Unmanned aerial vehicle (UAV) state estimation is fundamental across applications like robot navigation, autonomous driving, virtual reality (VR), and augmented reality (AR). This research highlights the critical role of robust state estimation in ensuring safe and efficient autonomous UAV navigation, particularly in challenging environments. We propose a deep learning-based adaptive sensor fusion framework for UAV state estimation, integrating multi-sensor data from stereo cameras, an IMU, two 3D LiDAR’s, and GPS. The framework dynamically adjusts fusion weights in real time using a long short-term memory (LSTM) model, enhancing robustness under diverse conditions such as illumination changes, structureless environments, degraded GPS signals, or complete signal loss where traditional single-sensor SLAM methods often fail. Validated on an in-house integrated UAV platform and evaluated against high-precision RTK ground truth, the algorithm incorporates deep learning-predicted fusion weights into an optimization-based odometry pipeline. The system delivers robust, consistent, and accurate state estimation, outperforming state-of-the-art techniques. Experimental results demonstrate its adaptability and effectiveness across challenging scenarios, showcasing significant advancements in UAV autonomy and reliability through the synergistic integration of deep learning and sensor fusion.

Unmanned Aerial Vehicles (UAV’s) State estimation is fundamental aspect across a wide range of applications, including robot navigation, autonomous driving, virtual reality, and augmented reality (AR). The proposed research emphasizes the vital role of robust state estimation in ensuring the safe navigation of autonomous UAVs. In this paper, we developed an optimization-based odometry state estimation framework that is compatible with multiple sensor setups. Our evaluation of the system is conducted using inhouse integrated UAV platform outfitted with multiple sensors including stereo cameras, an IMU, LiDAR sensors and GPS-RTK for ground truth comparison. The algorithm delivers robust and consistent UAV state estimation in various conditions including illumination changes, feature or structure-less environment or even during degraded Global Positioning System (GPS) signals or total signal loss, where single sensor SLAM mostly fails. The experimental findings demonstrate that the proposed method is superior in compare to current state-of-the-art techniques.

Remote locations including but not limited to, far-reaching offshore airspaces, provide limited communications capabilities between equipment and ground stations. The case for DAVs is no exception, all the while requiring swift decisions because of the high speeds, lack of detailed real-time weather data, and complex applications. With the limitations and require-ments at hand, we propose real-time edge fault-tolerant SCADA (detection of anomalies) based on learning continuous sequential data for efficient control of the UAV's altitude and heading. Our data-driven solution, involving an extensive suite of sensory data processing, demonstrates the potential to significantly reduce communication and decision-making capabilities in cases of remote locations, enabling safer and more efficient UAV operations. The proposed system leverages machine learning algorithms to analyze real-time data from both extrinsic and intrinsic UAV sensors, allowing for predictive control and fault detection. By processing data at the edge, our solution reduces the need for bandwidth-intensive data transmission minimizing latency and ensuring swift and reliable decision-making. We show the data collection and training in a high-fidelity aviation simulator that closely matches real flight conditions.

With the development of Autonomous Unmanned Aerial Vehicle's (UAV's), Precise state estimation is a fundamental aspect of autonomous flight and plays a critical role in enabling robots specially in GPS denied environment to operate safely, reliably, and effectively across a wide range of applications and operational scenarios. In this paper, we propose a tightly-coupled multi-sensor filtering framework for robust UAV/UGV state estimation, which integrates data from an Inertial Measurement Unit (IMU), a stereo camera, GPS, and 3D range measurements from two Light Detection and Ranging (LiDAR) sensors. The proposed LGVINS system significantly improves the accuracy and robustness of state estimation in both structured and unstructured outdoor environments, such as bridge inspections, open fields, urban city and areas near buildings. It also improves positioning accuracy in scenarios with or without GPS signals. The goal is to exploit the fact that these sensor modalities have mutually exclusive strengths, the visual, inertial and the Lidar sensor techniques are implemented to compensate for the robots state estimate errors in multiple outdoor challenging environment. It effectively reduces long-term trajectory drift and ensures smooth, continuous state estimation, regardless of GPS satellite availability. We demonstrate and evaluate the LGVINS approach on public dataset as well as our own dataset collected from the proposed hardware integration on UAV, deployed on computationally-constrained systems. This demonstrates that the proposed system achieves higher accuracy and robustness in state estimation across various environments compared to currently available methods.

Robotic surveillance, monitoring, and maintenance problem are open-for-research domains required by the military, industrial facilities, ports, airports, and various indoor and outdoor venues each having different needs. Recent work in path planning of aerial robotics is an emerging field of the surveillance problem, particularly for unstructured or unexplored areas. The nature of path planning problems with different foreign elements like wind, rain, and others escalate the cost of complex computation and power consumption. Due to constraints in payload and endurance, algorithms based on pose-graph, both from the run-time and solution point of view become inefficient when working with unstructured spaces. We propose a simple but effective Clipped Double Q-learning [1] based deep reinforcement learning algorithm (CDDQN)for efficient path planning under the influence of wind and with improved computational efficiency for surveillance in a port area. In the proposed algorithm we have formulated a dense reward structure in consideration of wind’s effect on power consumption and time to reach the destination which led to a robust path planning system for high wind scenarios.

This article presents an online local path planning approach for autonomous drone navigating a 2D plane in an unknown, indoor corridor-like environment. The proposed method utilizes a reinforcement learning approach for training a local path planner for navigation in the said environment. With a continuous actor-critic learning automaton (CACLA) applied for continuous action spaces, the proposed algorithm uses a reward structure that formulates a balancing function that gives reward based on balancing the vehicle between artificial potential hills. The drone thereby learns steering control and obstacle avoidance while maintaining a central aligned position with respect to the unknown hallways or corridors. A novel CACLA algorithm and incorporation of a special experience replay memory for the better converging tendency of drone toward the balancing point have been introduced in this article. The proposed reinforcement learning-based online local path planner has been tested on a simulated drone in Gazebo environment.

The paper describes an Internet of Vehicle (IoV) communication technology to control and monitor in-vehicle prototype-based devices as connected sensors and actuators. In addition to providing an Internet of Things (IoT) platform over the mobile application system, the proposed solution brings a fundamental change in reducing human energy as well as time. The IoV communication technology delivers real-time controlling, monitoring, and gathering of information on the vehicular network. Moreover, it provides a key solution for the processing, computing, sharing, and safe release of information onto the vehicular information platform. The ideal purpose of the work is to develop a signal generating kit which locks/unlocks the car doors anywhere through a tablet or smartphone. Moreover, we can monitor parameters through a smartphone application, the monitoring of tire air pressure, and fuel level through respective sensors network. For the purpose of the above-cited subject, the article aimed at developing a smart vehicle management technology.

In this paper, a modified heuristic guided Artificial Potential Field (APF) based algorithm has been proposed to find a practical trajectory for an Autonomous Unmanned Aerial Vehicle (UAV) path planning. The local minima are encountered in the conventional APF algorithm due to the cancellation of attractive and repulsive potential while avoiding unknown obstacles within the desired path, which results in the trapping of the agent before reaching the goal. Consequently, the traditional APF technique is therefore no longer advantageous in such cases. So in this proposed perpendicular approach based on APF helps to avoid such local minima. The advantage of the newly proposed method is the low computing time that lines up with the standard global path planner method. The proposed algorithm is tested and validated against existing general potential field techniques for different simulation scenarios in a 3D simulated environment using ROS and Gazebo supported PX4-SITL. The results have been presented for drone navigation and obstacle avoidance for the different scenarios in a simulated environment.

The paper presents an autonomous vision-based guidance and mapping algorithm for navigation of drones in a GPS-denied environment. We propose a novel algorithm that accurately uses OpenCV ArUco markers as a reference for path detection and guidance using a stereo camera. It enables the drone to navigate and map an environment using vision-based path planning. Special attention has been given towards the robustness of guidance and controlling strategy, accuracy in the vehicle pose estimation and real-time operation. The proposed algorithm is evaluated in a 3D simulated environment using ROS and Gazebo. The results have been presented for drone navigation in a maze pattern indoor scenario. Evaluation of the given guidance system in the simulated environment suggests that the proposed system can be used for generating a 2D/3D occupancy grid map autonomously without the use of high-level algorithms and expensive sensors such as lidars.