1 / 43

Jivko Sinapov, Kaijen Hsiao and Radu Bogdan Rusu

Jivko Sinapov, Kaijen Hsiao and Radu Bogdan Rusu. Proprioceptive Perception for Object Weight Classification. What is Proprioception?.

diamond
Download Presentation

Jivko Sinapov, Kaijen Hsiao and Radu Bogdan Rusu

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. Jivko Sinapov, Kaijen Hsiao and Radu Bogdan Rusu Proprioceptive Perception for Object Weight Classification

  2. What is Proprioception? “It is the sense that indicates whether the body is moving with required effort, as well as where the various parts of the body are located in relation to each other.” - Wikipedia

  3. Why Proprioception?

  4. Why Proprioception? Full Empty

  5. Why Proprioception? vs Soft Hard

  6. Lifting: gravity, effort, etc.

  7. Pushing: friction, mass, etc.

  8. Squeezing: compliance, flexibility

  9. Power, “Play and Exploration in Children and Animals”, 2000

  10. Related Work: Proprioception • “Learning Haptic Representations of Objects”: [ Natale et al (2004) ]

  11. Related Work: Proprioception • Proprioceptive Object Recognition [ Bergquist et al (2009) ]

  12. Perception Problem for PR2:Is the bottle full or empty?

  13. General Approach • Let the robot experience what full and empty bottles “feel” like • Use prior experience to classify new bottles as either full or empty

  14. Behavior: • Power, “Play and Exploration in Children and Animals”, 2000

  15. Behaviors 1) Unsupported Holding 2) Lifting

  16. Data Representation Behavior Execution: Recorded Data: [Ji, Ei, Ci] Joint Positions Class Label {full, empty} Efforts

  17. Example Recorded Joint Efforts of Left Arm:

  18. Classification Procedure Pr( ‘empty’ ) Pr( ‘full’ ) [Ji, Ei, ?] Recognition Model Feature Extraction

  19. Recognition Model X =[Ji, Ei, ?] Recognition Model

  20. Recognition Model X =[Ji, Ei, ?] Recognition Model Find N closest neighbors to X in joint-feature space

  21. Recognition Model X =[Ji, Ei, ?] Recognition Model Find N closest neighbors to X in joint-feature space Train classifier C on the N neighbors that maps effort features to class label

  22. Recognition Model X =[Ji, Ei, ?] Recognition Model Find N closest neighbors to X in joint-feature space Train classifier C on the N neighbors that maps effort features to class label Use trained classifier C to label X

  23. Training Procedure • Objects: • Procedure: • Place object on table • Robot grasps it and performs the current behavior (either hold or lift) in a random position in space • Robot puts object back down on table in random position; repeat. • Each behavior performed 100 times on each bottle in both full and empty states • A total of 2 x 5 x 100 x 2 = 2000 behavior executions

  24. Evaluation • 5 fold cross-validation: at each iteration, data with 4 out of the five bottles is used for training, and the rest used for testing • Three classification algorithms evaluated: • K-Nearest Neighbors • Support Vector Machine (quadratic kernel) • C4.5 Tree

  25. Chance Accuracy: 50%

  26. Can the robot boost recognition rate by applying a behavior multiple times?

  27. How much training data is necessary?

  28. (lift)

  29. Application to Regression X =[Ji, Ei, ?] Recognition Model Find N closest neighbors to X in joint-feature space Train regression model C on the N neighbors that maps effort features to class label Use trained regression model C to label X

  30. Regression Results

  31. Regression Results Mean Abs. Error = 0.08827 lbs

  32. Regression Results Chance error = 0.2674 lbs Mean Abs. Error = 0.08827 lbs

  33. Application to Sorting Task • Sorting task: • Place empty bottles in trash • Move full bottles on other side of table

  34. Application to Sorting Task

  35. Application to Sorting Task

  36. Sorting Task: video

  37. Application to a new recognition task Full or empty?

  38. Behavior: • 40 trials with full box and 40 trials with empty box • Recognition Accuracy: 98.75 % (all three algorithms) slide object across table

  39. Sliding task: video

  40. Conclusion • Behavior-grounded approach to proprioceptive perception • Implemented as a ROS package: • http://www.ros.org/wiki/proprioception This work has been submitted to ICRA 2011.

  41. Future Work • More advanced proprioceptive feature extraction • Multi-modal object perception: • Auditory • 3D • Tactile

More Related