Continuous Perception for Classifying Shapes and Weights of Garmentsfor Robotic Vision Applications

We present an approach to continuous perception for robotic laundry tasks. Our assumption is that the visual prediction of a garment's shapes and weights is possible via a neural network that learns the dynamic changes of garments from video sequences. Continuous perception is leveraged during training by inputting consecutive frames, of which the network learns how a garment deforms. To evaluate our hypothesis, we captured a dataset of 40K RGB and 40K depth video sequences while a garment is being manipulated. We also conducted ablation studies to understand whether the neural network learns the physical and dynamic properties of garments. Our findings suggest that a modified AlexNet-LSTM architecture has the best classification performance for the garment's shape and weights. To further provide evidence that continuous perception facilitates the prediction of the garment's shapes and weights, we evaluated our network on unseen video sequences and computed the 'Moving Average' over a sequence of predictions. We found that our network has a classification accuracy of 48% and 60% for shapes and weights of garments, respectively.

[1]  Oliver Brock,et al.  Interactive Perception: Leveraging Action in Perception and Perception in Action , 2016, IEEE Transactions on Robotics.

[2]  Jiajun Wu,et al.  Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids , 2018, ICLR.

[3]  Vladimír Petrík,et al.  Folding Clothes Autonomously: A Complete Pipeline , 2016, IEEE Transactions on Robotics.

[4]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[5]  Jessica K. Hodgins,et al.  Estimating cloth simulation parameters from video , 2003, SCA '03.

[6]  J. Paul Siebert,et al.  Recognising the clothing categories from free-configuration using Gaussian-Process-based interactive perception , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[7]  J. Paul Siebert,et al.  Single-shot clothing category recognition in free-configurations with application to autonomous clothes sorting , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[8]  Daniel L. K. Yamins,et al.  Visual Grounding of Learned Physical Models , 2020, ICML.

[9]  Katsu Yamane,et al.  Learning to Smooth and Fold Real Fabric Using Dense Object Descriptors Trained on Synthetic Color Images , 2020, ArXiv.

[10]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[11]  Ioannis Mariolis,et al.  Pose and category recognition of highly deformable objects using deep learning , 2015, 2015 International Conference on Advanced Robotics (ICAR).

[12]  Carme Torras,et al.  Perception of cloth in assistive robotic manipulation tasks , 2020, Natural Computing.

[13]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Maud Marchal,et al.  Simultaneous Tracking and Elasticity Parameter Estimation of Deformable Objects , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[15]  Ian D. Walker,et al.  Classification of clothing using interactive perception , 2011, 2011 IEEE International Conference on Robotics and Automation.

[16]  Ming C. Lin,et al.  Learning-Based Cloth Material Recovery from Video , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[17]  Li Sun,et al.  Accurate garment surface analysis using an active stereo robot head with application to dual-arm flattening , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[18]  Kimitoshi Yamazaki,et al.  A Learning Method of Dual-arm Manipulation for Cloth Folding Using Physics Simulator , 2019, 2019 IEEE International Conference on Mechatronics and Automation (ICMA).

[19]  Arnold W.M. Smeulders,et al.  Cloth in the Wind: A Case Study of Physical Measurement Through Simulation , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Frédo Durand,et al.  Visual vibrometry: Estimating material properties from small motions in video , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Javier Ruiz-del-Solar,et al.  Continuous perception for deformable objects understanding , 2019, Robotics Auton. Syst..

[22]  Frédo Durand,et al.  Visual vibrometry: Estimating material properties from small motions in video , 2015, CVPR.