Gibson Env: Real-World Perception for Embodied Agents

Developing visual perception models for active agents and sensorimotor control in the physical world are cumbersome as existing algorithms are too slow to efficiently learn in real-time and robots are fragile and costly. This has given rise to learning-in-simulation which consequently casts a question on whether the results transfer to real-world. In this paper, we investigate developing real-world perception for active agents, propose Gibson Environment for this purpose, and showcase a set of perceptual tasks learned therein. Gibson is based upon virtualizing real spaces, rather than artificially designed ones, and currently includes over 1400 floor spaces from 572 full buildings. The main characteristics of Gibson are: I. being from the real-world and reflecting its semantic complexity, II. having an internal synthesis mechanism "Goggles" enabling deploying the trained models in real-world without needing domain adaptation, III. embodiment of agents and making them subject to constraints of physics and space.

[1]  R. Held,et al.  MOVEMENT-PRODUCED STIMULATION IN THE DEVELOPMENT OF VISUALLY GUIDED BEHAVIOR. , 1963, Journal of comparative and physiological psychology.

[2]  Herbert A. Simon,et al.  The Sciences of the Artificial , 1970 .

[3]  J. Gibson.  The Ecological Approach to Visual Perception , 1979 .

[4]  Jaime G. Carbonell,et al.  The world modelers project: objectives and simulator architecture , 1986 .

[5]  Oussama Khatib,et al.  A unified approach for motion and force control of robot manipulators: The operational space formulation , 1987, IEEE J. Robotics Autom..

[6]  Dean Pomerleau,et al.  ALVINN, an autonomous land vehicle in a neural network , 2015 .

[7]  Oussama Khatib,et al.  Real-Time Obstacle Avoidance for Manipulators and Mobile Robots , 1985, Autonomous Robot Vehicles.

[8]  Rodney A. Brooks,et al.  Elephants don't play chess , 1990, Robotics Auton. Syst..

[9]  R. A. Brooks,et al.  Intelligence without Representation , 1991, Artif. Intell..

[10]  T. Sejnowski,et al.  A critique of pure vision , 1993 .

[11]  Lance Williams,et al.  View Interpolation for Image Synthesis , 1993, SIGGRAPH.

[12]  Stephen P. Boyd,et al.  Linear Matrix Inequalities in Systems and Control Theory , 1994 .

[13]  Steven M. Seitz,et al.  View morphing , 1996, SIGGRAPH.

[14]  Marc Levoy,et al.  Light field rendering , 1996, SIGGRAPH.

[15]  Leonard McMillan,et al.  Post-rendering 3D warping , 1997, SI3D.

[16]  E. Yaz.  Linear Matrix Inequalities In System And Control Theory , 1998, Proceedings of the IEEE.

[17]  Richard Szeliski,et al.  Layered depth images , 1998, SIGGRAPH.

[18]  Anselmo Lastra,et al.  LDI tree: a hierarchical representation for image-based rendering , 1999, SIGGRAPH.

[19]  Zoubin Ghahramani,et al.  Computational principles of movement neuroscience , 2000, Nature Neuroscience.

[20]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[21]  Vijay Kumar,et al.  Modeling and control of formations of nonholonomic mobile robots , 2001, IEEE Trans. Robotics Autom..

[22]  Michael Gasser,et al.  The Development of Embodied Cognition: Six Lessons from Babies , 2005, Artificial Life.

[23]  Christos Dimitrakakis,et al.  TORCS, The Open Racing Car Simulator , 2005 .

[24]  Pieter Abbeel,et al.  An Application of Reinforcement Learning to Aerobatic Helicopter Flight , 2006, NIPS.

[25]  John Blitzer,et al.  Domain Adaptation with Structural Correspondence Learning , 2006, EMNLP.

[26]  Hal Daumé,et al.  Frustratingly Easy Domain Adaptation , 2007, ACL.

[27]  Cordelia Schmid,et al.  Learning realistic human actions from movies , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Mubarak Shah,et al.  Action MACH a spatio-temporal Maximum Average Correlation Height filter for action recognition , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[30]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[31]  Eli Shechtman,et al.  Regenerative morphing , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[32]  Trevor Darrell,et al.  Adapting Visual Category Models to New Domains , 2010, ECCV.

[33]  Pieter Abbeel,et al.  Autonomous Helicopter Aerobatics through Apprenticeship Learning , 2010, Int. J. Robotics Res..

[34]  A. Parker.  On the origin of optics , 2011 .

[35]  David A. Forsyth,et al.  Rendering synthetic objects into legacy photographs , 2011, ACM Trans. Graph..

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

[37]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[38]  Bernhard Schölkopf,et al.  A Kernel Two-Sample Test , 2012, J. Mach. Learn. Res..

[39]  Andreas Geiger,et al.  Vision meets robotics: The KITTI dataset , 2013, Int. J. Robotics Res..

[40]  Rob Fergus,et al.  Depth Map Prediction from a Single Image using a Multi-Scale Deep Network , 2014, NIPS.

[41]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[42]  Michael Goesele,et al.  Let There Be Color! Large-Scale Texturing of 3D Reconstructions , 2014, ECCV.

[43]  Ira Kemelmacher-Shlizerman,et al.  Total Moving Face Reconstruction , 2014, ECCV.

[44]  George Drettakis,et al.  A Bayesian Approach for Selective Image-Based Rendering Using Superpixels , 2015, 2015 International Conference on 3D Vision.

[45]  Sergey Levine,et al.  Trust Region Policy Optimization , 2015, ICML.

[46]  Joshua B. Tenenbaum,et al.  Deep Convolutional Inverse Graphics Network , 2015, NIPS.

[47]  Jiajun Wu,et al.  Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning , 2015, NIPS.

[48]  Leonidas J. Guibas,et al.  ShapeNet: An Information-Rich 3D Model Repository , 2015, ArXiv.

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

[50]  Thomas Brox,et al.  Learning to generate chairs with convolutional neural networks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[52]  Marc G. Bellemare,et al.  The Arcade Learning Environment: An Evaluation Platform for General Agents , 2012, J. Artif. Intell. Res..

[53]  Jiajun Wu,et al.  Physics 101: Learning Physical Object Properties from Unlabeled Videos , 2016, BMVC.

[54]  Silvio Savarese,et al.  Learning Transferrable Representations for Unsupervised Domain Adaptation , 2016, NIPS.

[55]  Kate Saenko,et al.  Deep CORAL: Correlation Alignment for Deep Domain Adaptation , 2016, ECCV Workshops.

[56]  George Drettakis,et al.  Scalable inside-out image-based rendering , 2016, ACM Trans. Graph..

[57]  Ali Farhadi,et al.  Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[58]  Vladlen Koltun,et al.  Playing for Data: Ground Truth from Computer Games , 2016, ECCV.

[59]  Jitendra Malik,et al.  View Synthesis by Appearance Flow , 2016, ECCV.

[60]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[61]  Abhinav Gupta.  Supersizing Self-Supervision: Learning Perception and Action Without Human Supervision , 2016 .

[62]  Jitendra Malik,et al.  Learning to Poke by Poking: Experiential Learning of Intuitive Physics , 2016, NIPS.

[63]  Thomas Brox,et al.  Multi-view 3D Models from Single Images with a Convolutional Network , 2015, ECCV.

[64]  Antonio M. López,et al.  The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[65]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[66]  Wojciech Jaskowski,et al.  ViZDoom: A Doom-based AI research platform for visual reinforcement learning , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).

[67]  Sergey Levine,et al.  End-to-End Training of Deep Visuomotor Policies , 2015, J. Mach. Learn. Res..

[68]  Katja Hofmann,et al.  The Malmo Platform for Artificial Intelligence Experimentation , 2016, IJCAI.

[69]  Sergey Levine,et al.  Deep spatial autoencoders for visuomotor learning , 2015, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[70]  Kate Saenko,et al.  Return of Frustratingly Easy Domain Adaptation , 2015, AAAI.

[71]  Qiao Wang,et al.  VirtualWorlds as Proxy for Multi-object Tracking Analysis , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[72]  Abhinav Gupta,et al.  Supersizing self-supervision: Learning to grasp from 50K tries and 700 robot hours , 2015, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[73]  Wojciech Zaremba,et al.  OpenAI Gym , 2016, ArXiv.

[74]  Thomas A. Funkhouser,et al.  MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments , 2017, ArXiv.

[75]  Jana Kosecka,et al.  A dataset for developing and benchmarking active vision , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[76]  Germán Ros,et al.  CARLA: An Open Urban Driving Simulator , 2017, CoRL.

[77]  Alexei A. Efros,et al.  Curiosity-Driven Exploration by Self-Supervised Prediction , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[78]  Vladlen Koltun,et al.  Photographic Image Synthesis with Cascaded Refinement Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[79]  Silvio Savarese,et al.  Joint 2D-3D-Semantic Data for Indoor Scene Understanding , 2017, ArXiv.

[80]  Vladlen Koltun,et al.  Learning to Act by Predicting the Future , 2016, ICLR.

[81]  Alex Bewley,et al.  Addressing appearance change in outdoor robotics with adversarial domain adaptation , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[82]  Yang Gao,et al.  End-to-End Learning of Driving Models from Large-Scale Video Datasets , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[83]  Configurable, Photorealistic Image Rendering and Ground Truth Synthesis by Sampling Stochastic Grammars Representing Indoor Scenes , 2017, ArXiv.

[84]  Wojciech Zaremba,et al.  Domain randomization for transferring deep neural networks from simulation to the real world , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[85]  Ali Farhadi,et al.  Target-driven visual navigation in indoor scenes using deep reinforcement learning , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[86]  Jia Xu,et al.  Fast Image Processing with Fully-Convolutional Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[87]  Matthias Nießner,et al.  Matterport3D: Learning from RGB-D Data in Indoor Environments , 2017, 2017 International Conference on 3D Vision (3DV).

[88]  Thomas A. Funkhouser,et al.  Semantic Scene Completion from a Single Depth Image , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[89]  Ashish Kapoor,et al.  AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles , 2017, FSR.

[90]  Yuval Tassa,et al.  Emergence of Locomotion Behaviours in Rich Environments , 2017, ArXiv.

[91]  Alec Radford,et al.  Proximal Policy Optimization Algorithms , 2017, ArXiv.

[92]  Sergey Levine,et al.  (CAD)$^2$RL: Real Single-Image Flight without a Single Real Image , 2016, Robotics: Science and Systems.

[93]  Sergey Levine,et al.  Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection , 2016, Int. J. Robotics Res..

[94]  Yuandong Tian,et al.  Building Generalizable Agents with a Realistic and Rich 3D Environment , 2018, ICLR.

[95]  Qi Wu,et al.  Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[96]  Alexey Dosovitskiy,et al.  End-to-End Driving Via Conditional Imitation Learning , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[97]  Silvio Savarese,et al.  GONet: A Semi-Supervised Deep Learning Approach For Traversability Estimation , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[98]  Chenfanfu Jiang,et al.  Configurable 3D Scene Synthesis and 2D Image Rendering with Per-pixel Ground Truth Using Stochastic Grammars , 2017, International Journal of Computer Vision.

[99]  Bolei Zhou,et al.  Places: A 10 Million Image Database for Scene Recognition , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[100]  Rahul Sukthankar,et al.  Cognitive Mapping and Planning for Visual Navigation , 2017, International Journal of Computer Vision.

[101]  Wolfram Burgard,et al.  VR-Goggles for Robots: Real-to-Sim Domain Adaptation for Visual Control , 2018, IEEE Robotics and Automation Letters.