LSTM-based lane change prediction using Waymo open motion dataset: The role of vehicle operating space

Lane change prediction is critical for crash avoidance but challenging as it requires the understanding of the instantaneous driving environment.With cutting-edge artificial intelligence and sensing technologies,autonomous vehicles(AVs)are expected to have exceptional perception systems to capture instantaneously their driving environments for predicting lane changes.By exploring the Waymo open motion dataset,this study proposes a framework to explore autonomous driving data and investigate lane change behaviors.In the framework,this study develops a Long Short-Term Memory(LSTM)model to predict lane changing behaviors.The concept of Vehicle Operating Space(VOS)is introduced to quantify a vehicle's instantaneous driving environment as an important indicator used to predict vehicle lane changes.To examine the robustness of the model,a series of sensitivity analysis are conducted by varying the feature selection,prediction horizon,and training data balancing ratios.The test results show that including VOS into modeling can speed up the loss decay in the training process and lead to higher accuracy and recall for predicting lane-change behaviors.This study offers an example along with a methodological framework for transportation researchers to use emerging autonomous driving data to investigate driving behaviors and traffic environments.

Review of the studies on emission evaluation approaches for operating vehicles

With the increasing international consensus concerning the negative effects of climate change,reducing greenhouse gases has become a higher priority in government policies and research committees.The transportation sector generates approximately 29%of the total greenhouse gas emissions and 25%of the global energy related carbon dioxide(CO2)emissions.Thus,it is essential to understand the influencing factors of vehicle emissions and establish a corresponding evaluation model for the emission estimation of operating vehicles.This paper reviews different methods of measuring vehicle emissions,including laboratory measurements,on-road measurements,and tunnel measurements.Then,we summarize the factors affecting the emission evaluation of operating vehicles based on the vehicle operating features and road environment.Finally,the applications of vehicle emission evaluation models are analyzed,including the emission assessment of the vehicles operating at road segments and intersections.Based on this review,one can conclude that selecting different measurements will significantly impact the assessment of the vehicle emission results and the applicable scope of the measurements.Considering the different influencing factors of the operating vehicle emissions will have an impact on the model application of the vehicle emission evaluation.Moreover,several analysis methods for new technology vehicles can compensate for the potential lack in connectedness with the rapid development of new energy vehicle technology and the improvement of intelligent transportation systems(ITS).

Revision of the National Standard on Safety Specification for Power Driven Vehicles Operating on Roads

The national standard--Safety Specifications for Power Driven Vehicles Operating on Roads-is the most basic technieal regulation for safety and technical management of motor vehicles in China. It is the safety and technical basis for the Public Security Traffic Control Dept. to register new vehicles, periodic inspection of vehicles under operation and inspection of vehicles involved in traffic accidents. It is also one of the important technical bases of our country for compulsory inspection of new vehicles on finalization of its model, ex-works inspection of new vehicles and the inspection of imported motor vehicles.

Research on Hydrodynamics Model Test for Deepsea Open-Framed Remotely Operated Vehicle

This paper presents the features of newly designed hydrodynamics test for the scaled model of 4500 m deepsea open-framed remotely operated vehicle （ROV）, which is being researched and developed by Shanghai Jiao Tong University. Accurate hydrodynamics coefficients measurement and spatial modeling of ROV are significant for the maneuverability and control algorithm. The scaled model of ROV was constructed by 1：1.6. Hydrodynamics coefficients were measured through VPMM and LAHPMM towing test. And dynamics model was derived as a set of equations, describing nonlinear and coupled 5-DOF spatial motions. Rotation control motion was simulated to verify spatial model proposed. Research and application of hydrodynamics coefficients are expected to enable ROV to overcome uncertainty and disturbances of deepsea environment, and accomplish some more challengeable and practical missions.

Research on Ant Colony Algorithm in Vehicle Operation Adjustment Based on IOT

Automatic solution of vehicle operation adjustment is the important content in realizing vehicle traffic command automation on Internet of Things platform. Based on both the organization realization of Internet of Things platform and the merging vehicle operation adjustment into the Flow-Shop scheduling problem in manufacturing systems,this paper has constructed the optimization model with a two-lane vehicle operation adjustment. With respect to the large model solution space and complex constraints,a better solution algorithm is proposed based on ant colony algorithm for optimal quick solution. The simulation results show that the algorithm is feasible and the approximate optimal solution can be quickly obtained.

Heuristics for Improving Operational Performance of Permutation Circulati on-type Vehicle Routing System

This paper discusses an optimization of operating a p ermutation circulation-type vehicle routing system (PCVRS, for short), in w hich several stages are located along by a single loop, and a fleet of vehicles travels on the loop unidirectionally and repeatedly. Traveling on the loop, each vehicle receives an object from the loading stage and then carries it to a cert ain processing stage, or receives an object from a certain processing stage and then carries it to the unloading stage per a turnaround. No passing is allowed f or the vehicles on the loop (from which the system is called permutation, and th is restriction may cause interferences between vehicles). Material handling systems such as PCVRS are actually encountered in flexible man ufacturing systems and in automated storage/retrieval systems. In this paper, we propose a heuristic algorithm for operating the PCVRS, which i ncorporates a new scheduling method for the vehicles with the SPT (shortest proc essing time) numbering of jobs and a round-robin manner of allocating jobs to t he stages, aiming to reduce interferences between the vehicles. We also give num erical results with respect to system performances attained by the heuristic. Description of the system The PCVRS consists of a set of n v vehicles V={V 1,V 2,...,V n v}, a set of n s, processing stages S p={S 1,S 2,...,S n s}, a loading stage S 0 and an unloading stage S n s +1. We denote by S=S p∪{S 0,S n s+l} the set of all the stages. The vehicles travel on a single loop unidirectionany and repeated ly. The system layout is depicted in Fig.1. There is a set of n jobs J={J 1,J 2,...,J n} to be processed b y the vehicles. Each job consists of two tasks: That is, each vehicle receives a n object from S 0 and then carries it to S l with a certain l∈{1,2, ...,n s} (a throw-in job), or receives an object from S l with a certain l∈{1,2,...,n s} and then carries it to S n s+1 (a throw-out job ) per a turnaround. The loop consists of buffer zones BZ(l) and travel zones TZ(l) (see Fig. 1). Each buffer zone BZ(l) is placed in front of stage S l, l=0,1,..., n s, n s+1, in order to avoid a collision between vehicles (i.e., the syste m adopts the so-called zone control strategy). A heuristic algorithm We develop a heuristic algorithm to obtain a good performance for the PCVRS. An operation π={A/B/C} for the PCVRS consists of three decision factors: (A) Numbering jobs Jobs are loaded into S 0 according to an assending order of job numbers. In this paper, we use the following rules to number jobs: SPT: Order jobs in the shortest processing time rule, i.e., P 1≤P 2≤...≤P n for the set of jobs J={J 1,J 2,...,J n}, rather than the FCFS numbering (i.e., number jobs in first-come-first-served order). The SPT rule intends to reduce interferences between two adjacent vehicles at stages. (B) Allocating jobs to stages For the purpose of balancing loads of processing stages, we adopt the following to allocate jobs to the stages: ORDER: Allocate n jobs to n s, processing stages by an in-order manner , i.e., let l(i) be the index of processing stage allocated job J i by ORDER, it holds that l(i)=n s+1-(i-[(i-1)/n s]n s).(1) The ORDER rule intends to process jobs parallel at stages as many as possible. (C) Scheduling vehicles The following method for scheduling vehicles under ORDER rule is already known: Fig.1 The vehicle ro uting system, PCVRS Fig.2 Mean turnaroun d times by heuristics Unchange: Assign n jobs to n v vehicles such that let k(i) be the i ndex of vehicle processing job J i, then k(i)= i-[(i-1)/n v]n v.(2) In csse of n v≥n s, mod (n v,n s)=0 or n v<n s, mod (n s,n v)=0 (mod(x,y) is the remainder of x/y), the number of interferences between vehicles is minimized at stage S 1 under Unchange sche dules, while in the other cases it is not [Lu et al. (2001a)]. Therefore, in t his paper, we develop a new scheduling method of the vehicles, denoted by Ex change, to modify Unchange schedules. Note

A Hull-Inspect ROV Control System Architecture

The control architectures of ＂SY-2＂ Remote Operated Vehicle （ROV） are introduced. Both hardware architecture and software architecture are discussed. PC/104 embedded computer is used to control equipment for collecting sensor data and sending control commands. PC/104 embedded computer is integrated with A/D, D/A, 8 serial ports card and power supply unit. The surface computer is a X86PC. They transfer data through a fiber line. For software, real-time OS VxWorks is embedded in PC/104. A/D, D/A and serial ports operation are based on VxWorks OS, which increase the real-time quality of control system. Surface computer is the center of motion control and data processing. It is communicated with underwater PC/104 by socket. The whole system has been tested both on land and in tank.

多用途远程操作的海面运载器

Development of man-packable,versatile marine surface vehicle with ability to rescue a drowning victim and also capable of carrying mission specific sensor is explored.Design thinking methodology is implemented by using existing equipment/platform with the addition of external attachment to make it a functional product.Iterative prototyping process with extensive testing to achieve user-centric solution.Individual prototypes and their possible sub-configurations with their integration and characteristics are studied and compared with numerical model,inferences obtained are utilised to improve for the next iteration.A novel hinge-clamp assembly enables this marine surface vehicle to operate in the event of an overturn,this phenomenon is further studied with the aid of a mathematical model(Pendulum in a fluid).This research project aims to demonstrate a multi-role unmanned surface vehicle.

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.

OBLIQUE TOWING TEST AND MANEUVER SIMULATION AT LOW SPEED AND LARGE DRIFT ANGLE FOR DEEP SEA OPEN-FRAMED REMOTELY OPERATED VEHICLE

This article presents the newly designed oblique towing test in the horizontal plane for the scaled model of 4 500 m deep sea open-framed Remotely Operated Vehicle （ROV）,which is being researched and developed by Shanghai Jiao Tong University.Accurate hydrodynamics coefficients measurement is significant for the maneuverability and control system design.The scaled model of ROV was constructed by 1：1.6.Hydrodynamics tests of large drift angle were conducted through Large Amplitude Horizontal Planar Motion Mechanism （LAHPMM） under low speed.Multiple regression method is adopted to process the test data and obtain the related hydrodynamic coefficients.Simulations were designed for the horizontal plane motion of large drift angle to verify the coefficients calculated.And the results show that the data can satisfy with the design requirements of the ROV developed.

Automatic analysis of deep-water remotely operated vehicle footage for estimation of Norway lobster abundance

Underwater imaging is being used increasingly by marine biologists as a means to assess the abundance of marine resources and their biodiversity. Previously, we developed the first automatic approach for estimating the abundance of Norway lobsters and counting their burrows in video sequences captured using a monochrome camera mounted on trawling gear. In this paper, an alternative framework is proposed and tested using deep-water video sequences acquired via a remotely operated vehicle. The proposed framework consists of four modules:(1) preprocessing,(2) object detection and classification,(3) object-tracking, and(4) quantification. Encouraging results were obtained from available test videos for the automatic video-based abundance estimation in comparison with manual counts by human experts(ground truth). For the available test set, the proposed system achieved 100%precision and recall for lobster counting, and around 83% precision and recall for burrow detection.

Estimating impacts of emission specific characteristics on vehicle operation for quantifying air pollutant emissions and energy use

This paper proposes and illustrates a methodology to predict the fraction of time motor vehicles spend in different operating conditions from readily observable variables called emission specific characteristics （ESC）. ESC describe salient characteristics of vehicles, roadway geometry, the roadside environment, traffic, and driving style （aggressive, normal, and calm）. The information generated by our methodology can then be entered in vehicular emission models that rely on vehicle specific power, i.e., comprehensive modal emissions model （CMEM）, international vehicle emissions （IVE）, or motor vehicle emission simulator （MOVES） to compute energy consumption and vehicular emissions for various air pollutants. After generating second-by-second vehicle trajectories from a calibrated micro-simulation model, the authors estimated structural equation models to examine the influence of link ESC on vehicle operation. Authors＇ results show that 67% of the link speed variance is explained by ESC. Overall, the roadway geometry exerts a greater influence on link speed than traffic characteristics, the roadside environment, and driving style. Moreover, the speed limit has the strongest influence on vehicle operation, followed by facility type and driving style. Better understanding the impact on vehicle operation of ESC could help metropolitan planning organizations （MPOs） and regional transportation au- thorities predict vehicle operations and reduce the environmental footprint of motor vehicles.

Detecting large-scale underwater cracks based on remote operated vehicle and graph convolutional neural network

It is of great significance to quickly detect underwater cracks as they can seriously threaten the safety of underwater structures.Research to date has mainly focused on the detection of above-water-level cracks and hasn’t considered the large scale cracks.In this paper,a large-scale underwater crack examination method is proposed based on image stitching and segmentation.In addition,a purpose of this paper is to design a new convolution method to segment underwater images.An improved As-Projective-As-Possible(APAP)algorithm was designed to extract and stitch keyframes from videos.The graph convolutional neural network(GCN)was used to segment the stitched image.The GCN’s m-IOU is 24.02%higher than Fully convolutional networks(FCN),proving that GCN has great potential of application in image segmentation and underwater image processing.The result shows that the improved APAP algorithm and GCN can adapt to complex underwater environments and perform well in different study areas.

An approach to operational risk modeling and estimation of safety levels for deep water work class remotely operated vehicle-A case study with reference to ROSUB 6000

This paper presents a quantitative approach to operational risk modeling and estimation of safety integrity levels,required for the deep water electric work class remotely operated vehicle with reference to ROSUB6000 developed by the National Institute of Ocean Technology,India.ROSUB6000 is used for carrying out bathymetric surveys,gas hydrate surveys,poly-metallic nodule exploration,salvage operations,and meeting emergency response situations.The system is expected to be in operation for a period of 300 h per year,and has to be extremely safe and reliable.Methods and models for the quantitative assessment of operational safety and estimation of safety integrity levels for ROV are seldom available in the deep water intervention industry.The safety instrumented functions implemented in the ROV should be able to meet the SIL requirements of specific mission.This study indicates that the required safety factors are implemented into the design of the state-of-the-art ROV ROSUB 6000,considering IEC 61508/61511 recommendations on Health,Safety and Environment and it is found that the system is able to meet the required SIL for seven identified functions.This paper gives the design and safety engineers in the ROV industry,an overview of the numerical operational risk assessment methods and safety-centered ROV engineering.

Life-cycle cost analysis of optimal timing of pavement preservation

Optimal application of pavement preservation or preventive maintenance is critical for highway agencies to allocate the limited budget for different treatments. This study developed an integrated life-cycle cost analysis （LCCA） model to quantify the impact of pavement preservation on agency cost and vehicle operation cost （VOC） and analyzed the optimal timing of preservation treatments. The international roughness index （IRI） data were extracted from the long-term pavement performance （LTPP） program specific pavement studies 3 （SPS-3） to determine the long-term effectiveness of preservation treatments on IRI deterioration. The traffic loading and the initial IRI value significantly affects life extension and the benefit of agency cost caused by pavement preservation. The benefit in VOC is one to two orders greater in magnitude as compared to the benefit in agency cost. The optimal timing calculated based on VOC is always earlier than the optimal timing calculated based on agency cost. There are considerable differences among the optimal timing of three preservation treatments.

Efficient Identification of water conveyance tunnels siltation based on ensemble deep learning

The inspection of water conveyance tunnels plays an important role in water diversion projects.Siltation is an essential factor threatening the safety of water conveyance tunnels.Accurate and efficient identification of such siltation can reduce risks and enhance safety and reliability of these projects.The remotely operated vehicle(ROV)can detect such siltation.However,it needs to improve its intelligent recognition of image data it obtains.This paper introduces the idea of ensemble deep learning.Based on the VGG16 network,a compact convolutional neural network(CNN)is designed as a primary learner,called Silt-net,which is used to identify the siltation images.At the same time,the fully-connected network is applied as the meta-learner,and stacking ensemble learning is combined with the outputs of the primary classifiers to obtain satisfactory classification results.Finally,several evaluation metrics are used to measure the performance of the proposed method.The experimental results on the siltation dataset show that the classification accuracy of the proposed method reaches 97.2%,which is far better than the accuracy of other classifiers.Furthermore,the proposed method can weigh the accuracy and model complexity on a platform with limited computing resources.