DeepMPC: Learning Deep Latent Features for Model Predictive Control

Designing controllers for tasks with complex nonlinear dynamics is extremely challenging, time-consuming, and in many cases, infeasible. This difficulty is exacerbated in tasks such as robotic food-cutting, in which dynamics might vary both with environmental properties, such as material and tool class, and with time while acting. In this work, we present DeepMPC, an online real-time model-predictive control approach designed to handle such difficult tasks. Rather than hand-design a dynamics model for the task, our approach uses a novel deep architecture and learning algorithm, learning controllers for complex tasks directly from data. We validate our method in experiments on a large-scale dataset of 1488 material cuts for 20 diverse classes, and in 450 real-world robotic experiments, demonstrating significant improvement over several other approaches.

[1]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[2]  Christopher G. Atkeson,et al.  Estimation of Inertial Parameters of Manipulator Loads and Links , 1986 .

[3]  Anuradha M. Annaswamy,et al.  Stable Adaptive Systems , 1989 .

[4]  S. Bennett,et al.  A brief history of automatic control , 1996 .

[5]  David W. Clarke,et al.  Successive one-step-ahead predictions in multiple model predictive control , 1998, Int. J. Syst. Sci..

[6]  F. Moon,et al.  Nonlinear models for complex dynamics in cutting materials , 2001, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[7]  J. Kocijan,et al.  Gaussian process model based predictive control , 2004, Proceedings of the 2004 American Control Conference.

[8]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[9]  Manuela M. Veloso,et al.  Confidence-based policy learning from demonstration using Gaussian mixture models , 2007, AAMAS '07.

[10]  Joachim Hoffmann,et al.  Exploiting redundancy for flexible behavior: unsupervised learning in a modular sensorimotor control architecture. , 2007, Psychological review.

[11]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[12]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[13]  Honglak Lee,et al.  Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations , 2009, ICML '09.

[14]  Quoc V. Le,et al.  Measuring Invariances in Deep Networks , 2009, NIPS.

[15]  Geoffrey E. Hinton,et al.  Factored conditional restricted Boltzmann Machines for modeling motion style , 2009, ICML '09.

[16]  Alonzo Kelly,et al.  Receding Horizon Model-Predictive Control for Mobile Robot Navigation of Intricate Paths , 2009, FSR.

[17]  Geoffrey E. Hinton,et al.  Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines , 2010, Neural Computation.

[18]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[19]  A. Billard,et al.  Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models , 2011, IEEE Transactions on Robotics.

[20]  Quoc V. Le,et al.  On optimization methods for deep learning , 2011, ICML.

[21]  Aude Billard,et al.  Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models , 2011, IEEE Transactions on Robotics.

[22]  Dejan Pangercic,et al.  Robotic roommates making pancakes , 2011, 2011 11th IEEE-RAS International Conference on Humanoid Robots.

[23]  Carl E. Rasmussen,et al.  PILCO: A Model-Based and Data-Efficient Approach to Policy Search , 2011, ICML.

[24]  Jennifer Barry,et al.  Bakebot: Baking Cookies with the PR2 , 2011 .

[25]  Jan Peters,et al.  Model learning for robot control: a survey , 2011, Cognitive Processing.

[26]  Geoffrey E. Hinton,et al.  Generating Text with Recurrent Neural Networks , 2011, ICML.

[27]  Geoffrey E. Hinton,et al.  Acoustic Modeling Using Deep Belief Networks , 2012, IEEE Transactions on Audio, Speech, and Language Processing.

[28]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[29]  Alvaro García Cazorla,et al.  ROS : Robot Operating System , 2013 .

[30]  Yuval Tassa,et al.  An integrated system for real-time model predictive control of humanoid robots , 2013, 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids).

[31]  Louis L. Whitcomb,et al.  Experimental evaluation of adaptive model-based control for underwater vehicles in the presence of unmodeled actuator dynamics , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[32]  Kostas J. Kyriakopoulos,et al.  Robustness analysis of model predictive control for constrained Image-Based Visual Servoing , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[33]  Hema Swetha Koppula,et al.  RoboBrain: Large-Scale Knowledge Engine for Robots , 2014, ArXiv.

[34]  Rui Pedro Duarte Cortesão,et al.  Model predictive control architectures with force feedback for robotic-assisted beating heart surgery , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[35]  Sergey Levine,et al.  Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics , 2014, NIPS.

[36]  Ashutosh Saxena,et al.  Learning haptic representation for manipulating deformable food objects , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[37]  S. Sastry,et al.  Decentralized Reflective Model Predictive Control of Multiple Flying Robots in Dynamic Environment , 2022 .