Learning Manifolds for Sequential Motion Planning

Motion planning with constraints is an important part of many real-world robotic systems. In this work, we study manifold learning methods to learn such constraints from data. We explore two methods for learning implicit constraint manifolds from data: Variational Autoencoders (VAE), and a new method, Equality Constraint Manifold Neural Network (ECoMaNN). With the aim of incorporating learned constraints into a sampling-based motion planning framework, we evaluate the approaches on their ability to learn representations of constraints from various datasets and on the quality of paths produced during planning.

[1]  Marc Toussaint,et al.  Differentiable Physics and Stable Modes for Tool-Use and Manipulation Planning , 2018, Robotics: Science and Systems.

[2]  Lydia E. Kavraki,et al.  Exploring implicit spaces for constrained sampling-based planning , 2019, Int. J. Robotics Res..

[3]  Siddhartha S. Srinivasa,et al.  Task Space Regions , 2011, Int. J. Robotics Res..

[4]  Charles C. Kemp,et al.  A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-Based Variational Autoencoder , 2017, IEEE Robotics and Automation Letters.

[5]  Nathaniel E. Helwig,et al.  An Introduction to Linear Algebra , 2006 .

[6]  Nanda Kambhatla,et al.  Dimension Reduction by Local Principal Component Analysis , 1997, Neural Computation.

[7]  Frank Chongwoo Park,et al.  Tangent bundle RRT: A randomized algorithm for constrained motion planning , 2014, Robotica.

[8]  Mike Stilman,et al.  Global Manipulation Planning in Robot Joint Space With Task Constraints , 2010, IEEE Transactions on Robotics.

[9]  Yuval Tassa,et al.  MuJoCo: A physics engine for model-based control , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  Gaurav S. Sukhatme,et al.  Sampling-Based Motion Planning on Manifold Sequences , 2020, RSS 2020.

[11]  Swarat Chaudhuri,et al.  The Task-Motion Kit: An Open Source, General-Purpose Task and Motion-Planning Framework , 2018, IEEE Robotics & Automation Magazine.

[12]  Leslie Pack Kaelbling,et al.  From Skills to Symbols: Learning Symbolic Representations for Abstract High-Level Planning , 2018, J. Artif. Intell. Res..

[13]  Leslie Pack Kaelbling,et al.  Integrated task and motion planning in belief space , 2013, Int. J. Robotics Res..

[14]  Rachid Alami,et al.  A Hybrid Approach to Intricate Motion, Manipulation and Task Planning , 2009, Int. J. Robotics Res..

[15]  Léonard Jaillet,et al.  Asymptotically-optimal Path Planning on Manifolds , 2012, Robotics: Science and Systems.

[16]  John M. Lee.  Introduction to Smooth Manifolds , 2002 .

[17]  Sachin Chitta,et al.  Motion planning with constraints using configuration space approximations , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[18]  Maximilian Karl,et al.  Dynamic movement primitives in latent space of time-dependent variational autoencoders , 2016, 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids).

[19]  Gérard G. Medioni,et al.  Unsupervised Learning Using the Tensor Voting Graph , 2015, SSVM.

[20]  Thierry Siméon,et al.  Sampling-Based Motion Planning under Kinematic Loop-Closure Constraints , 2004, WAFR.

[21]  Leslie Pack Kaelbling,et al.  A hierarchical approach to manipulation with diverse actions , 2013, 2013 IEEE International Conference on Robotics and Automation.

[22]  Swarat Chaudhuri,et al.  Incremental Task and Motion Planning: A Constraint-Based Approach , 2016, Robotics: Science and Systems.