Deep Neural Network for Real-Time Autonomous Indoor Navigation

Autonomous indoor navigation of Micro Aerial Vehicles (MAVs) possesses many challenges. One main reason is that GPS has limited precision in indoor environments. The additional fact that MAVs are not able to carry heavy weight or power consuming sensors, such as range finders, makes indoor autonomous navigation a challenging task. In this paper, we propose a practical system in which a quadcopter autonomously navigates indoors and finds a specific target, i.e., a book bag, by using a single camera. A deep learning model, Convolutional Neural Network (ConvNet), is used to learn a controller strategy that mimics an expert pilot's choice of action. We show our system's performance through real-time experiments in diverse indoor locations. To understand more about our trained network, we use several visualization techniques.

[1]  G. Gerhart,et al.  Stereo vision and laser odometry for autonomous helicopters in GPS-denied indoor environments , 2009 .

[2]  Alexander Mordvintsev,et al.  Inceptionism: Going Deeper into Neural Networks , 2015 .

[3]  Arun K. Somani,et al.  Monocular vision SLAM for indoor aerial vehicles , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  Daniel Cremers,et al.  LSD-SLAM: Large-Scale Direct Monocular SLAM , 2014, ECCV.

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

[6]  Ian D. Reid,et al.  RSLAM: A System for Large-Scale Mapping in Constant-Time Using Stereo , 2011, International Journal of Computer Vision.

[7]  Nicholas Roy,et al.  State estimation for aggressive flight in GPS-denied environments using onboard sensing , 2012, 2012 IEEE International Conference on Robotics and Automation.

[8]  Dario Floreano,et al.  Quadrotor Using Minimal Sensing For Autonomous Indoor Flight , 2007 .

[9]  Florian Schweiger,et al.  TUMindoor: An extensive image and point cloud dataset for visual indoor localization and mapping , 2012, 2012 19th IEEE International Conference on Image Processing.

[10]  Marc Pollefeys,et al.  Vision-based autonomous mapping and exploration using a quadrotor MAV , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Roland Chapuis,et al.  Radar Scan Matching SLAM Using the Fourier-Mellin Transform , 2009, FSR.

[12]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[13]  Martial Hebert,et al.  Learning monocular reactive UAV control in cluttered natural environments , 2012, 2013 IEEE International Conference on Robotics and Automation.

[14]  Ashutosh Saxena,et al.  Autonomous MAV flight in indoor environments using single image perspective cues , 2011, 2011 IEEE International Conference on Robotics and Automation.

[15]  Nicholas Roy,et al.  Autonomous Flight in Unknown Indoor Environments , 2009 .

[16]  Hod Lipson,et al.  Understanding Neural Networks Through Deep Visualization , 2015, ArXiv.

[17]  Antonio Torralba,et al.  Recognizing indoor scenes , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  D. Powell,et al.  Land-vehicle navigation using GPS , 1999, Proc. IEEE.

[19]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.