Robots of the Lost Arc: Self-Supervised Learning to Dynamically Manipulate Fixed-Endpoint Cables

We explore how high-speed robot arm motions can dynamically manipulate ropes and cables to vault over obstacles, knock objects from pedestals, and weave between obstacles. In this paper, we propose a self-supervised learning framework that enables a UR5 robot to perform these three tasks. The framework finds a 3D apex point for the robot arm, which, together with a task-specific trajectory function, defines an arcing motion that dynamically manipulates the cable to perform a task with varying obstacle and target locations. The trajectory function computes minimum-jerk motions that are constrained to remain within joint limits and to travel through the 3D apex point by repeatedly solving quadratic programs to find the shortest and fastest feasible motion. We experiment with 5 physical cables with different thickness and mass and compare performance against two baselines in which a human chooses the apex point. Results suggest that a baseline with a fixed apex across the three tasks achieves respective success rates of 51.7 %, 36.7 %, and 15.0 %, and a baseline with human-specified, task-specific apex points achieves 66.7 %, 56.7 %, and 15.0 % success rate respectively, while the robot using the learned apex point can achieve success rates of 81.7 % in vaulting, 65.0 % in knocking, and 60.0 % in weaving. Code, data, and supplementary materials are available at https://sites.google.com/berkeley.edu/dynrope/home.

[1]  Roi Poranne,et al.  Dynamic Manipulation of Deformable Objects With Implicit Integration , 2021, IEEE Robotics and Automation Letters.

[2]  Peter R. Florence,et al.  Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networks , 2020, 2021 IEEE International Conference on Robotics and Automation (ICRA).

[3]  Yufei Wang,et al.  SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation , 2020, CoRL.

[4]  Priya Sundaresan,et al.  Untangling Dense Knots by Learning Task-Relevant Keypoints , 2020, CoRL.

[5]  Akansel Cosgun,et al.  Learning Arbitrary-Goal Fabric Folding with One Hour of Real Robot Experience , 2020, CoRL.

[6]  Pieter Abbeel,et al.  Learning Predictive Representations for Deformable Objects Using Contrastive Estimation , 2020, CoRL.

[7]  Ken Goldberg,et al.  GOMP: Grasp-Optimized Motion Planning for Bin Picking , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[8]  Priya Sundaresan,et al.  Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[9]  Benjamin Navarro,et al.  Robotic Manipulation Planning for Shaping Deformable Linear Objects WithEnvironmental Contacts , 2020, IEEE Robotics and Automation Letters.

[10]  Yilin Zhu,et al.  Self-Supervised Learning of State Estimation for Manipulating Deformable Linear Objects , 2019, IEEE Robotics and Automation Letters.

[11]  P. Abbeel,et al.  Learning to Manipulate Deformable Objects without Demonstrations , 2019, Robotics: Science and Systems.

[12]  E. Adelson,et al.  Cable manipulation with a tactile-reactive gripper , 2019, Robotics: Science and Systems.

[13]  Alberto Rodriguez,et al.  TossingBot: Learning to Throw Arbitrary Objects With Residual Physics , 2019, IEEE Transactions on Robotics.

[14]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[15]  Pieter Abbeel,et al.  Learning Robotic Manipulation through Visual Planning and Acting , 2019, Robotics: Science and Systems.

[16]  Abhinav Gupta,et al.  Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias , 2018, NeurIPS.

[17]  Belhassen-Chedli Bouzgarrou,et al.  Robotic manipulation and sensing of deformable objects in domestic and industrial applications: a survey , 2018, Int. J. Robotics Res..

[18]  Jitendra Malik,et al.  Zero-Shot Visual Imitation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[19]  Jitendra Malik,et al.  Combining self-supervised learning and imitation for vision-based rope manipulation , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[20]  Young-Ho Kim,et al.  Using a Compliant, Unactuated Tail to Manipulate Objects , 2017, IEEE Robotics and Automation Letters.

[21]  Devin J. Balkcom,et al.  Tying knot precisely , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[22]  Kenneth Y. Goldberg,et al.  Automating multi-throw multilateral surgical suturing with a mechanical needle guide and sequential convex optimization , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

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

[24]  Dmitry Berenson,et al.  An online method for tight-tolerance insertion tasks for string and rope , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[25]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[26]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Dylan Hadfield-Menell,et al.  Unifying scene registration and trajectory optimization for learning from demonstrations with application to manipulation of deformable objects , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[28]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[29]  Ankush Gupta,et al.  A case study of trajectory transfer through non-rigid registration for a simplified suturing scenario , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[30]  Ashutosh Saxena,et al.  Tangled: Learning to untangle ropes with RGB-D perception , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[31]  Masatoshi Ishikawa,et al.  Dynamic High-Speed Knotting of a Rope by a Manipulator , 2013 .

[32]  Pieter Abbeel,et al.  Learning from Demonstrations Through the Use of Non-rigid Registration , 2013, ISRR.

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

[34]  Masatoshi Ishikawa,et al.  Simple Model and Deformation Control of a Flexible Rope using Constant, High-Speed Motion of a Robot Arm , 2012, 2012 IEEE International Conference on Robotics and Automation.

[35]  Geoffrey J. Gordon,et al.  A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning , 2010, AISTATS.

[36]  Gang Wang,et al.  Analysis of fly fishing rod casting dynamics , 2011 .

[37]  Masatoshi Ishikawa,et al.  Motion planning for dynamic knotting of a flexible rope with a high-speed robot arm , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[38]  Pieter Abbeel,et al.  Superhuman performance of surgical tasks by robots using iterative learning from human-guided demonstrations , 2010, 2010 IEEE International Conference on Robotics and Automation.

[39]  Masatoshi Ishikawa,et al.  One-handed knotting of a flexible rope with a high-speed multifingered hand having tactile sensors , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[40]  Noel C. Perkins,et al.  Numerical model for the dynamics of a coupled fly line/fly rod system and experimental validation , 2004 .

[41]  Jun Takamatsu,et al.  Knot planning from observation , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[42]  Hirofumi Nakagaki,et al.  Study of deformation and insertion tasks of a flexible wire , 1997, Proceedings of International Conference on Robotics and Automation.

[43]  Hirofumi Nakagaki,et al.  Study of insertion task of a flexible wire into a hole by using visual tracking observed by stereo vision , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[44]  Dean Pomerleau,et al.  Efficient Training of Artificial Neural Networks for Autonomous Navigation , 1991, Neural Computation.

[45]  Joseph K. Kearney,et al.  A Case Study of Flexible Object Manipulation , 1991, Int. J. Robotics Res..

[46]  Roy Featherstone,et al.  Robot Dynamics Algorithms , 1987 .