UAV Framework for Autonomous Onboard Navigation and People/Object Detection in Cluttered Indoor Environments

Juan Sandino,Frederic Maire,Fernando Vanegas,Felipe Gonzalez,Peter Caccetta,Conrad Sanderson

doi:10.3390/rs12203386

Abstract

Response efforts in emergency applications such as border protection, humanitarian relief and disaster monitoring have improved with the use of Unmanned Aerial Vehicles (UAVs), which provide a flexibly deployed eye in the sky. These efforts have been further improved with advances in autonomous behaviours such as obstacle avoidance, take-off, landing, hovering and waypoint flight modes. However, most UAVs lack autonomous decision making for navigating in complex environments. This limitation creates a reliance on ground control stations to UAVs and, therefore, on their communication systems. The challenge is even more complex in indoor flight operations, where the strength of the Global Navigation Satellite System (GNSS) signals is absent or weak and compromises aircraft behaviour. This paper proposes a UAV framework for autonomous navigation to address uncertainty and partial observability from imperfect sensor readings in cluttered indoor scenarios. The framework design allocates the computing processes onboard the flight controller and companion computer of the UAV, allowing it to explore dangerous indoor areas without the supervision and physical presence of the human operator. The system is illustrated under a Search and Rescue (SAR) scenario to detect and locate victims inside a simulated office building. The navigation problem is modelled as a Partially Observable Markov Decision Process (POMDP) and solved in real time through the Augmented Belief Trees (ABT) algorithm. Data is collected using Hardware in the Loop (HIL) simulations and real flight tests. Experimental results show the robustness of the proposed framework to detect victims at various levels of location uncertainty. The proposed system ensures personal safety by letting the UAV to explore dangerous environments without the intervention of the human operator.

Highlights

High resolution satellite and aircraft imagery has and can assist in relief efforts after natural disasters such as earthquakes, floods, landslides and bush/forest fires
The metrics consisted on the victim confirmation rate, the victim miss rate, the Unmanned Aerial Vehicles (UAVs) collision rate, the UAV navigation rate flying beyond the area limits, the occurrences where the aircraft followed a sub-optimal path, and the timeout rate (i.e., k > 480 steps, or t ≥ 480 s)
A few timeout stopping conditions were triggered in missions with uniform clusters because the UAV kept navigating in unexplored areas after flying above and not detecting the mannequin

Summary

Introduction

High resolution satellite and aircraft imagery has and can assist in relief efforts after natural disasters such as earthquakes, floods, landslides and bush/forest fires. Studies on improving disaster management efforts in urban and peri-urban indoor areas are key to decrease the number of fatalities. Intelligent aerial platforms such as Unmanned Aerial Vehicles (UAVs)—commonly referred as drones—have improved response efforts in time-critical applications such as border protection, humanitarian relief and disaster monitoring [4]. The information acquired about the surveyed environment and their targets is in most cases, inaccurate due to imperfections in the UAV sensor readings, occlusion from obstacles and challenging surveying conditions. These imperfections restrict the inference of the actual conditions of the environment (e.g., search extent, obstacles, wind disturbances) and victims (e.g., location, classification, quantity). A possible approach to model sequential decision-making processes when dealing with high levels of uncertainty is based on POMDPs [41]

Methods

Results

Discussion

Conclusion