1 / 19

Temporal Logic Robot Mission Planning for Slow and Fast Actions

Temporal Logic Robot Mission Planning for Slow and Fast Actions. Vasu Raman Cameron Finucane Hadas Kress- Gazit Cornell University. High-Level Tasks. Images: http://www.popsci.com/files/imagecache/article_image_large/articles/ beerbot.jpg

nathan
Download Presentation

Temporal Logic Robot Mission Planning for Slow and Fast Actions

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. Temporal Logic Robot Mission Planning for Slow and Fast Actions Vasu Raman Cameron Finucane Hadas Kress-Gazit Cornell University

  2. High-Level Tasks Images: http://www.popsci.com/files/imagecache/article_image_large/articles/beerbot.jpg http://www.news.cornell.edu/stories/Nov07/DarpaCar.jpg http://www.technovelgy.com/graphics/content08/toyota-robot-maid-laundry.jpg

  3. Usual Approach Hard-code high-level aspects Path-planning during execution

  4. Usual Approach Hard-code high-level aspects Path-planning during execution Recent Approaches – formal methods Create abstraction ofproblem Synthesize correct discrete solution Continuously implement discrete solution

  5. LTLMoP Toolkit Overview Specification FSA Synthesizable Synthesis Unsynthesizable Specification Analysis Hybrid Controller Physical Robot Simulation

  6. LTLMoP Toolkit Overview Specification FSA Synthesizable Synthesis Unsynthesizable Specification Analysis Hybrid Controller Physical Robot Simulation

  7. Example: fast camera, slow motion

  8. Example: fast camera, slow motion

  9. Continuous Execution – Camera turns on – Motion from r1 to r2

  10. Original Approach: actions after motion • Motion from r1 to r2 Camera turns on

  11. Why is this undesirable? • - Delayed reactivity • - Potentially unsafe states

  12. Alternative Approach:simultaneous actions • Motion from r1 to r2 Camera turns on

  13. Why is this undesirable? • - Potentially unsafe executions

  14. What we really want: Goal: SAFE • - Automatically check for safe continuous • execution during synthesis

  15. Synthesis for Fast/Slow Actions Specification FSA Synthesizable Synthesis Unsynthesizable Specification Analysis Hybrid Controller Physical Robot Simulation

  16. Synthesis for Fast/Slow Actions “Slow” = motion, “Fast” = everything else Implicit intermediate state

  17. Synthesis for Fast/Slow Actions Implicit intermediate states are safe! Specification FSA Synthesizable Synthesis Unsynthesizable Specification Analysis Hybrid Controller Physical Robot Simulation

  18. Future Work • - More than two relative action completion durations • - Explaining unsynthesizability arising from different • controller execution durations Robot actions (in order of duration): – Turning on the camera – Waving hand – Motion between regions

  19. Temporal Logic Robot Mission Planning for Slow and Fast Actions Vasu Raman (vraman@cs.cornell.edu) Cameron Finucane (cpf37@cornell.edu) Hadas Kress-Gazit (hadaskg@cornell.edu) Cornell University LTLMoP: http://ltlmop.github.com/ (GPL)

More Related