robotic navigation experience gained with radar
play

Robotic Navigation - Experience Gained with RADAR Martin Adams - PowerPoint PPT Presentation

Robotic Navigation - Experience Gained with RADAR Martin Adams Dept. Electrical Engineering, AMTC Universidad de Chile (martin@ing.uchile.cl) 2 nd Workshop on Alternative Sensing for Robot Perception IROS 2015 Mapping, Tracking & SLAM at


  1. Robotic Navigation - Experience Gained with RADAR Martin Adams Dept. Electrical Engineering, AMTC Universidad de Chile (martin@ing.uchile.cl) 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  2. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM Presentation Outline 1. Mapping, Tracking & SLAM at U. Chile. 2. Sensor Measurement & Detections: • Landmark Existence and Spatial Uncertainty. 3. Simultaneous Localisation & Map Building (SLAM). • A Random Finite Set (RFS) Approach. • Set Based Likelihood Formulation. • RFS SLAM – A generalization of Random Vector SLAM. • RFS versus Vector Based SLAM – Results. 4. Future Work in RFS based Mapping/SLAM. 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  3. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM Presentation Outline 1. Mapping, Tracking & SLAM at U. Chile. 2. Sensor Measurement & Detections: • Landmark Existence and Spatial Uncertainty. 3. Simultaneous Localisation & Map Building (SLAM). • A Random Finite Set (RFS) Approach. • Set Based Likelihood Formulation. • RFS SLAM – A generalization of Random Vector SLAM. • RFS versus Vector Based SLAM – Results. 4. Future Work in RFS based Mapping/SLAM. 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  4. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM Mapping in Mines/Rugged Terrains Mapping El Teniente’s Esmeralda Mine. - VIDEO 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  5. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM Mapping in Mines/Rugged Terrains Individual LADAR scans Registered LADAR scans from 45 individual scans 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  6. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM Space Debris Tracking Detecting & Tracking space debris between 1 and 10 cubic cm based on optical & radio telescopic data Vicuña (Chile) NEO Space telescope (U. Chile + U. Serena) Chilbolton 3GHz range/Doppler radar for SSA 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  7. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM Space Debris Tracking Goals: Provide tracking SW framework robust to significant false alarms & radar/visual blind zones 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  8. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM SLAM in outdoor/mining environments 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  9. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM SLAM in outdoor/mining environments • Improved estimation and incorporation of detection statistics & measurement likelihoods in RFS based SLAM 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  10. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM Presentation Outline 1. Mapping, Tracking & SLAM at U. Chile. 2. Sensor Measurement & Detections: • Landmark Existence and Spatial Uncertainty. 3. Simultaneous Localisation & Map Building (SLAM). • A Random Finite Set (RFS) Approach. • Set Based Likelihood Formulation. • RFS SLAM – A generalization of Random Vector SLAM. • RFS versus Vector Based SLAM – Results. 4. Future Work in RFS based Mapping/SLAM. 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  11. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM Sensing the Environment Clearpath Robotic Skid Steer Platform  Acumine Radar 360 deg. scanning unit, 94GHz FMCW  Sick LD-LRS1000 Scanning LRF  Microsoft Kinect camera system Video El Teniente 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  12. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM Sensing the Environment: Detection Errors The random nature of detections Radar LRF + Line RANSAC Visual SURF Features 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  13. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM Sensing the Environment: Detection Statistics Feature absence & presence statistics Radar LRF + Line RANSAC Visual SURF Features 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  14. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM What’s in a Measurement? 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  15. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM What’s in a Measurement? 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  16. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM What’s in a Measurement? Robotic Interpretation: 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  17. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM What’s in a Measurement? Robotic Interpretation: 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  18. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM What’s in a Measurement? Robotic Interpretation: Radar Interpretation: 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  19. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM What’s in a Measurement? Robotic Interpretation: Radar Interpretation: 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  20. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM What’s in a Measurement? • In reality – Probability of Detection less than unity, but may not be known. 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  21. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM What’s in a Measurement? • In reality – Probability of Detection less than unity, but may not be known. • However, landmark/feature measurements in SLAM result from a feature detection algorithm. 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  22. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM What’s in a Measurement? • In reality – Probability of Detection less than unity, but may not be known. • However, landmark/feature measurements in SLAM result from a feature detection algorithm. • Principled algorithms provide estimates of , or they can and P P D fa be estimated a-priori (e.g. RANSAC). 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  23. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM What’s in a Measurement? • In reality – Probability of Detection less than unity, but may not be known. • However, landmark/feature measurements in SLAM result from a feature detection algorithm. • Principled algorithms provide estimates of , or they can and P P D fa be estimated a-priori (e.g. RANSAC). • Ideal scenario: Represent all detection hypotheses in terms of their: (i.e. range, spatial uncertainty, detection , σ 2 i i i ( ) , ( ) and r P r P uncertainty and false alarm probability). k k D k fa 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  24. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM The Importance of Missed Detections  Wider beam width  Foliage penetration 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  25. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM The Importance of False Alarms Radar detections registered to ground truth location. 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

  26. Mapping, Tracking & SLAM at U. Chile Sensor Measurements & Detections SLAM Future Work in RFS Based SLAM Radar Based Projects: A*Star - Radar vs. Ladar Video: Raw_Data_Display.avi 2 nd Workshop on Alternative Sensing for Robot Perception – IROS 2015

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend