Comparative Analysis Between Recurrent Convolutional and Convolutional Neural Networks for Horizon Detection

This paper proposes a completely wireless-based navigation system for high-speed navigation for unmanned ground vehicles (UGVs) on the varied landscape. This paper presents huge, precisely adjusted and time-synchronized datasets, accumulated outside, in controlled natural conditions, utilizing an automated ground vehicle e(UGV), furnished with a wide assortment of sensors to gauge the dynamic field. The hardware circuit is created in the short separation radar of the UGV way shape and longitudinal speed. Dynamic constraints, terrain conditions, and route conditions can be expressed in this space. A move is picked inside set of performance limits, in light of the potential field slope. As opposed to customary potential field techniques, the proposed strategy is dependent upon neighbourhood greatest issues, instead of nearby least. It is demonstrated that a basic randomization method can be utilized to address this issue. Recreation and exploratory outcomes show that the proposed technique can effectively explore a UGV between pre-characterized waypoints at rapid while maintaining a strategic distance from obscure perils. Further, vehicle speed and ebb and flow are controlled to stay away from roll over and over the top side slip. The technique is computationally proficient, and along these lines appropriate for on-board continuous execution. Keywords: Guidance System, Radar System, Object Detection Algorithm, Robot Control. Cite this Article Pintoo Nishad, Rajat Mishra, Satyam Shivansh, Rajat Agarwal, Raj Bharthwal, Ram Sewak Singh. Autonomous Military Robot with Short Range Radar and Guidance System. Journal of Microelectronics and Solid State Devices . 2020; 7(2): 4–8p.

The autonomous landing of fixed-wing unmanned aerial vehicles (UAVs) on moving unmanned ground vehicles (UGVs) demands precise spatial synchronization of both vehicle systems. To achieve this goal, using individual GNSS receivers and additional sensors for both vehicles and having the vehicles exchange their respective 6D pose via radio communication is a straightforward approach for mutual localization. However, failure of the radio communication or individual sensors can critically affect the safety of the landing maneuver without suitable additional sensors or fallback systems. In this work, we present and compare two methods for estimating the relative 6D pose between a UGV and a UAV using camera systems attached to the UGV. The first approach uses a stereo grayscale camera setup with fiducial markers on the underside of the wings of the UAV. The second approach uses a single RGB camera and a convolutional neural network (CNN) trained on synthetic data, which is combined with a pose tracking filter to improve the update rate. Requirements for the pose estimation system are an average position error below 0.5 m and an orientation angle error below 10 deg, while the update rate should be at least 20 Hz. Different experiments with a demonstrator vehicle setup are presented, showing the performance and advantages of the respective approaches. During flight experiments with eleven flyovers, the CNN-based system was consistently able to detect the UAV pose, while the marker-based system had detections in seven cases. The CNN-based system had RMS position errors between 0.19 m and 1.36 m, and RMS yaw angle errors between 1.2 deg and 7.7 deg, which is an average improvement of 0.33 m and 5.6 deg, respectively, compared to the marker-based system. In future work, the pose estimation will be tested in the control loop with an automated UAV and UGV.

In this paper, we propose an autonomous navigation for Unmanned Ground Vehicles (UGVs) by a path selection method based on local features of terrain in unknown outdoor rough terrain environment. The correlation between a local terrain feature obtained from a path and a value of the path obtained from the global path planning is extracted in advance. When UGV comes to a branch while it is running, the value of path is estimated using the correlation with local terrain feature. Thereby, UGV navigation is performed by path selection under the criterion of shortest time in unknown outdoor environment. We experimented on a simulator and confirmed that the proposed method can select more effective paths in comparison with a simple path selection method.

Sensor-centric navigation of unmanned ground vehicles (UGVs) operating in rugged and expansive terrains requires the competency to evaluate the utility of sensor information such that it results in intelligent behavior of the vehicles. In this paper, we propose an entropic information metric for the above purpose where entropy is used to quantify the probabilistic uncertainty in sensor measurements. We present results using data obtained from field trials on an unmanned vehicle to substantiate the utility of the proposed metric. We also show how low and high level tasks can be predicated upon this metric in potential application areas related to autonomous vehicle navigation.

In this paper, we present a novel integrated vehicular system using collaborative unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) for autonomous exploration, mapping, and navigation in GPS-denied 3-dimensional (3-D) unknown environments. The system implements a novel two-layered exploration strategy to decompose the perception task into a coarse exploration layer and a fine mapping layer. The coarse exploration makes use of a UGV to carry out fast autonomous exploration and active 2.5D simultaneous localization and mapping (SLAM) to generate a coarse environment model, which serves as a navigation reference for subsequent complementary 3-D fine mapping conducted by a UAV. The two layers share a novel optimized exploration path planning and navigation framework, which provides optimal exploration paths and integrates the collaborative exploration and mapping efforts through an OctoMap-based volumetric motion planning interface. The proposed system provides an efficient pipeline of fast environment perception taking advantages of the agility of the UAVs as well as the powerful computation resource aboard UGVs, also allowing assistive local perception with augmented object information when necessary. The effectiveness of our system is verified by both simulations and experiments, which demonstrate its capability of implementing heterogeneous UAV and UGV collaborative exploration and structural reconstruction of the environments through active SLAM, providing optimized perception for navigation tasks.

In the research reported in this paper, we propose to overcome the unavailability of Global Positioning System (GPS) using combined information obtained from a scanning LADAR rangefinder on an Unmanned Ground Vehicle (UGV) and a LADAR mounted on an Unmanned Aerial Vehicle (UAV) that flies over the terrain being traversed. The approach to estimate and update the position of the UGV involves registering range data from the two LADARs using a combination of a feature-based registration method and a modified version of the well-known Iterative Closest Point (ICP) algorithm. Registration of range data thus guarantees an estimate of the vehicle's position even when only one of the vehicles has GPS information. Additionally, such registration over time (i.e., from sample to sample), enables position information to be maintained even when both vehicles can no longer maintain GPS contact. The approach has been validated by conducting systematic experiments on complex real-world data.

We study the problem of covering an environment using an Unmanned Aerial Vehicle (UAV) with limited battery capacity. We consider a scenario where the UAV can land on an Unmanned Ground Vehicle (UGV) and recharge the onboard battery. The UGV can also recharge the UAV while transporting the UAV to the next take-off site. We present an algorithm to solve a new variant of the area coverage problem that takes into account this symbiotic UAV and UGV system. The input consists of a set of boustrophedon cells -- rectangular strips whose width is equal to the field-of-view of the sensor on the UAV. The goal is to find a coordinated strategy for the UAV and UGV that visits and covers all cells in minimum time, while optimally finding how much to recharge, where to recharge, and when to recharge the battery. This includes flight time for visiting and covering all cells, recharging time, as well as the take-off and landing times. We show how to reduce this problem to a known NP-hard problem, Generalized Traveling Salesperson Problem (GTSP). Given an optimal GTSP solver, our approach finds the optimal coverage paths for the UAV and UGV. Our formulation models multi-rotor UAVs as well as hybrid UAVs that can operate in fixed-wing and Vertical Take-off and Landing modes. We evaluate our algorithm through simulations and proof-of-concept experiments.

The use of unmanned aerial vehicles (UAV) for aid in unmanned ground vehicle (UGV) navigation makes it possible to plan routes more efficiently. Aerial images contain information about the environment that would be hard to obtain from the surface. This can be exploited to provide ground robots with route instructions. Digital image processing and computer vision techniques can identify regions of interest for UGV traversal. This article brings forth the concept of traversal difficulty image (TDI) and proposes techniques for TDI computation, with images taken from UAVs as input. We analyze the performance of four techniques and our results show that at least three of them can consistently identify levels of traversal difficulty associated with regions in the input image.

The use of unmanned ground vehicles (mobile robots) and unmanned aerial vehicles (drones) in the civil infrastructure asset management sector: Applications, robotic platforms, sensors, and algorithms

Over the past few decades, the usage of unmanned vehicles has grown exponentially, expanding into applications such as the automation of industrial processes and automobiles. However, their utility has often been limited by operational concerns. Fully controlled unmanned vehicles require multiple human operators, while their fully autonomous counterparts lack the ability to handle the complex maneuvers necessary in natural disaster relief and/or search and rescue situations. Semi-autonomous UAVs offer a feasible compromise between the two extremes. In this scenario, an unmanned aerial vehicle (UAV) sends birds-eye images of the terrain beneath it to a computing cluster, which will identify easily traversable terrain and generate a path of least risk to an unmanned ground vehicle (UGV). If the path's risk is below a certain threshold, then the UGV will be permitted to proceed on its own. Otherwise, a human operator will be notified, so that he or she may control the UGV directly until it exits the most dangerous terrain. This paradigm allows a single operator to manage several UAVs simultaneously.

This paper focuses on the real time implementation of cooperative navigation aiding for a small unmanned aerial vehicle (UAV) based on vision systems on board unmanned ground vehicles (UGV). In urban environments the signal quality of global satellite navigation systems (GNSS) often is bad or signals are even lost, so that the navigation solution of a UAV is aected. Especially in such situations the UAV’s geo-referenced position has to be known to ensure a safe guidance. A team of UGVs can overcome the problem of no GNSS position solution by the detection and tracking of the UAV in its on board images and the subsequent geo-localization. The determination of the UAV’s geo-referenced position can be achieved with several algorithms, depending on the number of UGVs. To integrate these position measurements in the UAV’s on board navigation computer the quality of the detection and geo-localization has to be estimated. All parts are implemented on embedded PC platforms. To allow real time usage on board the UGVs special algorithms have to be used for the most tasks, as image processing needs high computational power. The particular parts of this setup as well as the whole system are tested with experimental data.

This paper addresses the control of a formation composed of an unmanned ground vehicle (UGV) and an unmanned aerial vehicle (UAV). The formation navigates in a coordinated way, with the UAV following the UGV while keeping a relative pose with respect to the UGV as long as the UGV follows a specified path, so that the UAV can land on the UGV at any desired instant. This application is conceived in a context in which the UAV has finished a package delivery task and comes back to land over a platform used as a base for the package delivery operation. Experimental results are presented, which validate the approach adopted to accomplish such a task.

Ground-Air coordination is a very complex environment for a machine learning algorithm. We focus on the case where an Unmanned Aerial Vehicle (UAV) needs to support a group of Unmanned Ground Vehicles (UGVs). The UAV is required to broadcast an image that contains all UGVs, thus, offering a bird-eye-view on the group as a whole. The source of complexity in this task is twofold. First, coordination needs to occur without communication between the UAV and UGVs. Second, the ability of the UAV to sense the UGVs is coupled with the ability of the UAV to learn how to track laterally the UGVs and adapt its vertical position so that the images of the UGVs are appropriately spaced within the camera field of view. In this paper, we propose using the Deep Actor Network component of an Actor-Critic Deep Reinforcement Learning architecture as a supervised learner. The advantage of this approach is that it offers a step towards autonomous learning whereby the full Actor-Critic model can be utilized in the future. Human demonstrations are collected for the deep Actor network to learn from. The system is built using the Gazebo Simulator, Robot Operating System, and the OpenAI Gym. We show that the proposed setup is able to train the UAV to follow the UGVs while maintaining all UGVs within camera range in situations where UGVs are performing complex maneuvers.

We consider persistent (long-horizon) surveillance over an environment by using energy-constrained unmanned aerial vehicles (UAVs), which are supported by unmanned ground vehicles (UGVs) serving as mobile charging stations. The goal is to periodically visit a set of monitoring points by the UAVs while minimizing the maximum time between the consecutive visits to any of those points. In general, the optimal planning of UAVs and UGVs in such a persistent surveillance scenario is an NP-hard combinatorial optimization problem. Furthermore, the problem also demands a solution strategy that can successfully handle obstacles, especially on the ground, that are unknown a priori in many real-life scenarios. We present a scalable and robust approximate algorithm that is based on 1) forming uniform UAV-UGV teams, 2) decomposing the environment into maximal partitions that can be covered by the UAVs in a single fuel cycle as long as the UAVs are released sufficiently close to the centers of the partitions, 3) maintaining the teams uniformly distributed over a cyclic path traversing those partitions, and 4) having the UAVs in each team cover their current partition and be transported to the next partition while being recharged by the UGV. We support our proposed algorithm with some theoretical results and simulations.

In this paper, alternative direction finding methods have been proposed using deep learning techniques. Firstly, Regeression and Classification models have created by using Convolutional Neural Networks (CNNs). In the second Convolutional Neural Networks and Recurrent Neural Networks (RNNs) have been utilized in the proposed methods. Despite having vast amount of direction finding studies, utilization of neural networks is scarce in literature and past works mostly only includes usage of CNNs. In this study, direction finding is performed by learning signals reaching multiple antenna arrays by networks. Created neural networks have been fed with different data formats and their performances against noisy and no-noise data have been shown. In addition, comparative analysis of the developed models were made in the similar Signal-to-Noise Ratio (SNR) range with the subspace based MUSIC algorithm, which is frequently used in direction finding.