FIR-YOLACT:Fusion of ICIoU and Res2Net for YOLACT on Real-Time Vehicle Instance Segmentation

Autonomous driving technology has made a lot of outstanding achievements with deep learning,and the vehicle detection and classification algorithm has become one of the critical technologies of autonomous driving systems.The vehicle instance segmentation can perform instance-level semantic parsing of vehicle information,which is more accurate and reliable than object detection.However,the existing instance segmentation algorithms still have the problems of poor mask prediction accuracy and low detection speed.Therefore,this paper proposes an advanced real-time instance segmentation model named FIR-YOLACT,which fuses the ICIoU(Improved Complete Intersection over Union)and Res2Net for the YOLACT algorithm.Specifically,the ICIoU function can effectively solve the degradation problem of the original CIoU loss function,and improve the training convergence speed and detection accuracy.The Res2Net module fused with the ECA(Efficient Channel Attention)Net is added to the model’s backbone network,which improves the multi-scale detection capability and mask prediction accuracy.Furthermore,the Cluster NMS(Non-Maximum Suppression)algorithm is introduced in the model’s bounding box regression to enhance the performance of detecting similarly occluded objects.The experimental results demonstrate the superiority of FIR-YOLACT to the based methods and the effectiveness of all components.The processing speed reaches 28 FPS,which meets the demands of real-time vehicle instance segmentation.

Application of A* Algorithm for Real-time Path Re-planning of an Unmanned Surface Vehicle Avoiding Underwater Obstacles

This paper describes path re-planning techniques and underwater obstacle avoidance for unmanned surface vehicle(USV) based on multi-beam forward looking sonar(FLS). Near-optimal paths in static and dynamic environments with underwater obstacles are computed using a numerical solution procedure based on an A* algorithm. The USV is modeled with a circular shape in 2 degrees of freedom(surge and yaw). In this paper, two-dimensional(2-D) underwater obstacle avoidance and the robust real-time path re-planning technique for actual USV using multi-beam FLS are developed. Our real-time path re-planning algorithm has been tested to regenerate the optimal path for several updated frames in the field of view of the sonar with a proper update frequency of the FLS. The performance of the proposed method was verified through simulations, and sea experiments. For simulations, the USV model can avoid both a single stationary obstacle, multiple stationary obstacles and moving obstacles with the near-optimal trajectory that are performed both in the vehicle and the world reference frame. For sea experiments, the proposed method for an underwater obstacle avoidance system is implemented with a USV test platform. The actual USV is automatically controlled and succeeded in its real-time avoidance against the stationary undersea obstacle in the field of view of the FLS together with the Global Positioning System(GPS) of the USV.

Experimental Model and Analytic Solution for Real-time Observation of Vehicle's Additional Steer Angle

The current research of real-time observation for vehicle roll steer angle and compliance steer angle（both of them comprehensively referred as the additional steer angle in this paper） mainly employs the linear vehicle dynamic model, in which only the lateral acceleration of vehicle body is considered. The observation accuracy resorting to this method cannot meet the requirements of vehicle real-time stability control, especially under extreme driving conditions. The paper explores the solution resorting to experimental method. Firstly, a multi-body dynamic model of a passenger car is built based on the ADAMS/Car software, whose dynamic accuracy is verified by the same vehicle＇s roadway test data of steady static circular test. Based on this simulation platform, several influencing factors of additional steer angle under different driving conditions are quantitatively analyzed. Then ε-SVR algorithm is employed to build the additional steer angle prediction model, whose input vectors mainly include the sensor information of standard electronic stability control system（ESC）. The method of typical slalom tests and FMVSS 126 tests are adopted to make simulation, train model and test model＇s generalization performance. The test result shows that the influence of lateral acceleration on additional steer angle is maximal （the magnitude up to 1°）, followed by the longitudinal acceleration-deceleration and the road wave amplitude （the magnitude up to 0.3°）. Moreover, both the prediction accuracy and the calculation real-time of the model can meet the control requirements of ESC This research expands the accurate observation methods of the additional steer angle under extreme driving conditions.

Real-Time Black Carbon Emissions from Light-Duty Passenger Vehicles Using a Portable Emissions Measurement System

Black carbon(BC)is considered the second largest anthropogenic climate forcer,but the radiative effects of BC are highly correlated with its combustion sources.On-road vehicles are an important source of anthropogenic BC.However,there are major uncertainties in the estimates of the BC emissions from on-road light-duty passenger vehicles(LDPVs),and results obtained with the portable emissions measurement system(PEMS)method are particularly lacking.We developed a PEMS platform and evaluated the on-road BC emissions from ten in-use LDPVs.We demonstrated that the BC emission factors(EFs)of gasoline direction injection(GDI)engine vehicles range from 1.10 to 1.56 mg.km^(-1),which are higher than the EFs of port fuel injection(PFI)engine vehicles(0.10–0.17 mg.km^(-1))by a factor of 11.The BC emissions during the cold-start phase contributed 2%–33%to the total emissions.A strong correlation(R^(2)=0.70)was observed between the relative BC EFs and average vehicle speed,indicating that traffic congestion alleviation could effectively mitigate BC emissions.Moreover,BC and particle number(PN)emissions were linearly correlated(R^(2)=0.90),and compared to PFI engine vehicles,the instantaneous PN-to-BC emission rates of GDI engine vehicles were less sensitive to vehicle specific power-to-velocity(VSPV)increase in all speed ranges.

Low-Power Operational Amplifier for Real-Time Signal Processing System of Micro Air Vehicle

A low-power complementary metal oxide semiconductor（CMOS） operational amplifier （op-amp） for real-time signal processing of micro air vehicle （MAV） is designed in this paper.Traditional folded cascode architecture with positive channel metal oxide semiconductor（PMOS） differential input transistors and sub-threshold technology are applied under the low supply voltage.Simulation results show that this amplifier has significantly low power,while maintaining almost the same gain,bandwidth and other key performances.The power required is only 0.12 mW,which is applicable to low-power and low-voltage real-time signal acquisition and processing system.

Application Research of an Intelligent Detection Algorithm for Vehicle Trajectory Route Deviation

In the vehicle trajectory application system, it is often necessary to detect whether the vehicle deviates from the specified route. Trajectory planning in the traditional route deviation detection is defined by the driver through the mobile phone navigation software, which plays a more auxiliary driving role. This paper presents a method of vehicle trajectory deviation detection. Firstly, the manager customizes the trajectory planning and then uses big data technologies to match the deviation between the trajectory planning and the vehicle trajectory. Finally, it achieves the supervisory function of the manager on the vehicle track route in real-time. The results show that this method could detect the vehicle trajectory deviation quickly and accurately, and has practical application value.

Parallel Neural Network-Based Motion Controller for Autonomous Underwater Vehicles

A parallel neural network-based controller （PNNC） is presented for the motion control of underwater vehicles in this paper. It consists of a real-time part, a self-learning part and a desired-state programmer, and it is different from normal adaptive neural network controller in structure. Owing to the introduction of the self-learning part, on-line learning can be performed without sample data in several sample periods, resulting in high learning speed of the controller and good control performance. The desired-state programmer is utilized to obtain better learning samples of the neural network to keep the stability of the controller. The developed controller is applied to the 4-degree of freedom control of the AUV “IUV- IV” and is successful on the simulation platform. The control performance is also compared with that of neural network controller with different structures such as normal adaptive neural network and different learning methods. Current effects and surge velocity control are also included to demonstrate the controller＇ s performance. It is shown that the PNNC has a great possibility to solve the problems in the control system design of underwater vehicles.

ENERGY MANAGEMENT STRATEGY FOR PARALLEL HYBRID ELECTRIC VEHICLES

Energy management strategy (EMS) is the core of the real-time controlalgorithm of the hybrid electric vehicle (HEV). A novel EMS using the logic threshold approach withincorporation of a stand-by optimization algorithm is proposed. The aim of it is to minimize theengine fuel consumption and maintain the battery state of charge (SOC) in its operation range, whilesatisfying the vehicle performance and drivability requirements. The hybrid powertrain bench testis carried out to collect data of the engine, motor and battery pack, which are used in the EMS tocontrol the powertrain. Computer simulation model of the HEV is established in the MATLAB/Simulinkenvironment according to the bench test results. Simulation results are presented for behaviors ofthe engine, motor and battery. The proposed EMS is implemented for a real parallel hybrid carcontrol system and validated by vehicle field tests.

A Model Predictive Scheduling Algorithm inReal-Time Control Systems

The ineffective utilization of power resources has attracted much attention in current years. This paper proposes a real-time distributed load scheduling algorithm considering constraints of power supply. Firstly, an objective function is designed based on the constraint, and a base load forecasting model is established when aggregating renewable generation and non-deferrable load into a power system, which aims to transform the problem of deferrable loads scheduling into a distributed optimal control problem. Then, to optimize the objective function, a real-time scheduling algorithm is presented to solve the proposed control problem. At every time step, the purpose is to minimize the variance of differences between power supply and aggregate load, which can thus ensure the effective utilization of power resources. Finally, simulation examples are provided to illustrate the effectiveness of the proposed algorithm.

Electric vehicle simulation with battery in the loop

An electric vehicle simulation system with battery in the loop（BIL） is described in this paper.Virtual models are used for the other parts of power train including the electric motor/controller,transmission and vehicle dynamics,which allows the easy change of system parameters and rapid evaluation of vehicle and battery performance for different vehicle configurations.Tests were conducted using the system and the measurements（voltage and current,efficiency） obtained from the real battery were compared with those obtained from a standard nominal model of the battery.The results indicate that the measured voltage and current between the real battery and those obtained from the model are significantly different.Additionally,it is expected that the difference will increase significantly as the battery ages.

A New Algorithmic Approach for Detection and Identification of Vehicle Plate Numbers

This work proposes a method for the detection and identification of parked vehicles stationed. This technique composed many algorithms for the detection, localization, segmentation, extraction and recognition of number plates in images. It is acts of a technology of image processing used to identify the vehicles by their number plates. Knowing that we work on images whose level of gray is sampled with (120×180), resulting from a base of abundant data by PSA. We present two algorithms allowing the detection of the horizontal position of the vehicle: the classical method “horizontal gradients” and our approach “symmetrical method”. In fact, a car seen from the front presents a symmetry plan and by detecting its axis, that one finds its position in the image. A phase of localization is treated using the parameter MGD (Maximum Gradient Difference) which allows locating all the segments of text per horizontal scan. A specific technique of filtering, combining the method of symmetry and the localization by the MGD allows eliminating the blocks which don’t pass by the axis of symmetry and thus find the good block containing the number plate. Once we locate the plate, we use four algorithms that must be realized in order to allow our system to identify a license plate. The first algorithm is adjusting the intensity and the contrast of the image. The second algorithm is segmenting the characters on the plate using profile method. Then extracting and resizing the characters and finally recognizing them by means of optical character recogni-tion OCR. The efficiency of these algorithms is shown using a database of 350 images for the tests. We find a rate of lo-calization of 99.6% on a basis of 350 images with a rate of false alarms (wrong block text) of 0.88% by image.

Performance Evaluation of Multiple Unmanned Aerial Vehicles Operating in General Regime with Shortage of Maintenance Facilities

We consider a real-world problem of military intelligence unit equipped with multiple identical unmanned aerial vehicles (UAV) responsible for several regions (with requests of real-time jobs arriving from independent sources). We suppose that there are no ample maintenance facilities, allowing simultaneous treatment of all vehicles if necessary. Under certain assumptions, these real-time systems can be treated using a queueing theory methodology and/or as Markov chains. We show how to compute steady-state probabilities of these systems, their performance effectiveness, and various performance parameters (for exponentially distributed service and maintenance times of UAVs, as well as tasks duration and their arrival pattern).

GeeNet:robust and fast point cloud completion for ground elevation estimation towards autonomous vehicles

Ground elevation estimation is vital for numerous applications in autonomous vehicles and intelligent robotics including three-dimensional object detection,navigable space detection,point cloud matching for localization,and registration for mapping.However,most works regard the ground as a plane without height information,which causes inaccurate manipulation in these applications.In this work,we propose GeeNet,a novel end-to-end,lightweight method that completes the ground in nearly real time and simultaneously estimates the ground elevation in a grid-based representation.GeeNet leverages the mixing of two-and three-dimensional convolutions to preserve a lightweight architecture to regress ground elevation information for each cell of the grid.For the first time,GeeNet has fulfilled ground elevation estimation from semantic scene completion.We use the SemanticKITTI and SemanticPOSS datasets to validate the proposed GeeNet,demonstrating the qualitative and quantitative performances of GeeNet on ground elevation estimation and semantic scene completion of the point cloud.Moreover,the crossdataset generalization capability of GeeNet is experimentally proven.GeeNet achieves state-of-the-art performance in terms of point cloud completion and ground elevation estimation,with a runtime of 0.88 ms.

Real-time energy-efficient anticipative driving control of connected and automated hybrid electric vehicles

In this paper,we propose a real-time energy-efficient anticipative driving control strategy for connected and automated hybrid electric vehicles(HEVs).Considering the inherent complexities brought about by the velocity profile optimization and energy management control,a hierarchical control architecture in the model predictive control(MPC)framework is developed for real-time implementation.In the higher level controller,a novel velocity optimization problem is proposed to realize safe and energy-efficient anticipative driving.The real-time control actions are derived through a computationally efficient algorithm.In the lower level controller,an explicit solution of the optimal torque split ratio and gear shift schedule is introduced for following the optimal velocity profile obtained from the higher level controller.The comparative simulation results demonstrate that the proposed strategy can achieve approximately 13%fuel consumption saving compared with a benchmark strategy.

车辆实时调度系统中的交通数据描述模型

针对车辆实时调度系统应用中的问题,在探讨可扩展标记语言(XML)数据交换方面优势和分析物流运输企业车辆实时调度系统所需交通数据流的基础上,总结实时交通数据模型,以实现数据无缝交换为目标,从数据交换标准化的角度,基于XML构建了车辆实时调度系统交通数据描述标记语言(Traffic Data Markup Language)模型,探讨了其定义、数据层次框架,并设计了TDML Schema;最后,应用TDML于城市商用车辆调度系统的实时交通数据交换。

Real-time optimization of energy consumption under adaptive cruise control for connected HEVs

This paper presents a real-time energy optimization algorithm for a hybrid electric vehicle(HEV)that operates with adaptive cruise control(ACC).Real-time energy optimization is an essential ssue such that the HEV powertrain system is as efficient as possible.With connected vehice technique,ACC system shows considerable potential of high energy eficiency.Combining a classical ACC algorithm,a two-level cooperative control scheme is constructed to realize real-time power distribution for the host HEV that operates in a vehicle platoon.The proposed control strategy actually provides a solution for an optimal control problem with multi objectives in terms of string stable of vehicle platoon and energy consumption minimization of the individual following vehicle.The string stability and the real-time optimization performance of the cooperative control system are confirmed by simulations with respect to several operating scenarios.

Field testing innovative differential geospatial and photogrammetric monitoring technologiesin mountainous terrain near Ashcroft,British Columbia,Canada

This paper presents a novel approach to continuously monitor very slow-moving translational landslides in mountainous terrain using conventional and experimental differential global navigation satellite system(d-GNSS)technologies.A key research question addressed is whether displacement trends captured by a radio-frequency“mobile”d-GNSS network compare with the spatial and temporal patterns in activity indicated by satellite interferometric synthetic aperture radar(InSAR)and unmanned aerial vehicle(UAV)photogrammetry.Field testing undertaken at Ripley Landslide,near Ashcroft in south-central British Columbia,Canada,demonstrates the applicability of new geospatial technologies to monitoring ground control points(GCPs)and railway infrastructure on a landslide with small and slow annual displacements(<10 cm/yr).Each technique records increased landslide activity and ground displacement in late winter and early spring.During this interval,river and groundwater levels are at their lowest levels,while ground saturation rapidly increases in response to the thawing of surficial earth materials,and the infiltration of snowmelt and runoff occurs by way of deep-penetrating tension cracks at the head scarp and across the main slide body.Research over the last decade provides vital information for government agencies,national railway companies,and other stakeholders to understand geohazard risk,predict landslide movement,improve the safety,security,and resilience of Canada’s transportation infrastructure;and reduce risks to the economy,environment,natural resources,and public safety.

THE SPUTNIK OF SERVGOODS： AUTONOMOUS VEHICLES

In an earlier paper （Tien 2015）, the author defmed the concept of a servgood, which can be thought of as a physical good or product enveloped by a services-oriented layer that makes the good smarter or more adaptable and customizable for a particular use. Adding another layer of physical sensors could then enhance its smartness and intelligence, especially if it were to be connected with each other or with other servgoods through the Internet of Things. Such sensed servgoods are becoming the products of the future. Indeed, autonomous vehicles can be considered the exemplar servgoods of the future; it is about decision informatics and embraces the advanced technologies of sensing （i.e., Big Data）, processing （i.e., real-time analytics）, reacting （i.e., real-time decision-making）, and learning （i.e., deep learning）. Since autonomous vehicles constitute a huge quality-of-life disruption, it is also critical to consider its policy impact on privacy and security, regulations and standards, and liability and insurance. Finally, just as the Soviet Union inaugurated the space age on October 4, 1957, with the launch of Sputnik, the first man-made object to orbit the Earth, the U. S. has inaugurated an age of automata or autonomous vehicles that can be considered to be the U. S. Sputnik of servgoods, with the full support of the U. S. government, the U. S. auto industry, the U. S. electronic industry, and the U.S. higher educational enterprise.

开发水下机器人控制器的MDAMBSE方法的实用专业化研究

The model-driven architecture(MDA)/model-based systems engineering(MBSE)approach,in combination with the real-time Unified Modeling Language(UML)/Systems Modeling Language(SysML),unscented Kalman filter(UKF)algorithm,and hybrid automata,are specialized to conveniently analyze,design,and implement controllers of autonomous underwater vehicles(AUVs).The dynamics and control structure of AUVs are adapted and integrated with the specialized features of the MDA/MBSE approach as follows.The computation-independent model is defined by the specification of a use case model together with the UKF algorithm and hybrid automata and is used in intensive requirement analysis.The platform-independent model(PIM)is then built by specializing the real-time UML/SysML’s features,such as the main control capsules and their dynamic evolutions,which reflect the structures and behaviors of controllers.The detailed PIM is subsequently converted into the platform-specific model by using open-source platforms to quickly implement and deploy AUV controllers.The study ends with a trial trip and deployment results for a planar trajectory-tracking controller of a miniature AUV with a torpedo shape.

Development of a Robot for In-service Radiography Inspection of Subsea Flexible Risers

The extreme operational environmental conditions and aging conditions of subsea structures pose a risk to their structural integrity and is critical to their safety.Nondestructive testing is essential to identify defects developing within the structure,allowing repair in a timely manner to mitigate against failures that cause damage to the environment and pose a hazard to human operators.However,to be cost effective,inspections must be carried out without taking the risers out of service.This poses significant safety risks if undertaken manually.This paper presents the development of an automated inspection system for flexible risers that are used to connect wellheads on the seafloor to the offshore production and storage facility.Due to the complex structure of risers,radiography is considered as the best technique to inspect multiple layers of the risers.However,radiography inspection,in turn,requires a robotic system for in-situ inspection with higher payload capacity,precise movement of source and detector which is able to withstand an extreme operational environment.The deployment of a radiography inspection system hasbeen achieved bydeveloping acustomized subsearobotic system called RiserSure that can provide precise scanning motion of a gamma ray source and digital detector moving in alignment.The prototype has been tested on a flexible riser during shallow water sea trials with the system placed around a riser by a remotely operated vehicle.The results from the trials show that the internal inner and outer tensile armor layer and defects in the riser can be successfully imaged in real operational conditions.