machine learning applications for personal service robots
play

Machine Learning Applications for Personal Service Robots Jun Miura - PowerPoint PPT Presentation

LAIAR-2018, Baden-Baden, Germany, June 11, 2018 TOYOHASHI UNIVERSITY OF TECHNOLOGY Machine Learning Applications for Personal Service Robots Jun Miura Active Intelligent Systems Laboratory (AISL) Department of Computer Science and


  1. LAIAR-2018, Baden-Baden, Germany, June 11, 2018 TOYOHASHI UNIVERSITY OF TECHNOLOGY Machine Learning Applications for Personal Service Robots Jun Miura Active Intelligent Systems Laboratory (AISL) Department of Computer Science and Engineering Toyohashi University of Technology

  2. Personal Service Robot Projects at AISL TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018 guide stay aside attend watch 光・熱・空気 Measure physical 機器の制御 Control appliances の状態監視 Detect Conditions 危険状態の発 potential dangers ⾒ ⼈への働きか Give cares to person け

  3. Our person following robots TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018

  4. Robotic lifestyle support TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 Speech-based June 11, 2018 control Delivery task Visual Stimuli TOYOTA Human Support Robot BMI-controlled robot

  5. Functional Components of Robot TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018 Robotics in Planning Computer Science Action Recognition Attend Environment �with Human�

  6. Important functions of personal service robots TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  Person recognition – Person detection – Person identification – Person state estimation  Person-aware behavior generation – Person’s awareness estimation – Recognize person’s intention – Attending behavior generation  Autonomous navigation – Localization and path planning  Object recognition and manipulation – Specific and general object recognition – Hand motion generation

  7. TOYOHASHI UNIVERSITY OF TECHNOLOGY Person detection and identification

  8. People detection TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  Shape-based person modeling 3D LIDAR [Kidono 2011] 2D LIDAR x2 (waist and legs) [Koide 2016]  Image-based person modeling (YOLO)

  9. Person identification TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  Use of multiple features [Koide 2016] – Cannot know which features are effective in advance  adaptive feature selection using an online boosting algorithm Face features People detection, orientation estimation, and identification Clothing features

  10. TOYOHASHI UNIVERSITY OF TECHNOLOGY Person state estimation

  11. Combined tracking and body orientation estimation [Ardiyanto 2014] TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  Image-based orientation estimation (8 orientations)  Use of motion-orientation consistency for a better estimation � � � � � � � � Correlation at higher speed � � � , � � , � � �� � Image-based Motion-based � � →∞ � � → 0 →ω (motion) → 0 (shape)

  12. One-shot body orientation estimation TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  CNN-based body orientation estimation [Kohari 2018] – Train the network using SURREAL dataset Accuracy [%] Accuracy [%] Accuracy [%] Average error Averaged ( ± 0 [deg]) ( ± 10 [deg]) ( ± 20 [deg]) [deg] time [msec] 47.7 89.7 97.5 6.94 8.73

  13. Pose estimation from depth images using deep neural network [Nishi 2017] TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018 Experimental Thermal point Extracted human Input depth data Pose estimation scene cloud region result

  14. Illumination normalization for face detection and recognition [Dewantara 2016] TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  Appearance of face changes input due to illumination changes.  Have a similar face image in output any illumination conditions  Use a fast GA-optimized fuzzy inference on-line

  15. TOYOHASHI UNIVERSITY OF TECHNOLOGY Person-aware robotic behavior

  16. Estimating person’s awareness of an obstacle [Koide 2016] TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  Key assumption: – If a person is not aware of an obstacle, the person acts as if there is no obstacle. aware exist Machine Machine learning learning unaware not exist Red : aware Green : not aware

  17. Social force guiding model [Dewantara 2016] TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018

  18. Q-learning in perceived state TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 Static and dynamic obstacles Relative position Body and head orientation June 11, 2018 Target state Robot state Obstacles state

  19. TOYOHASHI UNIVERSITY OF TECHNOLOGY Autonomous navigation

  20. View-based localization using two-stage SVM [Miura 2008] TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018 Learning Recognition Localization SVMs Is location A or SVM learning Location A Is not location A algorithm recognizer Location B recognizer Object Object recognition results recognition Location X negative result recognizer positive Object recognition Location A negative Recognizer is constructed for every location.

  21. Single SVM-based localization: results TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018  Input image is tested for all location models. June 11, 2018 – A single location is not always chosen. Multiple location models have positive output Good result The highest output is negative Input image Outputs of all location models Best matched learned image

  22. Introducing Markov localization TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  Output of localization SVM is used as likelihood values in Markov localization Input image Distribution of locations Best matched learned image

  23. Combination with Bayesian filtering TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018  SVM output is used as likelihood in the correction step of June 11, 2018 discrete Bayes filter. Input image: Jun. 22, 5pm Location on rainy the map: trained image- Best matched location image: relations are Jun. 20, 5pm manually assigned. sunny Estimated probability distribution of locations Location ID

  24. To apply machine learning to robotics TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  Simulation for training and testing  Learning from humans  Post-processing of module outputs before applying to robots

  25. TOYOHASHI UNIVERSITY OF TECHNOLOGY Dataset generation for depth image- based pose estimation

  26. Person state monitoring in unusual situations TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  Head position estimation for various postures Estimation results  Generating training data for head position estimation [Nishi 2015]

  27. Generating depth data with body part labels [Nishi 2017] TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018 Adding body Generating depth Generating parts and skeletal data and body part Adding pose data CG models information label images Attach body part and skeletal information Construct to the models various human Use a motion capture body models system for giving various pose data

  28. Motion capture for generating various pose data TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018

  29. Generated data examples TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018

  30. Dataset for partially-occluded cases TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  Put occluding objects before rendering [Nishi 2017] Input depth Input depth Correct Test scene Results Results data data labeling (RGB, Thermal)

  31. Behavior simulation TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  Simulating human behaviors in cafeteria [Shigemura 2011] – Walking towards a destination while avoiding collisions, queueing, searching for a seat to sit, … – We can specify the number of people, their objectives, floorplan, …

  32. To apply machine learning to robotics TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  Simulation for training and testing  Learning from humans  Post-processing of module outputs before applying to robots

  33. Learn how to attend from person (what attending actions are comfortable to people) TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  Attending behavior measurement system [Koide 2017] 3D LIDAR A long and wide-area Measure measurement is position and possible poses Person-person-environment behaviors are measured using a pre-constructed map

  34. Measurement example TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  Observe an attending task of a caregiver in a nearby hospital Scene Person detection Relative Relative distance position

  35. To apply machine learning to robotics TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  Simulation for training and testing  Learning from humans  Post-processing of module outputs before applying to robots

  36. Summary TOYOHASHI UNIVERSITY OF TECHNOLOGY LAIAR 2018 June 11, 2018  Machine learning methods are applicable to many robotic recognition and planning tasks, and quite useful with an enough amount and variety of data.  To use machine learning methods in robotics: – Simulation for training and testing – Learning from humans – Post-processing of their outputs before applying to robots  How to introduce ML methods? – End-to-end learning directly? – Step-by-step fashion (e.g., replace one module after another)?

Recommend


More recommend