Multi-Task Regression-Based Learning for Autonomous Unmanned Aerial Vehicle Flight Control Within Unstructured Outdoor Environments

Abstract

Increased growth in the global Unmanned Aerial Vehicles (UAV) (drone) industry has expanded possibilities for fully autonomous UAV applications. A particular application which has in part motivated this research is the use of UAV in wide area search and surveillance operations in unstructured outdoor environments. The critical issue with such environments is the lack of structured features that could aid in autonomous flight, such as road lines or paths. In this paper, we propose an End-to-End Multi-Task Regression-based Learning approach capable of defining flight commands for navigation and exploration under the forest canopy, regardless of the presence of trails or additional sensors (i.e. GPS). Training and testing are performed using a software in the loop pipeline which allows for a detailed evaluation against state-of-the-art pose estimation techniques.Our extensive experiments demonstrate that our approach excels in performing dense exploration within the required search perimeter, is capable of covering wider search regions, generalises to previously unseen and unexplored environments and outperforms contemporary state-of-the-art techniques.

The Use of Emerging Technologies DIoT: Elderly Daily Living in Post-Epidemic Era

“…These functions enable people to remotely control the devices and reduce body exposure in ADLs and interaction in planned tasks. DIoT depicts the fundamental of layered architecture control for UAV to perform in the different communication environment [12][13][14]. As shown in Figure 1, UAV has demonstrated its variety of civil usage for daily living purposes such as surveillance, delivery, and task performance in the segments of law enforcement [15], disaster rescue [16], journalism and filming [17], traffic load monitoring [18], and healthcare.…”

Online Deep Reinforcement Learning for Autonomous UAV Navigation and Exploration of Outdoor Environments

“…Similarly, the use of Long short-term memory (LSTM) [25] has been vastly explored [18], [26] and although significant improvements have been achieved, our previous work [27] demonstrates that to reach a meaningful understanding of the environment, the trained model tends to focus on high-level features from the set of input images. This subsequently results in the model becoming specialised within a single scenario/environment [28], thus nullifying the ability for generalisation and adaptability to changes in weather conditions or unseen environments.…”

A Secure Communication Protocol for Unmanned Aerial Vehicles

“…An Unmanned Aerial Vehicle is a pilotless aircraft without any crew on board [2,3]. They can operate completely autonomously [4,5] through autopilot, which means they can complete tasks without human interaction or can be non-autonomous with the help of remote control or a human pilot operating in runtime from a ground control station [6]. The most common use is either by the military [7][8][9] for battlefields or reconnaissance or by civilians for leisure and entertainment [10,11].…”