Learning to Navigate from Simulation via Spatial and Semantic Information Synthesis

While training an end-to-end navigation network in the real world is usually of high cost, simulations provide a safe and cheap environment in this training stage. However, training neural network models in simulations brings up the problem of how to effectively transfer the model from simulations to the real world (sim-to-real). In this work, we regard the environment representation as a crucial element in this transfer process and propose a visual information pyramid (VIP) model to systematically investigate a practical environment representation. A novel representation composed of spatial and semantic information synthesis is then established accordingly. To explore the effectiveness of this representation, we compared the performance with representations popularly used in the literature in both simulated and real-world scenarios. Results suggest that our proposed environment representation behaves best. Furthermore, an analysis on the feature map is implemented to investigate the effectiveness through inner reaction, which could be irradiative for future researches on end-to-end navigation.

[1]  T. Hafting,et al.  Microstructure of a spatial map in the entorhinal cortex , 2005, Nature.

[2]  Roberto Cipolla,et al.  Semantic object classes in video: A high-definition ground truth database , 2009, Pattern Recognit. Lett..

[3]  Anna Choromanska,et al.  Sensor modality fusion with CNNs for UGV autonomous driving in indoor environments , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[4]  Lutz Frommberger.  Generalization and Transfer Learning in Noise-Affected Robot Navigation Tasks , 2007, EPIA Workshops.

[5]  V. Polotski,et al.  Occlusions in obstacle detection for safe navigation , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[6]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[8]  David Hsu,et al.  Intention-aware online POMDP planning for autonomous driving in a crowd , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[9]  Kaiming He,et al.  Mask R-CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[10]  Carlos R. del-Blanco,et al.  DroNet: Learning to Fly by Driving , 2018, IEEE Robotics and Automation Letters.

[11]  Ming Liu,et al.  A deep-network solution towards model-less obstacle avoidance , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[12]  Wei Gao,et al.  Intention-Net: Integrating Planning and Deep Learning for Goal-Directed Autonomous Navigation , 2017, CoRL.

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

[14]  Jonathan P. How,et al.  Socially aware motion planning with deep reinforcement learning , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[15]  Marc Pollefeys,et al.  Reactive avoidance using embedded stereo vision for MAV flight , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[16]  Geoffrey J. Gordon,et al.  No-Regret Reductions for Imitation Learning and Structured Prediction , 2010, ArXiv.

[17]  Andrew Howard,et al.  Design and use paradigms for Gazebo, an open-source multi-robot simulator , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[18]  Jürgen Schmidhuber,et al.  A Machine Learning Approach to Visual Perception of Forest Trails for Mobile Robots , 2016, IEEE Robotics and Automation Letters.

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

[20]  Yoshua Bengio,et al.  The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

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

[22]  Jitendra Malik,et al.  Indoor Scene Understanding with RGB-D Images: Bottom-up Segmentation, Object Detection and Semantic Segmentation , 2015, International Journal of Computer Vision.

[23]  Zhang-Wei Hong,et al.  Virtual-to-Real: Learning to Control in Visual Semantic Segmentation , 2018, IJCAI.

[24]  Ming Liu,et al.  Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[25]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

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

[27]  Noah Snavely,et al.  Unsupervised Learning of Depth and Ego-Motion from Video , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Wolfram Burgard,et al.  Socially Compliant Navigation Through Raw Depth Inputs with Generative Adversarial Imitation Learning , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[29]  Yann LeCun,et al.  Off-Road Obstacle Avoidance through End-to-End Learning , 2005, NIPS.

[30]  Thorsten Joachims,et al.  Semantic Labeling of 3D Point Clouds for Indoor Scenes , 2011, NIPS.

[31]  Jana Kosecka,et al.  Visual Representations for Semantic Target Driven Navigation , 2018, 2019 International Conference on Robotics and Automation (ICRA).

[32]  Bernard Ghanem,et al.  Driving Policy Transfer via Modularity and Abstraction , 2018, CoRL.

[33]  Sascha Hornauer,et al.  Imitation Learning of Path-Planned Driving Using Disparity-Depth Images , 2018, ECCV Workshops.

[34]  Andreas Geiger,et al.  Conditional Affordance Learning for Driving in Urban Environments , 2018, CoRL.

[35]  Yoshua Bengio,et al.  A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policies , 2018, 2019 International Conference on Robotics and Automation (ICRA).

[36]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Cewu Lu,et al.  Virtual to Real Reinforcement Learning for Autonomous Driving , 2017, BMVC.

[38]  Razvan Pascanu,et al.  Sim-to-Real Robot Learning from Pixels with Progressive Nets , 2016, CoRL.

[39]  Nikolai Smolyanskiy,et al.  Toward low-flying autonomous MAV trail navigation using deep neural networks for environmental awareness , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[40]  Shahram Izadi,et al.  Modeling Kinect Sensor Noise for Improved 3D Reconstruction and Tracking , 2012, 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission.

[41]  Kate Saenko,et al.  Learning a visuomotor controller for real world robotic grasping using simulated depth images , 2017, CoRL.

[42]  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).

[43]  Chenliang Xu,et al.  Navigation by Imitation in a Pedestrian-Rich Environment , 2018, ArXiv.

[44]  M Sarcinelli-Filho,et al.  An efficient obstacle recognition system for helping mobile robot navigation , 2000 .

[45]  Abhinav Gupta,et al.  Learning to fly by crashing , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[46]  Bolei Zhou,et al.  Semantic Understanding of Scenes Through the ADE20K Dataset , 2016, International Journal of Computer Vision.

[47]  Jianxiong Xiao,et al.  DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).