1 / 13

Stanley: The Robot that Won the DARPA Grand Challenge

Stanley: The Robot that Won the DARPA Grand Challenge. Mark Holak. DARPA: http://www.darpa.mil/ Defense Advanced Research Projects Agency Created in 1958 as a response to the launch of Sputnik Early work focused on missile defense

zuwena
Download Presentation

Stanley: The Robot that Won the DARPA Grand Challenge

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. Stanley: The Robot that Won the DARPA Grand Challenge Mark Holak

  2. DARPA: http://www.darpa.mil/ • Defense Advanced Research Projects Agency • Created in 1958 as a response to the launch of Sputnik • Early work focused on missile defense • 1972 Gave birth to early forms of the internet (ARPANET) • 1976-81 DARPA technologies dominated air, land, sea and space • 1980 started focusing on information processing • DARPA’s mission: “To prevent technological surprise for us and to create technological surprise for our adversaries.“ • Key Creations • The Internet • Stealth Fighters • M16 Assault Riffle • Future: By 2015, 1/3 of operational ground combat vehicles will be unmanned • Supply • Surveillance • Reconnaissance • Targeting • Countermine

  3. The Car Volkswagen Touareg http://www.youtube.com/watch?v=PcfVaiqsFFs

  4. The Car Volkswagen Touareg The “senses” • Sight: Five laser rangefinders; monocular and stereo video camera; radar for long range sight • Position: GPS sensor with 20 cm resolution for pose estimation; measurements of wheel speed for pose estimation • Balance: a 6DOF inertial measurement unit; GPS compass generates 2DOF balance information from two separate GPS antennas

  5. RDDF • Consists of 5 attributes: • WP Number • WP Latitude • WP Longitude • Lateral Boundary • Speed Limit

  6. 3D point cloud acquired by the moving vehicle. The scan data is integrated into point clouds using an inertially guided system for determining the location and orientation of the sensor

  7. Stanley’s Vision http://www.youtube.com/watch?v=FLi_IQgCxbo&feature=related

  8. Sebastian Stanley • Stanley speed has three states: • Maintain the speed limit defined in the RDDF • Reduce speed for obstacles and unstable terrain • Accelerate to speed limit

  9. Field Potentials

  10. Acknowledgments http://robots.stanford.edu/talks/stanley/http://www.darpa.mil/mission.html http://cs.stanford.edu/group/roadrunner//old/presskit/about_stanley.pdf http://robots.stanford.edu/talks/stanley/SRT-Online-v1.ppt http://robots.stanford.edu/papers/thrun.mapping-Stanley.pdf http://robots.stanford.edu/papers/dahlkamp.adaptvision06.pdf http://robots.stanford.edu/papers/stavens_hoffmann_thrun_ijcai07.pdf The Race http://www.youtube.com/watch?v=M2AcMnfzpNg&feature=related

  11. Questions Could this work be applied to other areas other than robot soccer with minimal changes? Andrew Courter What is Potential Fields in this paper [in plain words]? Songxin Li (Dustin) & Xiang Li

More Related