Deep Neural Network for Real-Time Autonomous Indoor Navigation

By Dong Ki Kim, Tsuhan Chen. 2015

125 citations recorded by the source corpus.

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.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing (2018, background): “Output representations range from predicting discrete navigation commands (classification in action space) [11], [7], [15] to direct regression of control signals [19].”
Deep Drone Racing: Learning Agile Flight in Dynamic Environments (2018, background): “Known output representations range from predicting discrete navigation commands [15, 17]— which enables high robustness but leads to low agility—to direct control [14]—which can lead to highly agile control, but suffers from high sample complexity.”
(CAD)$^2$RL: Real Single-Image Flight without a Single Real Image (2016, methodology): “Learning has previously been used to detect obstacles for indoor flight [5, 19], as well as to directly learn a turn classifier for outdoor forest trail following [14].”
Teaching UAVs to Race: End-to-End Regression of Agile Controls in Simulation (2017, background): “, the trained network leads to a slow, non-smooth (zig-zag) trajectory at a ﬁxed altitude above the ground. It is worthwhile to note that indoor UAV control using DNNs has also been recently explored [1,16,41]. Importance of Exploration in Supervised Learning. In imitation learning [14], the ‘expert”
From perception to decision: A data-driven approach to end-to-end motion planning for autonomous ground robots (2016, background): “[15] extended this approach to a hallway application where they learn translational and rotational velocities.”
Combining Optimal Control and Learning for Visual Navigation in Novel Environments (2019, background): “There has been a recent interest in employing end-toend learning for training policies for goal-driven navigation [8, 9, 10, 11].”
Sim4CV: A Photo-Realistic Simulator for Computer Vision Applications (2017, unknown): “Work by [4; 5; 50; 42; 35; 1; 20; 48] show that with suﬃcient training data and augmented camera views autonomous driving and ﬂight can be learned by a DNN.”
Teaching UAVs to Race Using UE4Sim (2017, background): “It is worthwhile to note that indoor UAV control using DNNs has also been recently explored [1, 17, 39].”
A Review of Deep Learning Methods and Applications for Unmanned Aerial Vehicles (2017, background): “Concerning the UAV indoor navigation task, recent advances have led to a successful application of CNNs in order to map images to high-level behaviour directives (e.g., turn left, turn right, rotate left, and rotate right) [38, 39].”
Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Mapless Navigation by Leveraging Prior Demonstrations (2018, background): “[14] present an IL approach for hallway navigation and collision avoidance for an unmanned aerial vehicle (UAV).”