João Frazão

  6. Example A robot with 3 agents: • Mapping • Position • Navigation Blackboard João Frazão

  7. Example • Navigation - Further decomposing: • Wander • Path Follow • Blimp Follow • How to assemble? Composition • FSM • Planning • Custom João Frazão

  8. Execution Modes • Control • Design • Calibration • Supervisory Control and monitoring • Data logging and Debug João Frazão

  9. System João Frazão

  10. Conclusions • Distributed system for heterogeneous robots: • Easier to manage the team • Easier to handle the robots • Easier to test • Real time performance – parallel processing, event driven, performance libraries • Easier to develop - Agent-Oriented João Frazão

More Related