Assistive System for Navigating Complex Realistic Simulated World Using Reinforcement Learning

Finding a free path without obstacles or situation that pose minimal risk is critical for safe navigation. People who are sighted and people who are blind or visually impaired require navigation safety while walking on a sidewalk. In this paper we develop assistive navigation on a sidewalk by integrating sensory inputs using reinforcement learning. We train the reinforcement model in a simulated robotic environment which is used to avoid sidewalk obstacles. A conversational agent is built by training with real conversation data. The reinforcement learning model along with a conversational agent improved the obstacle avoidance experience about 2.5% from the base case which is 78.75%.

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

[2]  Leopoldo Acosta,et al.  A Combined Voxel and Particle Filter-Based Approach for Fast Obstacle Detection and Tracking in Automotive Applications , 2017, IEEE Transactions on Intelligent Transportation Systems.

[3]  Mohammed Yeasin,et al.  RNN and CNN for Way-Finding and Obstacle Avoidance for Visually Impaired , 2019, 2019 2nd International Conference on Data Intelligence and Security (ICDIS).

[4]  Hector D. Escobar-Alvarez,et al.  R‐ADVANCE: Rapid Adaptive Prediction for Vision‐based Autonomous Navigation, Control, and Evasion , 2018, J. Field Robotics.

[5]  M. Balakrishnan,et al.  'Smart' Cane for the Visually Impaired: Design and Controlled Field Testing of an Affordable Obstacle Detection System , 2010 .

[6]  Md. Forkan Uddin,et al.  Mitigating unfairness problem in WLANs caused by asymmetric co-channel interference , 2018, Int. J. Mob. Commun..

[7]  Majid Sarrafzadeh,et al.  The SmartCane system: an assistive device for geriatrics , 2008, BODYNETS.

[8]  Iwan Ulrich,et al.  The GuideCane-applying mobile robot technologies to assist the visually impaired , 2001, IEEE Trans. Syst. Man Cybern. Part A.

[9]  Ariffin Abdul Mutalib,et al.  Smart Cane: Assistive Cane for Visually-impaired People , 2011, ArXiv.

[10]  Richard W. Bohannon.  Comfortable and maximum walking speed of adults aged 20-79 years: reference values and determinants. , 1997, Age and ageing.

[11]  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).

[12]  David Pfeiffer.  The Stixel World , 2012 .

[13]  Andrew J. Barry.  High‐speed autonomous obstacle avoidance with pushbroom stereo , 2018, J. Field Robotics.

[14]  Kailun Yang,et al.  Long-Range Traversability Awareness and Low-Lying Obstacle Negotiation with RealSense for the Visually Impaired , 2018 .

[15]  Huai-Rong Shao,et al.  WiFi-based indoor positioning , 2015, IEEE Communications Magazine.

[16]  Weijian Hu,et al.  An Environmental Perception and Navigational Assistance System for Visually Impaired Persons Based on Semantic Stixels and Sound Interaction , 2018, 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[17]  Masayuki Murata,et al.  Achieving Practical and Accurate Indoor Navigation for People with Visual Impairments , 2017, W4A.

[18]  Yong Seon Moon,et al.  A method for object detection using point cloud measurement in the sea environment , 2017, 2017 IEEE Underwater Technology (UT).

[19]  Yunhao Liu,et al.  Peer-to-Peer Indoor Navigation Using Smartphones , 2017, IEEE Journal on Selected Areas in Communications.

[20]  Mohammed Yeasin,et al.  An Interactive Device for Ambient Awareness on Sidewalk for Visually Impaired , 2018, 2018 IEEE International Smart Cities Conference (ISC2).

[21]  Tie Zhang,et al.  An indoor mobile robot navigation technique using odometry and electronic compass , 2017 .

[22]  Leonidas J. Guibas,et al.  PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Mohammed Yeasin,et al.  Image Captioning for Ambient Awareness on a Sidewalk , 2018, 2018 1st International Conference on Data Intelligence and Security (ICDIS).

[24]  Fei Li,et al.  Design and implementation of a novel obstacle avoidance scheme based on combination of CNN-based deep learning method and liDAR-based image processing approach , 2018, J. Intell. Fuzzy Syst..

[25]  Abdelsalam Helal,et al.  Drishti: an integrated navigation system for visually impaired and disabled , 2001, Proceedings Fifth International Symposium on Wearable Computers.

[26]  Shraga Shoval,et al.  NavBelt and the Guide-Cane [obstacle-avoidance systems for the blind and visually impaired] , 2003, IEEE Robotics Autom. Mag..

[27]  R. Sherline Jesie.  Advanced talking navigation cane for visually impaired using capacitive touch keypad , 2015, 2015 International Conference on Circuits, Power and Computing Technologies [ICCPCT-2015].

[28]  Arno Solin,et al.  PIVO: Probabilistic Inertial-Visual Odometry for Occlusion-Robust Navigation , 2018, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[29]  Mohammed Yeasin,et al.  Optimization and evaluation of deep architectures for ambient awareness on a sidewalk , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[30]  Ashutosh Saxena,et al.  High speed obstacle avoidance using monocular vision and reinforcement learning , 2005, ICML.

[31]  Nick Pawlowski,et al.  Rasa: Open Source Language Understanding and Dialogue Management , 2017, ArXiv.

[32]  Hung-Huan Liu,et al.  WiFi-based indoor positioning for multi-floor Environment , 2011, TENCON 2011 - 2011 IEEE Region 10 Conference.