RoboGrammar

Fig. 1. The input to our system is a set of base robot components, such as links, joints, and end structures, and at least one terrain, such as stepped terrain or terrain with wall obstacles. RoboGrammar provides a recursive graph grammar to efficiently generate hundreds of thousands of robot structures built with the given components. We then use Graph Heuristic Search coupled with model predictive control (MPC) to facilitate exploration of the large design space, and identify high performing examples for a given terrain. Our approach enables co-optimization of both robot structures and controllers.

[1]  Gregory S. Hornby,et al.  Computer Creativity in the Automatic Design of Robots , 2003, Leonardo.

[2]  Sanjit A. Seshia,et al.  Learning Heuristics for Automated Reasoning through Deep Reinforcement Learning , 2018, ArXiv.

[3]  Csaba Szepesvári,et al.  Bandit Based Monte-Carlo Planning , 2006, ECML.

[4]  J. M. D. Silva,et al.  Model Predictive Control of a Mobile Robot Using Linearization , 2022 .

[5]  Alexei A. Efros,et al.  Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity , 2019, NeurIPS.

[6]  Alaa A. Kharbouch,et al.  Three models for the description of language , 1956, IRE Trans. Inf. Theory.

[7]  Hod Lipson,et al.  Automatic Design and Manufacture of Soft Robots , 2012, IEEE Transactions on Robotics.

[8]  David Ha,et al.  Reinforcement Learning for Improving Agent Design , 2018, Artificial Life.

[9]  Niloy J. Mitra,et al.  Creating consistent scene graphs using a probabilistic grammar , 2014, ACM Trans. Graph..

[10]  Jure Leskovec,et al.  Hierarchical Graph Representation Learning with Differentiable Pooling , 2018, NeurIPS.

[11]  Rui Wang,et al.  Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions , 2019, ArXiv.

[12]  Levente Kocsis,et al.  Transpositions and move groups in Monte Carlo tree search , 2008, 2008 IEEE Symposium On Computational Intelligence and Games.

[13]  Leif Kobbelt,et al.  Generalized Use of Non‐Terminal Symbols for Procedural Modeling , 2010, Comput. Graph. Forum.

[14]  H. Sebastian Seung,et al.  Stochastic policy gradient reinforcement learning on a simple 3D biped , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[15]  Michèle Sebag,et al.  The grand challenge of computer Go , 2012, Commun. ACM.

[16]  R. Featherstone.  The Calculation of Robot Dynamics Using Articulated-Body Inertias , 1983 .

[17]  David P. Helmbold,et al.  All-Moves-As-First Heuristics in Monte-Carlo Go , 2009, IC-AI.

[18]  Gregory S. Hornby,et al.  The advantages of generative grammatical encodings for physical design , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[19]  Luc Van Gool,et al.  Procedural modeling of buildings , 2006, SIGGRAPH 2006.

[20]  Erwin Coumans,et al.  Bullet physics simulation , 2015, SIGGRAPH Courses.

[21]  Z. M. Bi,et al.  Concurrent optimal design of modular robotic configuration , 2001, J. Field Robotics.

[22]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[23]  Mark Yim,et al.  Accomplishing high-level tasks with modular robots , 2017, Autonomous Robots.

[24]  François Charpillet,et al.  Long-term robot motion planning for active sound source localization with Monte Carlo tree search , 2017, 2017 Hands-free Speech Communications and Microphone Arrays (HSCMA).

[25]  Michael Wimmer,et al.  Interactive visual editing of grammars for procedural architecture , 2008, ACM Trans. Graph..

[26]  Sanja Fidler,et al.  Neural Graph Evolution: Towards Efficient Automatic Robot Design , 2019, ICLR.

[27]  Phil Husbands,et al.  Evolutionary robotics , 2014, Evolutionary Intelligence.

[28]  SzepesváriCsaba,et al.  The grand challenge of computer Go , 2012 .

[29]  Takeo Igarashi,et al.  Converting 3D furniture models to fabricatable parts and connectors , 2011, ACM Trans. Graph..

[30]  António Augusto de Sousa,et al.  Layered shape grammars for procedural modelling of buildings , 2016, The Visual Computer.

[31]  David Silver,et al.  Monte-Carlo tree search and rapid action value estimation in computer Go , 2011, Artif. Intell..

[32]  Igor Skrjanc,et al.  Tracking-error model-based predictive control for mobile robots in real time , 2007, Robotics Auton. Syst..

[33]  Kristina Shea,et al.  A Simulation-Driven Graph Grammar Method for the Automated Synthesis of Passive Dynamic Brachiating Robots , 2015 .

[34]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[35]  Eric Klavins,et al.  Graph grammars for self assembling robotic systems , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[36]  Jonathan Cagan,et al.  GGREADA: A graph grammar-based machine design algorithm , 1997 .

[37]  Peter Wonka,et al.  Interactive design of probability density functions for shape grammars , 2015, ACM Trans. Graph..

[38]  George Stiny,et al.  Spatial Relations and Grammars , 1982 .

[39]  José Pinto Duarte,et al.  Towards the Mass Customization of Housing: The Grammar of Siza's Houses at Malagueira , 2005 .

[40]  U Flemming,et al.  The Bungalows of Buffalo , 1981 .

[41]  George Stiny,et al.  Shape Grammars and the Generative Specification of Painting and Sculpture , 1971, IFIP Congress.

[42]  Pascal Müller,et al.  Procedural modeling of cities , 2001, SIGGRAPH.

[43]  Jon McCormack,et al.  Generative design: a paradigm for design research , 2005 .

[44]  James M. Rehg,et al.  Aggressive driving with model predictive path integral control , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[45]  Wojciech Matusik,et al.  Learning-In-The-Loop Optimization: End-To-End Control And Co-Design Of Soft Robots Through Learned Deep Latent Representations , 2019, NeurIPS.

[46]  Dong-Ming Yan,et al.  Inverse procedural modeling of facade layouts , 2013, ACM Trans. Graph..

[47]  Glen Berseth,et al.  DeepLoco , 2017, ACM Trans. Graph..

[48]  Rémi Munos,et al.  From Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning , 2014, Found. Trends Mach. Learn..

[49]  Dan Boneh,et al.  On genetic algorithms , 1995, COLT '95.

[50]  Jordan B. Pollack,et al.  Embodied Evolution: Distributing an evolutionary algorithm in a population of robots , 2002, Robotics Auton. Syst..

[51]  Scott Curland Chase,et al.  A Graph Grammar Approach for Structure Synthesis of Mechanisms , 2000 .

[52]  F. Iida,et al.  Morphological Evolution of Physical Robots through Model-Free Phenotype Development , 2015, PloS one.

[53]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[54]  Simon M. Lucas,et al.  A Survey of Monte Carlo Tree Search Methods , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

[55]  Alcherio Martinoli,et al.  Inspiring and Modeling Multi-Robot Search with Particle Swarm Optimization , 2007, 2007 IEEE Swarm Intelligence Symposium.

[56]  Magnus Egerstedt,et al.  Multi-robot deployment and coordination with Embedded Graph Grammars , 2009, Auton. Robots.

[57]  H. Jaap van den Herik,et al.  Single-Player Monte-Carlo Tree Search , 2008, Computers and Games.

[58]  Sham M. Kakade,et al.  Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control , 2018, ICLR.

[59]  Michael Wimmer,et al.  Instant architecture , 2003, ACM Trans. Graph..

[60]  Manfred Morari,et al.  Model predictive control: Theory and practice - A survey , 1989, Autom..

[61]  Joel W. Burdick,et al.  Determining task optimal modular robot assembly configurations , 1995, Proceedings of 1995 IEEE International Conference on Robotics and Automation.

[62]  John R. Koza,et al.  Survey of genetic algorithms and genetic programming , 1995, Proceedings of WESCON'95.

[63]  William J. Mitchell,et al.  The Palladian Grammar , 1978 .

[64]  Matthew R. Walter,et al.  Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning , 2018, 2019 International Conference on Robotics and Automation (ICRA).

[65]  Karl Sims,et al.  Evolving virtual creatures , 1994, SIGGRAPH.

[66]  Yi Chen,et al.  Wasserstein blue noise sampling , 2017, TOGS.

[67]  Kristina Shea,et al.  A Spatial Grammar Method for the Computational Design Synthesis of Virtual Soft Locomotion Robots , 2019, Journal of Mechanical Design.

[68]  H. Seidel,et al.  A connection between partial symmetry and inverse procedural modeling , 2010, ACM Trans. Graph..

[69]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[70]  Daniel G. Aliaga,et al.  Inverse Procedural Modeling by Automatic Generation of L‐systems , 2010, Comput. Graph. Forum.