Real Field Trials Research Articles

Emergency obstacle avoidance system of sugarcane basecutter based on improved YOLOv5s

The basecutter collides with obstacles in the field while sugarcane harvesters operate, easily damaging the blades of the basecutter. The design of an emergency obstacle avoidance system with machine vision and deep learning for sugarcane basecutters was used to identify obstacles in the cane field. The embedded system then was used to control the lifting and lowering of the basecutter to complete the real-time obstacle avoidance work. The YOLOv5s target detection model was structurally optimized in a real field trial environment. With a weight file that is 8.4 M, 41.6 % smaller than the original model, and a detection speed increase of 7.98 fps, the improved detection model generally satisfies the real-time needs of the field detection tests. The detection model used on the Raspberry Pi in the field test can achieve better detection accuracy with an inference delay of just 0.2 s, ensuring both detection accuracy and speed while accounting for the size of the model memory. A better obstacle avoidance effect can be achieved under light to moderate occlusion conditions and the positive obstacle avoidance rate can be greater than 80 % when the harvester is moving at a speed between 0.25 m⋅s−1 and 0.35 m⋅s−1. The effect of obstacle avoidance is diminished when the harvester is moving at its general top speed and comes into contact with severe occlusion conditions, but it may still satisfy obstacle avoidance requirements in field work settings and fully protect the blade.

Fully digital, urban networked staring radar: Simulation and experimentation

AbstractThe application and uses of drones in all areas are continuously rising, especially in civilian use cases. This increasing threat requires reliable drone surveillance in urban environments. Radar is the obvious candidate with its ability to detect small objects at range, in all weather conditions. The use of an L‐band networked radar for urban sensing of S‐UAS targets is explored. Small echoes from S‐UAS places a premium on synchronisation, which is the fundamental key for high performance networked radar. The effect of timing errors on the operation of the network radar is investigated theoretically and experimentally, and the processing tools for synchronising data based on the direct signal returns of the transmitter are developed. Also, drone detection using bistatic L‐band staring radar is achieved both in simulation and then in real field trials where the SNR and detection performance are computed and analysed. The updated direct signal synchronisation method for bistatic staring radar is shown to provide comparable SNR and positional accuracy for S‐UAS targets as the monostatic staring radar.

A Cooperative P2P Trading Framework: Developed and Validated Through Hardware-in-Loop

In the past five years, the importance of peer-to-peer (P2P) trading for promoting the use of renewable energy has been demonstrated in many scientific literature and pilot projects. However, a large-scale demonstration of P2P trading in today’s electricity market is yet to be implemented. The reason for this can be partially attributed to two factors. First, most existing pilot projects focus on the aspects of communications between different participants and settlements of energy trading parameters between them without giving considerable attention to the impact of such trading on the distribution network. Second, scientific studies that have rigorously investigated the impact on distribution networks mostly validated their frameworks using numerical simulations without substantiating the findings through hardware implementation. In this paper, this gap is addressed by proposing a ready-to-implement canonical coalition game-based P2P energy trading scheme for electricity customers within a local distribution network. It is shown that the proposed scheme not only guarantees stable and fair outcomes for all participants, but also satisfies all mandatory power network constraints during the trading process. Importantly, the proposed framework is implemented in an RSCAD-RTDS (real-time digital simulator) platform and the readiness of the scheme for a real-field trial is demonstrated through validation in software-in-loop and hardware-in-loop setups. The usefulness and suitability of the proposed scheme to be implemented in today’s electricity network are established via both software-in-loop and hardware-in-loop case studies.

A Novel Two-Degree-of-Freedom Gimbal for Dynamic Laser Weeding: Design, Analysis, and Experimentation

Current robotic laser weeding systems mostly rely on serial mechanisms with one or two actuated axes, which can barely meet the requirements of high precision and dynamic performances. In this article, a novel laser weeding gimbal is proposed based on a two-degree-of-freedom 5-revolute rotational parallel manipulator to perform a dynamic intrarow laser weeding operation. Comprehensive analyses consisting of kinematics, workspace, singularity, and dynamics are carried out to evaluate the performance of the proposed design. Finally, experimental tests were conducted both in lab and field environments and the results are provided, in which the positioning accuracy has been evaluated as in average errors of 0.62 mm in position at the distance of 535 mm, and the dynamic weeding efficiency is around 0.72 s/weed with a dwell time of 0.64 s at the tracking speed of 0.1 m/s. The effectiveness of the proposed dynamic intrarow weeding mechanism has been evaluated in a real field trial.

Revisiting the Lognormal Modelling of Shadowing Effects during Wireless Communications by Means of the α-μ/α-μ Composite Distribution

Properly modeling the shadowing effects during wireless transmissions is crucial to perform the network quality assessment. From a mathematical point of view, using composite distributions allows one to combine both fast fading and slow fading stochastic phenomena. Numerous statistical distributions have been used to account for the fast fading effects. On the other hand, even though several studies indicate the adequacy of the Lognormal distributon (LNd) as a shadowing model, they also reveal this distribution renders some analytic tractability issues. Past works include the combination of Rayleigh and Weibull distributions with LNd. Due to the difficulty inherent to obtaining closed form expressions for the probability density functions involved, other authors approximated LNd as a Gamma distribution, creating Nakagami-m/Gamma and Rayleigh/Gamma composite distributions. In order to better mimic the LNd, approximations using the inverse Gamma and the inverse Nakagami-m distributions have also been considered. Although all these alternatives were discussed, it is still an open question how to effectively use the LNd in the compound models and still get closed-form results. We present a novel understanding on how the α-μ distribution can be reduced to a LNd by a limiting procedure, overcoming the analytic intractability inherent to Lognormal fading processes. Interestingly, new closed-form and series representations for the PDF and CDF of the composite distributions are derived. We build computational codes to evaluate all the expression hereby derived as well as model real field trial results by the equations developed. The accuracy of the codes and of the model are remarkable.

Auto-3P: An autonomous VNF performance prediction & placement framework based on machine learning

We propose Auto-3P, an Autonomous module for Virtual Network Functions Performance Prediction and Placement at network cloud and edge facilities based on Machine Learning (ML). Auto-3P augments the autonomous placement capabilities of MANagement and Orchestration frameworks (MANOs) by considering both resource availability at hosting nodes and the implied impact of a VNF node placement decisions on the whole service level end-to-end performance. Unlike that, most existing placement methods take a rather myopic approach after manual rule-based decisions, and/or based exclusively on a host-centric view that focuses merely on node-local resource availability and network metrics. We evaluate and validate Auto-3P with real-field trials in the context of a well-defined Smart City Safety use case using a real end-to-end application over a real city-based testbed. We meticulously conduct repeated tests to assess (i) the accuracy of our adopted prediction models; and (ii) their placement performance against three other existing MANO approaches, namely, a “Traditional”, a “Latency-aware” and a “Random” one, as well as against a collection of well-known Time Series Forecasting (TSF) methods. Our results show that the accuracy of our ML models outperforms the one by TSF models, with the most prominent accuracy performances being exhibited by models such as K-Nearest Neighbors Regression (K-NNR), Decision Tree (DT), and Support Vector Regression (SVR). What is more, the resulted end-to-end service level performance of our approach outperforms “Traditional”, “Latency-aware”, and Random MANO placement. Last, Auto-3P achieves load balancing at selected VNF hosts without degrading end-to-end service level delay, and without a need for a (fixed) overload threshold check, unlike what is suggested by other works in the literature for coping with heavy system-wide load conditions.

Resources Sustainability. N Application in Crops to Determine the Best Environmental Performance Using Life Cycle Assessment Methodology

The use of mineral fertilizer in horticultural crops is a very important issue due to its effects on crop yield and its environmental impact. For the period 2011-2012, the total mineral fertilizer consumption in EU-27 reached 10.4 million tons of nitrogen (N), 1.0 million tons of phosphorus (K) and 2.2 million tons of potassium (K). Though many recent studies have examined horticultural crops, few have focused on mineral fertilizers in order to make an environmental assessment of a tomato crop. Therefore, the aim of this research was to study the agronomical (i.e. yield) and the environmental performance of a horticultural tomato crop fertilized with four different doses of mineral fertilizer (N0, N1, N2 and N3), using Life Cycle Assessment methodology. Data and conditions for the crop were taken from a real field trial with an experimental design carried out in North-east Catalonia, Spain. Following the guidelines of the ISO 14044, the study considered all stages of the life cycle of a horticultural tomato crop (i.e. mineral fertilizer production, transport and cultivation phase). Six impact categories were included in the study: climate change, photochemical oxidation formation, land acidification, freshwater and marine eutrophication and fossil depletion. Overall, the results showed that the best result was for the N1 treatment, with a yield of 61 ton ha-1 and 55 ton ha-1 for total and commercial yield, respectively. N1 showed the best environmental performance in all categories assessed.

Data‐driven learning and planning for environmental sampling

AbstractRobots such as autonomous underwater vehicles (AUVs) and autonomous surface vehicles (ASVs) have been used for sensing and monitoring aquatic environments such as oceans and lakes. Environmental sampling is a challenging task because the environmental attributes to be observed can vary both spatially and temporally, and the target environment is usually a large and continuous domain whereas the sampling data are typically sparse and limited. The challenges require that the sampling method must be informative and efficient enough to catch up with the environmental dynamics. In this paper, we present a planning and learning method that enables a sampling robot to perform persistent monitoring tasks by learning and refining a dynamic “data map” that models a spatiotemporal environment attribute such as ocean salinity content. Our environmental sampling framework consists of two components: To maximize the information collected, we propose an informative planning component that efficiently generates sampling waypoints that contain the maximal information; to alleviate the computational bottleneck caused by large‐scale data accumulated, we develop a component based on a sparse Gaussian process whose hyperparameters are learned online by taking advantage of only a subset of data that provides the greatest contribution. We validate our method with both simulations running on real ocean data and field trials with an ASV in a lake environment. Our experiments show that the proposed framework is both accurate in learning the environmental data map and efficient in catching up with the dynamic environmental changes.

The fast marching method based intelligent navigation of an unmanned surface vehicle

Unmanned surface vehicles (USVs) have obtained increasing interests in recent decades. Because of the features of improved mission efficiency and decreased resource costs, applications of USVs can been seen in both civilian and naval areas. In order to efficiently and effectively achieve missions without any human intervention, a robust and intelligent navigation, guidance and control (NGC) system is vital for USV. This paper has therefore presented a novel NGC system designed for a USV named Springer. The system is developed by integrating multiple functional modules, which include a reliable navigation module that provides reliable position and heading information, a robust autopilot module enabling Springer tracking well the waypoints and an intelligent path planning module that is capable of generating feasible and practical waypoints. The path planning algorithm has been developed based upon the angle guidance fast marching square method, which is able to calculate the optimal path according to vehicle's motion constraints. The designed NGC system has been validated in both real field trials and computer based simulations proving that Springer USV is able to autonomously navigate in different maritime environments with the guidance of the NGC system.

Determination of residues of sulfonylurea herbicides in soil by using microwave-assisted extraction and high performance liquid chromatographic method

A modified method for the analysis of nicosulfuron, rimsulfuron and prosulfuron was developed and validated by using microwave-assisted extraction (MAE) and ultra-performance liquid chromatography with diode array detection in the ultraviolet region (HPLC-UV-DAD). The most important experimental parameters of extraction procedure and HPLC-UV-DAD technique were optimised in respect to those sulfonylurea herbicides. High recoveries of the microwave-assisted extraction were obtained by using a dichloromethane?acetonitrile mixture (2:1 volume ratio) acidified with acetic acid (0.8 vol.%) with the addition of urea. The mean recoveries at three spiking levels ranged from 97.47 to 98.76% for nicosulfuron, 97.88 to 99.17% for rimsulfuron and from 97.91 to 99.83% for prosulfuron. The limits of detection of nicosulfuron, rimsulfuron and prosulfuron were 0.95, 0.91 and 0.89 ?g kg?1, respectively. The accuracy of the developed method was confirmed by HPLC coupled with tandem mass spectrometry parallel analyses. The developed method was used to investigate the dissipation dynamics of sulfonylurea herbicides in the real field trials in Vojvodina Province, Serbia. The obtained half-lives were 0.05, 0.23 and 0.15 days for recommended dose application of nicosulfuron, rimsulfuron and prosulfuron, respectively. Low residues and short half-life in soil suggested that the risk to sensitive rotational crops after application of those sulfonylurea herbicides is low when they are used in the appropriate dosages.

Improving load balancing techniques by location awareness at indoor femtocell networks

Femtocells are the auspicious solution for the coverage and capacity challenges that mobile operators are currently facing indoors. Whereas some operators are focused on offloading data traffic from macrocells to femtocells, others prefer to ensure indoor coverage and prioritize voice traffic in order to mitigate the negative impact of blocked or dropped calls. In this context, this paper proposes a novel self-optimizing mechanism to prevent congestion problems at indoor environments, focused on operators that prioritize voice traffic connections. A challenge specific to femtocells is that they normally can only serve a small number of simultaneous connections. Based on this restriction, the proposed mechanism resizes femtocell coverage areas by tuning their transmission powers for load balancing purposes. How information on user location can enhance the optimization process is also investigated in this paper. According to this, two methods to estimate the received signal level per user are evaluated. Finally, the performance is studied by means of both simulations and a real field trial.

A novel particle filter approach for indoor positioning by fusing WiFi and inertial sensors

WiFi fingerprinting is the method of recording WiFi signal strength from access points (AP) along with the positions at which they were recorded, and later matching those to new measurements for indoor positioning. Inertial positioning utilizes the accelerometer and gyroscopes for pedestrian positioning. However, both methods have their limitations, such as the WiFi fluctuations and the accumulative error of inertial sensors. Usually, the filtering method is used for integrating the two approaches to achieve better location accuracy. In the real environments, especially in the indoor field, the APs could be sparse and short range. To overcome the limitations, a novel particle filter approach based on Rao Blackwellized particle filter (RBPF) is presented in this paper. The indoor environment is divided into several local maps, which are assumed to be independent of each other. The local areas are estimated by the local particle filter, whereas the global areas are combined by the global particle filter. The algorithm has been investigated by real field trials using a WiFi tablet on hand with an inertial sensor on foot. It could be concluded that the proposed method reduces the complexity of the positioning algorithm obviously, as well as offers a significant improvement in position accuracy compared to other conventional algorithms, allowing indoor positioning error below 1.2m.

ROTATING A MEMS INERTIAL MEASUREMENT UNIT FOR A FOOT-MOUNTED PEDESTRIAN NAVIGATION

Pedestrian navigation especially indoors suffers from the unavailability of useful GNSS signals for positioning. Alternatively, a low-cost Inertial Measurement Unit (IMU) positioning system that does not depend on the GNSS signal can be used for indoor navigation. However its performance is still compromised because of the fast-accumulating heading drift error affecting such a low-cost IMU sensor. This results in a huge positioning error when navigating more than a few seconds using only the low-cost sensor. In this study, real field trials results are presented when a foot-mounted IMU is rotated on a single axis. Two promising results have been obtained. First, it mitigates the heading drift error significantly and second, it increases the observability of IMU z-axis gyro bias error. This has resulted in a greatly reduced error in position for the low-cost pedestrian navigation system.

On magnetometer heading updates for inertial pedestrian navigation system

A magnetometer is often used to aid heading estimation of a low-cost Inertial Pedestrian Navigation System (IPNS) without which the latter will not be able to accurately estimate heading for more than a few seconds, even with the help of Zero Velocity Update (ZVU). Heading measurements from the magnetometer are typically integrated with gyro heading in an estimation filter such as Kalman Filter (KF) — to best estimate the true IPNS heading, resulting in a better positioning accuracy. However indoors the reliability of these measurements is often questionable because of the magnetic disturbances that can disrupt the measurements. To solve this problem, a filtering method is often used to select the best measurements. However, the importance of the frequency of these measurement updates has not been highlighted. In this paper, the impact of frequency of magnetometer updates on the overall accuracy of the navigation system is presented. The paper starts by discussing the use of a magnetometer in a low-cost IPNS. An exemplary filter to extract reliable heading measurements from the magnetometer is then described. From real field trial results, it will be shown that even if reliable heading measurements may be obtained indoors, it is still insufficient to increase the positioning accuracy of the low-cost IPNS unless it is reliable on every epoch.

Integration of GPS and low cost INS for pedestrian navigation aided by building layout

In outdoor environments, GPS is often used for pedestrian navigation by utilizing its signals for position computation, but in indoor or semi-obstructed environments, GPS signals are often unavailable. Therefore, pedestrian navigation for these environments should be realized by the integration of GPS and inertial navigation system (INS). However, the lowcost INS could induce errors that may result in a large position drift. The problem can be minimized by mounting the sensors on the pedestrian’s foot, using zero velocity update (ZUPT) method with the standard navigation algorithm to restrict the error growth. However, heading drift still remains despite using ZUPT measurements since the heading error is unobservable. Also, foot mounted INS suffers from the initialization ambiguity of position and heading from GPS. In this paper, a novel algorithm is developed to mitigate the heading drift problem when using ZUPT. The method uses building layout to aid the heading measurement in Kalman filter, and it could also be combined for the initialization. The algorithm has been investigated with real field trials using the low cost Microstrain 3DM-GX3-25 inertial sensor, a Leica GS10 GPS receiver and a uBlox EVK-6T GPS receiver. It could be concluded that the proposed method offers a significant improvement in position accuracy for the long period, allowing pedestrian navigation for nearly40min with mean position error less than 2.8m. This method also has a considerable effect on the accuracy of the initialization.

The frequency of CFVD speed report for highway traffic

AbstractThe control signals of cellular networks have been used to infer the traffic conditions of the road network. In particular, consecutive handover events are being used to estimate the traffic speed. During traffic congestion, consecutive handover events may be rare because vehicles move slowly, and thus very few or no speed reports would be generated from the congested area.However, the traffic speed report rate during traffic congestion has not been investigated in the literature. In this paper, we present an analytic model to estimate the speed report rate from cellular network signaling in steady traffic conditions, that is, the traffic speed and flow are assumed constant. Real field trial data were used to validate our analytic model. In addition, computer simulations were conducted to study how speed reports are generated in dynamic traffic conditions when traffic speed and flow change rapidly. Our study indicates that in a typical cell of length 1.5 km with a typical expected call holding time of 1 min, no speed report was generated from a congested three‐lane highway. Our study demonstrates that the lack of speed reports from consecutive handover events during rush hours indicates severe traffic congestion, and new methods that can estimate traffic speed from cellular network data during severe traffic congestion need to be developed. Copyright © 2013 John Wiley & Sons, Ltd.

Energy generation based on piezoelectric transducers

In this paper, the design, implementation and testing of a prototype for electric energy generation from collecting wasted ambient power sources coming from the mechanic vibrations (Piezoelectric Energy Harvesting PEH) is presented. This prototype has been specifically designed for applications where it is required to connect multiple transducers in order to obtain greater power levels. This design is based on a previous comparative analysis among all the existing auto-harvesting circuits. The prototype has been tested both in laboratory tests as in real field trials on board railway units, with encouraging results. It has been proved that, though achieving power levels of a few milliwatts, its application in the autonomous low-consumption devices powering systems field is a real possibility.

SimTD: a car-to-X system architecture for field operational tests [Topics in Automotive Networking

Car-to-car and car-to-infrastructure communications are considered as a key technology for safe and intelligent mobility in the future. In the German project sim <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TD</sup> , <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> car-to-x communication is shifting from a pure research topic toward a first deployment of such a system: the goal of sim <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TD</sup> is to test car-to-x applications in a real metropolitan field trial. The sim <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TD</sup> scenario includes vehicles, roadside units, and infrastructural facilities for traffic and test management. Besides these domains, several third parties are involved to provide access to additional services. The main communication partners are furthermore distributed over a wide area including highway, suburban, and urban scenarios. As a result, such a system requires a commonly accepted architecture of the individual components and a seamless communication network for reliable and efficient information interchange. In this article we propose the sim <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TD</sup> system architecture and the components necessary for successful deployment in the large-scale field trial.

On Automatic Bioacoustic Detection of Pests: The Cases of &lt;I&gt;Rhynchophorus ferrugineus&lt;/I&gt; and &lt;I&gt;Sitophilus oryzae&lt;/I&gt;

The present work reports research efforts toward development and evaluation of a unified framework for automatic bioacoustic recognition of specific insect pests. Our approach is based on capturing and automatically recognizing the acoustic emission resulting from typical behaviors, e.g., locomotion and feeding, of the target pests. After acquisition the signals are amplified, filtered, parameterized, and classified by advanced machine learning methods on a portable computer. Specifically, we investigate an advanced signal parameterization scheme that relies on variable size signal segmentation. The feature vector computed for each segment of the signal is composed of the dominant harmonic, which carry information about the periodicity of the signal, and the cepstral coefficients, which carry information about the relative distribution of energy among the different spectral sub-bands. This parameterization offers a reliable representation of both the acoustic emissions of the pests of interest and the interferences from the environment. We illustrate the practical significance of our methodology on two specific cases: 1) a devastating pest for palm plantations, namely, Rhynchophorus ferrugineus Olivier and 2) a pest that attacks warehouse stored rice (Oryza sativa L.), the rice weevil, Sitophilus oryzae (L.) (both Coleoptera: Curculionidae, Dryophorinae). These pests are known in many countries around the world and contribute for significant economical loss. The proposed approach led to detection results in real field trials, reaching 99.1% on real-field recordings of R. ferrugineus and 100% for S. oryzae.

Cost-effective Product Traceability System Based on Widely Distributed Databases

A cost-effective and easy way of introducing a product traceability system is to start from a small system and gradually extend it to a large-scale system. Traceability systems used in previous field tests are unsuitable for largescale deployment because they use a single, centralized database. This paper describes an extendable traceability system proposed by Toshiba that employs distributed databases. Our proposed system called LoTR consists of two components, a DHT-based ID-DB resolution mechanism and TraceBack method. The ID-DB resolution mechanism is used to acquire a DB location from an ID. We apply the DHT to accomplish required scalability. We have developed a DHTDNS mounter to achieve seamless access to DHT-based IDDB resolution from ordinary DNS resolvers. In addition, the TraceBack method creates links to bind distributed databases. We have evaluated the operation of the system with a real field trial. As the next step, we shall analyze its qualitative behavior through large-scale experiments.