Deep Neural Network for Real-Time Autonomous Indoor Navigation

Abstract

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.

References in corpus (1)

• Understanding Neural Networks Through Deep Visualization

Cited by in corpus (13)

• From Perception to Decision: A Data-driven Approach to End-to-end Motion Planning for Autonomous Ground Robots
• Sim4CV: A Photo-Realistic Simulator for Computer Vision Applications
• Towards Monocular Vision based Obstacle Avoidance through Deep Reinforcement Learning
• Neural Network-based Flight Control Systems: Present and Future
• Combining Optimal Control and Learning for Visual Navigation in Novel Environments
• Deep Drone Racing: Learning Agile Flight in Dynamic Environments
• Generating Robust Supervision for Learning-Based Visual Navigation Using Hamilton-Jacobi Reachability
• Learning to Navigate Autonomously in Outdoor Environments : MAVNet
• Teaching UAVs to Race: End-to-End Regression of Agile Controls in Simulation
• Drone Path-Following in GPS-Denied Environments using Convolutional Networks
• VGF-Net: Visual-Geometric Fusion Learning for Simultaneous Drone Navigation and Height Mapping
• Vision-Based Autonomous Drone Control using Supervised Learning in Simulation
• Learn by Observation: Imitation Learning for Drone Patrolling from Videos of A Human Navigator