1 / 15

MARS 2020 Kick-Off Meeting 13 November 2002 Georgia Tech

Explore Tucker Balch's research at Georgia Tech focusing on communication-sensitive behaviors, mission tools, and planning for robot teams. Learn about infrastructure building, 3D simulations, and metrics assessment for navigation tasks.

yut
Download Presentation

MARS 2020 Kick-Off Meeting 13 November 2002 Georgia Tech

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. MARS 2020 Kick-Off Meeting13 November 2002 Georgia Tech

  2. Personnel • Faculty • Prof. Ronald Arkin • Prof. Tucker Balch • Dr. Robert Burridge • Students • Keith O’Hara • Matt Powers • Patrick Ulam • Alan Wagner Tucker Balch Georgia Institute of Technology

  3. Georgia Tech’s Research Tasks • Employ information about the network (BBN) as a sensor for communication sensitive behaviors • Develop and assess: • Communication sensitive behaviors • Communication sensitive mission specification tools • Communication sensitive planning (a la Payton’s internalized plans) Tucker Balch Georgia Institute of Technology

  4. Current Focus • Infrastructure building (MissionLab) • Addition of 3-dimensional simulation and behaviors. • Visualization tools. • Integration of BBN communications models. • Support for heterogeneous teams. • Methodologies • Metrics • Some initial experiments Tucker Balch Georgia Institute of Technology

  5. Some Initial Results… • Task for a robot team: • Navigate to a goal location while maintaining fully connected comm network. • Environment: • 200 x 200 meter arena. • Scattered, comm-blocking obstacles. • Approach: • Integrate preserve-comm motor schema with other navigational schemas. Tucker Balch Georgia Institute of Technology

  6. Navigation without Preserve-Comm Tucker Balch Georgia Institute of Technology

  7. Navigation with Preserve-Comm Tucker Balch Georgia Institute of Technology

  8. Scenario #1 • 1 Goal • 4 Robots spaced by 15m • 200m x 200m arena • 15% Obstacle coverage • 20 random worlds Tucker Balch Georgia Institute of Technology

  9. Scenario #2 • 4 Goals • Visited in order • 4 Robots spaced by15m • 200m x 200m arena • 15% Obstacle coverage • 20 random worlds Tucker Balch Georgia Institute of Technology

  10. Metrics to Assess Performance • Time Until Completion • Length of experiment. • One Network • Percentage of time spent as one network. • Full Network • Percentage of time spent as a fully connected network. • Loners • Percentage of time where there was at least one unconnected node. Tucker Balch Georgia Institute of Technology

  11. One Network Tucker Balch Georgia Institute of Technology

  12. Full Network Tucker Balch Georgia Institute of Technology

  13. Loners Tucker Balch Georgia Institute of Technology

  14. Time Until Completion Tucker Balch Georgia Institute of Technology

  15. Next Steps • Continue: • Infrastructure building. • Continued integration of BBN communications models. • Development and assessment of comm-sensitive behaviors. • Begin • Integration with UPenn and USC vehicles. • Integration of plans as resources. Tucker Balch Georgia Institute of Technology

More Related