Car Navigation Research Articles

New technologies as a driver of change in the agricultural sector

Faced with a demographic boom, enormous urbanization and a lack of agricultural land, traditional agricultural production is losing pace with new needs and demands. Due to the increased demand for food, efforts are being made to develop technologies that would improve production, with the sustainable use of existing resources. Solving this challenge is possible by introducing Internet of Things technologies, satellite navigation, mobile communications and ubiquitous computing, which is called smart agriculture. The main goals of smart agriculture are to increase yields (provide information needed to analyze and make decisions that will maximize yields), efficient water use, more efficient agricultural operations (automation of daily activities, real-time monitoring, advanced analytics, daily and seasonal forecasting), cooperation with suppliers and public administration are more efficient and take place in real time). This article highlights the potential of the Internet of Things, big data and drones in agriculture, as well as the challenges of applying these technologies in relation to traditional agricultural practices.

Continuous Tracking of GPS Signals with Data Wipe-Off Method

The decentralized pre-filter based vector tracking loop (VTL) configuration with data wipe-off (DWO) method of the Global Positioning System (GPS) receiver is proposed for performance enhancement. It is a challenging task to continuously track the satellites’ signals in weak signal environment for the GPS receiver. VTL is a very attractive technique as it can provide tracking capability in signal-challenged environments. In the VTL, each channel will not form a loop independently. On the contrary, the signals in the channels of VTL are shared with each other; the navigation processor in turn predicts the code phases. Thus, the receiver can successfully track signals even the signal strength from individual satellite is weak. The tracking loop based on the pre-filter provides more flexible adjustment to specific environments to reduce noise interference. Therefore, even if the signals from some satellites are very weak the receiver can track them from the navigation results based on the other satellites. The navigation data, which contains information necessary to perform navigation computations, are binary phase-shift keying (BPSK) modulated onto the GPS carrier phase with the bit duration of 20 ms (i.e., 50 bits per second) for the GPS L1 C/A signals. The coherent integration interval can be extended for improved tracking performance in signal-challenged environment. However, tracking accuracy is decreased by possible data bit sign reversal. The DWO algorithm can be employed to remove the data bit in I and Q correlation values so as to avoid energy loss due to bit transitions when the integration interval of the correlator is extended over 20 ms under the low carrier-to-noise ratio (C/No) environments. The proposed method has an advantage to provide continuous tracking of signals and obtain improved navigation performance. Performance evaluation of the tracking capability as well as positioning accuracy will be presented.

Data Wipe-Off Technique for Tracking Weak GPS Signals

In this paper, the data wipe-off (DWO) algorithm is incorporated into the vector tracking loop of the Global Positioning System (GPS) receiver for improving signal tracking performance. The navigation data, which contains information that is necessary to perform navigation computations, are binary phase-shift keying (BPSK) modulated onto the GPS carrier phase with the bit duration of 20 ms (i.e., 50 bits per second). To continuously track the satellite’s signal in weak signal environment, the DWO algorithm on the basis of pre-detection method is adopted to detect data bit sign reversal every 20 ms. Tracking accuracy of a weak GPS signal is decreased by possible data bit sign reversal every 20 ms to the predetection integration time (PIT) or integration interval. To achieve better tracking performance in weak signal environment, the coherent integration interval can be extended. However, increase of the integration interval lead to decrease of the tracking accuracy by possible data bit sign reversal every 20 ms to the integration interval. When the integration interval of the correlator is extended over 20 ms in low C/No levels, the navigation DWO algorithm can be employed to avoid energy loss due to bit transitions. The method presented in this paper has an advantage to continuously estimate the navigation data bit and achieve improved tracking performance. Evaluation of the tracking performance based on the various integration intervals for the vector tracking loop of a GPS receiver will be presented.

农具自动导航技术的研究进展. 综述

Automatic navigation system for agricultural vehicles have become a widely used technology in precision agriculture over the last few decades. More and more sophisticated tractor control systems, however, revealed that exact positioning of the actual implement is equally or even more important. Based on literature sources and patent databases, the aim of this review is to introduce implement guidance systems and describe its current application in agricultural implement. Agricultural implement guidance is an essential technology for autonomous vehicle operations. In addition, applications and new technologies associated with navigation sensors on passive and active implement guidance are analyzed. Finally, challenges and future perspectives of agricultural implement systems are summarized and forecasted. This study can enrich the application of automatic navigation sensors on agricultural implements and provide a reference for the application of automatic navigation on more field operations.

Deep and Transfer Learning Approaches for Pedestrian Identification and Classification in Autonomous Vehicles

Pedestrian detection is at the core of autonomous road vehicle navigation systems as they allow a vehicle to understand where potential hazards lie in the surrounding area and enable it to act in such a way that avoids traffic-accidents, which may result in individuals being harmed. In this work, a review of the convolutional neural networks (CNN) to tackle pedestrian detection is presented. We further present models based on CNN and transfer learning. The CNN model with the VGG-16 architecture is further optimised using the transfer learning approach. This paper demonstrates that the use of image augmentation on training data can yield varying results. In addition, a pre-processing system that can be used to prepare 3D spatial data obtained via LiDAR sensors is proposed. This pre-processing system is able to identify candidate regions that can be put forward for classification, whether that be 3D classification or a combination of 2D and 3D classifications via sensor fusion. We proposed a number of models based on transfer learning and convolutional neural networks and achieved over 98% accuracy with the adaptive transfer learning model.

Mining crowdsourced trajectory and geo‐tagged data for spatial‐semantic road map construction

AbstractThe road map is a fundamental part of a spatial data infrastructure (SDI), and is widely applied in navigation, smart transportation, and mobile location services. Recently, with the ubiquity of positioning devices, crowdsourced trajectories have become a significant data resource for road map construction and updating. However, existing trajectory‐based methods mainly place emphasis on extracting road geometry features and may ignore continuous updating of road semantic information. Hence, we propose a divide‐and‐conquer method to construct a spatial‐semantic road map by incorporating multiple data sources (e.g., crowdsourced trajectories and geo‐tagged data). The proposed method divides road map construction into two sub‐tasks, road structure reconstruction and road attributes inference. The road structure reconstruction process starts to partition raw trajectory data into different cliques of roadways and road intersections, and then extracts various targeted road structures by analyzing the turning modes in different trajectory cliques. The road attributes inference process aims to infer three pieces of crucial semantic information about road speeds, turning rules, and road names from crowdsourced trajectories and geo‐tagged data. The case studies in Wuhan were examined to illustrate that the proposed method can construct a routable road map with enhanced geometric structures and rich semantic information, providing a beneficial data solution for car navigation and SDI update.

Vehicle Navigation System based on Pollution Metric Analysis with Q-Learning Algorithm

The navigation systems available in the present scenario takes into account the path distance for their estimations. In some advanced navigation systems, the road traffic analysis is also considered in the algorithm for their predictions. The proposed work estimates a navigation path with respect to the present pollution level on the roadways. The work suggests an alternate path to avoid additional vehicles to enter the same road which is already impacted by air pollution. A Q-learning (Quality learning) prediction algorithm is trained in the proposed work with a self-made dataset for the estimations. The experimental work presented in the paper explores the accuracy and computational speed of the developed algorithm in comparison to the traditional algorithms.

Laser-scanning rangefinder fixed on a gimbal with two degrees of freedom

A laser-scanning rangefinder mounted on a gimbal with two degrees of freedom is presented. The rangefinder can be used as part of a navigation system of an unmanned aerial vehicle to avoid obstacles or prevent collisions. Compared to stereo cameras, the device requires significantly less computing resources and is less dependent on lighting conditions. Compared to integrated lidars, the cost of the device is by an order lower. А model of the device was developed and an obstacle avoidance flight was simulated in the Gazebo simulator. The PX4/Avoidance software was used as an autopilot. As a result of a model experiment, we found that a scanning laser rangefinder can provide autonomous navigation with obstacle avoidance.

Privacy-Preserving Aggregation for Federated Learning-Based Navigation in Vehicular Fog

Federated learning-based automotive navigation has recently received considerable attention, as it can potentially address the issue of weak global positioning system (GPS) signals under severe blockages, such as in downtowns and tunnels. Specifically, the data-driven navigation framework combines the position estimation offered by the high-sampling inertial measurement units and the position calibration provided by the low-sampling GPS signals. Despite its promise, the privacy preservation and flexibility of the participating users in the federated learning process are still problematic. To address these challenges, in this article, we propose an efficient, flexible, and privacy-preserving model aggregation scheme under a federated learning-based navigation framework named FedLoc. Specifically, our proposed scheme efficiently protects the locally trained model updates, flexibly supports the fluctuation of participants, and is robust against unregistered malicious users by exploiting a homomorphic threshold cryptosystem, together with the bounded Laplace mechanism and the skip list. We perform a detailed security analysis to demonstrate the security properties in terms of privacy preservation and dishonest user detection. In addition, we evaluate and compare the computational efficiency with two traditional schemes, and the simulation results show that our scheme greatly improves the computational efficiency during participant fluctuation. To validate the effectiveness of our scheme, we also show that only part of the model update is excluded from aggregation in the case of a dishonest user.

Model of the location system for transport

In the modern world, tracking systems are actively implemented in various forms, ranging from smart surveillance cameras and integrated smart home systems to tracking parcels, passenger vehicles or vehicles carrying important cargo. This topic is actual for the companies working with vehicles, such as insurance companies, emergency services, and car fleets where tracking the vehicles becomes the commercial necessity. It also concerns those who prefer to work on a rotational basis and have contractors on wheels, for example mining companies, where it is important to track accurately the location of vehicles and calculate the route time. The tracker is a small device used to determine the location and track it. Nowadays, due to its unique properties, this device has a wide range of implementations such as monitoring of children and the elderly, creating optimal routes for the movement of goods using car navigators and video recorders, or ensuring the safety and accuracy of movement of private and commercial vehicles. These small electronic devices can not only determine their coordinates using GPS satellites, but use the built-in communication module to send them to a remote server for further database storage and processing. The currently popular cloud services can be used as a remote server, for instance, Amazon Web Services, the computing power of which is distributed in many geographic locations all around the world, and therefore, it is possible not only to save the obtained data in the geographic location closest to the user, but also to perform their analysis and processing without renting a separate physical server.

METHOD OF ALLOCATION OF MOUNTING POINTS ON AEROPHOTOGRAPHS OBTAINED BY UNLIMITED AIRCRAFT FOR USE DURING THE CAR

A retrospective analysis of the use of unmanned aerial vehicles in the combat zone indicates a steady increase in the use of electronic warfare by the enemy, which reduces the effectiveness of reconnaissance flights of unmanned aerial vehicles, and in some cases leads to their loss. The article considers the prospects of creating and improving high-precision navigation systems, which is currently one of the priority areas for the development of unmanned aerial vehicles and relevant for ensuring high efficiency of unmanned aerial vehicles for both civil and military purposes. To develop and study methods and algorithms for localizing the position of unmanned aerial vehicles based on terrain images obtained by non-identical surveying means, taking into account the influence of electronic warfare on it, the article primarily considers approaches to comparing earth surface images as the main information component. The next step is to assess the correctness of the choice of informative parameters of the anchor points, where the mathematical model for their description and selection is the basis for the development of methods and algorithms for the formation of an autonomous navigation system for unmanned aerial vehicles. Taking into account the research conducted in the work, it was proposed to implement on board the drone intelligent information and calculation system of autonomous navigation, the algorithm of which is based on the logical basis of the SIFT descriptor. Thanks to the software implementation of the approaches proposed in the work and obtained on the basis of their experimental results, it is possible to develop and further improve methods of positioning unmanned aerial vehicles in space.

Study of front panel electrode coatings for combined visible and short wavelength infrared photodetectors

ZnO-Ga2O3 composite oxide films were RF sputtered and studied how the optical and electrical film properties are affected by the sputtering conditions and film thickness. The aim was to achieve low resistivity and at the same time, high transparency for the visible and short wavelength infrared (SWIR) electromagnetic range for the needs of simple, transparent and indium-free electrodes. A comparison was made with pristine ZnO films. We found that plasma voltage, respectively plasma power plays a crucial role in determining the optoelectronic properties of the deposited films for the fabrication of combined photodetectors. The effective surface roughness of the ZnO-Ga2O3 films varied between 12.9 nm and 16.7 nm when plasma power density varied between 35 and 54 W/cm2, respectively. The increase of the sputtering power narrowed the transmission band to the longer wavelength from the visible spectrum. The transparency in the SWIR range varied between 83 and 96% and decreased with the plasma power increase, while the corresponding transparency in the visible range varied between 60 and 82%. The sheet resistance for the films under the best parameters demonstrating the highest transmission in both electromagnetic ranges showed relatively low sheet resistance of 48 Ω/sq. The potential application of the prepared films is for VIS-IR detectors used in robotics for spatial information gain, gaming and virtual reality and autonomous car navigation, where the day and the night visions are equally important.

LIDAR Self Driving Car

Abstract: Increasing population is the major issue of transportation nowadays. People who live and work in the major cities of the world are faced with increasing levels of congestion, delays, total travel time, costs, frustration, accidents and loss of life. The objective of this project is to help prevent traffic accidents and save people’s time by fundamentally changing car use. The system would have sensors to detect the obstacles and to be able to react according to their position. In this project we have developed an automated driving system which drives the car automatically. We have developed a technology for cars that drives it automatically using LIDAR. This car is capable of sensing the surroundings, navigating and fulfilling the human transportation capabilities without any human input. It continuously tracks the surrounding and if any obstacle is detected vehicle senses and moves around and avoids the obstacle. An autonomous car navigation system based on Global Positioning System (GPS) is a new and promising technology, which uses real time geographical data received from several GPS satellites to calculate longitude, latitude, speed and course to help navigate a car. As we know the development of gps is more improved now the accuracy of gps we can see centimetre also so Like for our car to go at specific inputted location we use this gps technology.Lidar is used for sensing the surroundings. Like radar, lidar is an active remote sensing technology but instead of using radio or microwaves it uses electromagnetic waves. Keywords: Congestion, Traffic Accident, LIDAR sensor, Global Positioning System, Electromagnetic waves

Dual Band GNSS Antenna Phase Center Characterization for Automotive Applications

High-accuracy Global Navigation Satellite System (GNSS) positioning is a prospective technology that will be used in future automotive navigation systems. This system will be a composite of the United States' Global Positioning System (GPS), the Russian Federation's Global Orbiting Navigation Satellite System (GLONASS), China Beidou Navigation Satellite System (BDS) and the European Union’s Galileo. The major improvement in accuracy and precision is based on (1) multiband signal transmitting, (2) carrier phase correction, (3) Real Time Kinematic (RTK). Due to the size and high-cost of today’s survey-grade antenna solutions, this kind of technology is difficult to use widely in the automotive sector. In this paper, a low-cost small size dual-band ceramic GNSS patch antenna is presented from design to real sample. A further study of this patch antenna illustrates the absolute phase center variation measured in an indoor range to achieve a received signal phase error correction. In addition, this low-cost antenna solution is investigated when integrated into a standard multi-band automotive antenna product. This product is evaluated both on its own in an indoor range and on a typical vehicle roof at an outdoor range. By using this evaluation file to estimate the receiver position could achieve phase motion error-free result.

A connectome of the Drosophila central complex reveals network motifs suitable for flexible navigation and context-dependent action selection.

Flexible behaviors over long timescales are thought to engage recurrent neural networks in deep brain regions, which are experimentally challenging to study. In insects, recurrent circuit dynamics in a brain region called the central complex (CX) enable directed locomotion, sleep, and context- and experience-dependent spatial navigation. We describe the first complete electron microscopy-based connectome of the Drosophila CX, including all its neurons and circuits at synaptic resolution. We identified new CX neuron types, novel sensory and motor pathways, and network motifs that likely enable the CX to extract the fly's head direction, maintain it with attractor dynamics, and combine it with other sensorimotor information to perform vector-based navigational computations. We also identified numerous pathways that may facilitate the selection of CX-driven behavioral patterns by context and internal state. The CX connectome provides a comprehensive blueprint necessary for a detailed understanding of network dynamics underlying sleep, flexible navigation, and state-dependent action selection.

Road Curb Detection: A Historical Survey.

Curbs are used as physical markers to delimit roads and to redirect traffic into multiple directions (e.g., islands and roundabouts). Detection of road curbs is a fundamental task for autonomous vehicle navigation in urban environments. Since almost two decades, solutions that use various types of sensors, including vision, Light Detection and Ranging (LiDAR) sensors, among others, have emerged to address the curb detection problem. This survey elaborates on the advances of road curb detection problems, a research field that has grown over the last two decades and continues to be the ground for new theoretical and applied developments. We identify the tasks involved in the road curb detection methods and their applications on autonomous vehicle navigation and advanced driver assistance system (ADAS). Finally, we present an analysis on the similarities and differences of the wide variety of contributions.

GNSS Spoofing Detection Based on Coupled Visual/Inertial/GNSS Navigation System.

Spoofing attacks are one of the severest threats for global navigation satellite systems (GNSSs). This kind of attack can damage the navigation systems of unmanned air vehicles (UAVs) and other unmanned vehicles (UVs), which are highly dependent on GNSSs. A novel method for GNSS spoofing detection based on a coupled visual/inertial/GNSS positioning algorithm is proposed in this paper. Visual inertial odometry (VIO) has high accuracy for state estimation in the short term and is a good supplement for GNSSs. Coupled VIO/GNSS navigation systems are, unfortunately, also vulnerable when the GNSS is subject to spoofing attacks. The method proposed in this article involves monitoring the deviation between the VIO and GNSS under an optimization framework. A modified Chi-square test triggers the spoofing alarm when the detection factors become abnormal. After spoofing detection, the optimal estimation algorithm is modified to prevent it being deceived by the spoofed GNSS data and to enable it to carry on positioning. The performance of the proposed spoofing detection method is evaluated through a real-world visual/inertial/GNSS dataset and a real GNSS spoofing attack experiment. The results indicate that the proposed method works well even when the deviation caused by spoofing is small, which proves the efficiency of the method.

Indoor and Outdoor Seamless Positioning Method Using UWB Enhanced Multi-Sensor Tightly-Coupled Integration

As one of the main methods in positioning and navigation, the Global Navigation Satellite System (GNSS) is widely applied in many areas, such as road engineering, automobile navigation and many other outdoor applications. In addition to an outdoor location-based service, there are many needs for indoor positioning. However, GNSS is hard to position indoors due to signal blockage, and outdoor–indoor transition areas where multipath effects are unavoidable and signal interference is severe. This article proposes a GNSS/INS/UWB tightly-coupled integration positioning methodology to address the problem of accurate positioning in GNSS-difficult areas and aims to provide seamless positioning in different scenarios. In indoor environments, the system uses the UWB/INS tightly-coupled integration positioning mode and periodically corrects the INS errors with range measurements obtained from the UWB transmitting unit to achieve centimeter-level accuracy. In outdoor GNSS-difficult areas like outdoor–indoor transition areas, a GNSS/INS/UWB tightly-coupled integration positioning system is proposed to ensure positioning accuracy continuity and further improve the reliability of the system. To evaluate the positioning performance of the proposed UWB enhanced multi-sensor tightly-coupled integration system, an experiment was conducted in a high-rise building. The experiment results show that the proposed integrated positioning system can provide seamless and accurate positioning results in both indoor and outdoor–indoor transition areas, with DRMS of 5.25 cm and RMSE of 10.18 cm.

Audio Hotspot Attack: An Attack on Voice Assistance Systems Using Directional Sound Beams and its Feasibility

We propose a novel attack, called an “Audio Hotspot Attack,” which performs an inaudible malicious voice command attack, by targeting voice assistance systems, e.g., smart speakers or in-car navigation systems. The key idea of the approach is to leverage directional sound beams generated from parametric loudspeakers, which emit amplitude-modulated ultrasounds that will be self-demodulated in the air. Our work goes beyond the previous studies of inaudible voice command attack in the following three aspects: (1) the attack can succeed on a long distance (3.5 meters in a small room, and 12 meters in a long hallway), (2) it can control the spot of the audible area by using two directional sound beams, which consist of a carrier wave and a sideband wave, and (3) the proposed attack leverages a physical phenomenon i.e., non-linearity in the air, to attack voice assistance systems. To evaluate the feasibility of the attack, we performed extensive in-lab experiments and a user study involving 20 participants. The results demonstrated that the attack was feasible in a real-world setting. We discussed the extent of the threat, as well as the possible countermeasures against the attack.

Compositional Learning and Verification of Neural Network Controllers

Recent advances in deep learning have enabled data-driven controller design for autonomous systems. However, verifying safety of such controllers, which are often hard-to-analyze neural networks, remains a challenge. Inspired by compositional strategies for program verification, we propose a framework for compositional learning and verification of neural network controllers. Our approach is to decompose the task (e.g., car navigation) into a sequence of subtasks (e.g., segments of the track), each corresponding to a different mode of the system (e.g., go straight or turn). Then, we learn a separate controller for each mode, and verify correctness by proving that (i) each controller is correct within its mode, and (ii) transitions between modes are correct. This compositional strategy not only improves scalability of both learning and verification, but also enables our approach to verify correctness for arbitrary compositions of the subtasks. To handle partial observability (e.g., LiDAR), we additionally learn and verify a mode predictor that predicts which controller to use. Finally, our framework also incorporates an algorithm that, given a set of controllers, automatically synthesizes the pre- and postconditions required by our verification procedure. We validate our approach in a case study on a simulation model of the F1/10 autonomous car, a system that poses challenges for existing verification tools due to both its reliance on LiDAR observations, as well as the need to prove safety for complex track geometries. We leverage our framework to learn and verify a controller that safely completes any track consisting of an arbitrary sequence of five kinds of track segments.