LU100760B1

LU100760B1 - Vehicular motion assessment method

Info

Publication number: LU100760B1
Application number: LU100760A
Authority: LU
Inventors: German Castignani; Leandro Masello
Original assignee: Motion S
Priority date: 2018-04-09
Filing date: 2018-04-09
Publication date: 2019-10-11
Also published as: EP3774478A1; WO2019197345A1

Abstract

A vehicular motion assessment method (Fig. 1) comprises: capturing motion observations on-board a vehicle (12), the motion observations including timestamped vehicle positions; logging the motion observations; map-matching the motion observations so as to identify, for each vehicle position a road link of a road network stored in a map database (18) as well as a map-matched position on the road link; contextualizing the motion observations by augmenting them with situational data obtained by querying the map database (18) or another geographic information database; determining, based on the contextualized motion observations, whether the vehicle (12) was exposed, during the trips, to unsafe driving situations; and communicating one or more risk scores indicative of accident probability, calculated based on determined exposures to unsafe driving situations.

Description

DESCRIPTION

VEHICULAR MOTION ASSESSMENT METHOD

Field of the Invention [0001] The invention generally relates to monitoring vehicular motion and driving styleprofiling by assessing exposure of the vehicle to unsafe driving situations, in particularunsafe driving situations imputable to the driver.

Background of the Invention [0002] Monitoring driving activity has become an important topic in the recent years.Two main application fields have been devised in which real-time analysis andevaluation of the driving behaviour will play a prominent role. The first application fieldis (car) fleet management, where real-time information on the driving behaviour maybe used in taking measures aiming at motivating the drivers to adopt a more efficientdriving style, to reduce their energy footprint and to save fuel. On the scale of the fleets,significant savings in terms of CO2 emissions and fleet depreciation may be achieved.The second important application field is the car insurance market. The calculation ofcar insurance premium may be enriched by or exclusively be based on individualparameters like the covered distance, the time spent on the road, the time of day, theroads used, etc. Those concepts are usually referred to as Pay-As-You-Drive (PAYD),Pay-How-You-Drive (PHYD) or Usage-Based Insurance (UBI). An importantparameter in such premium calculation schemes is the driving style (i.e. an indicator ofhow many and how important are risks the driver takes when diving).

[0003] International patent application WO 2013/104805 A1 discloses an apparatus,a system and a method for calculating a driving behaviour risk indicator for a vehicledriver. The system uses a 3D inertial sensor with 3D gyroscope functionality and therisk indicator is based on events detected using the sensor, in particular on the countof events occurring in predetermined categories associated with dangerous and/oraggressive driving.

[0004] International patent application WO2016/107876 A1 discloses a vehicularmotion monitoring method, wherein motion observations are captured on-board avehicle with one or more sensors and sets of motion observations are mapped onto arespective feature vector in an at least two-dimensional feature space, each feature vector having a first vector component representative of a longitudinal motioncharacteristic and a second vector component representative of a lateral motioncharacteristic. Determinative parameters of a multivariate Gaussian probability densityfunction modelling a population of collected feature vectors are then updated and ariskiness indicator is assigned to each feature vector. The calculation of the riskinessindicator is based upon an event severity indicator indicative of how anomalous eachfeature vector is in comparison to the modelled population and upon a position of thefeature vector relative to one or more previous and/or subsequent feature vectors. Theriskiness indicator is integrated over time so as to obtain a risk assessment of thedriving style. The method described in WO2016/107876 A1 suffers from severaldrawbacks, in particular, from the fact that the telematics metrics (acceleration,braking, cornering and speed) have no objective connection to risk statistics.

Summary of the Invention [0005] A first aspect of the invention relates to a vehicular motion assessmentmethod, comprising: a. capturing motion observations with a mobile terminal on-board a vehicle, themobile terminal including or being connected to a GNSS receiver, the motionobservations including timestamped vehicle positions (“trackpoints”) measuredby the GNSS receiver; b. logging the motion observations; c. map-matching the motion observations so as to identify, for each vehicle positiona road link of a road network stored in a map database as well as a map-matchedposition on the road link; d. contextualizing the motion observations by augmenting them with situational dataobtained by querying the map database and/or another geographic informationdatabase (e.g. a weather database); e. determining, based on the contextualized motion observations, whether thevehicle was exposed, during the trips, to unsafe driving situations, e.g. unsafedriving situations imputable to the driver; and f. communicating (e.g. via a display and/or via a telecommunication link) one ormore risk scores indicative of accident probability, calculated based ondetermined exposures to unsafe driving situations.

[0006] The vehicular motion assessment method may be carried out by the mobileterminal, which could comprise a smartphone, a tablet, a phablet, a notebook, an on-board diagnostic unit, a dedicated data logger, or the like. The mobile terminal couldbe separate from or integrated into the vehicle. The map database and/or the othergeographic information database could be stored on the mobile terminal but it couldalso be located elsewhere, with the mobile terminal having access to it via a privatenetwork or the Internet.

[0007] Those skilled in the art will appreciate that certain steps of the vehicular motionassessment method could be carried out remotely from the mobile terminal.Accordingly, a second aspect of the invention relates to a vehicular motion assessmentmethod, wherein above steps c., d., e. and f. are delegated to a data collection platform(also called “contextualization and profiling platform”). The method according to thesecond aspect thus comprises above steps a. and b., and further: o establishing a secure communication link with a data collection platformconfigured to carry out above steps c., d., e. and f.; and o transmitting the logged motion observations via the communication link to thedata collection platform.

In order to allow unambiguous identification of the vehicle by the data collectionplatform, the mobile terminal establishes a connection with the vehicle and tags themotion observations captured while the data connection exists with an identifier of themobile terminal and/or of the vehicle known to the data collection platform. Theconnection the mobile terminal establishes with the vehicle could be a data connection.However, although the possibility of data exchange between the vehicle and the mobileterminal may be preferable, it is not necessary for all applications of the invention. Forinstance, the connection could be established via a plug with wireless functionality thatconnects to the vehicle power supply (e.g. an ISO 4165:2001 connector): when theplug is powered by the vehicle, the wireless functionality is on and the mobile terminalmay sense the presence of the plug and hence that the vehicle power supply is on.

[0008] A third aspect of the invention relates to a vehicular motion assessmentmethod capable of being carried out by a data collection platform upon receipt of themotion observations. The method according to the third aspect comprises: o obtaining (e.g. via a data link, from a computer memory, etc.) motionobservations logged on-board a vehicle, the motion observations includingtimestamped vehicle positions; o determining if the obtained motion observations are organized in trips and, ifthey are not, dividing them into trips by detecting spatial and/or temporaldiscontinuities and/or a driver change in the obtained motion observations; o map-matching the motion observations so as to identify, for each vehicleposition a road link of a road network stored in a map database as well as amap-matched position on the road link; o contextualizing the motion observations by augmenting them with situationaldata obtained by querying the map database and/or another geographicinformation database; o determining, based on the contextualized motion observations, whether thevehicle was exposed, during the trips, to unsafe driving situations; and o communicating (e.g. to the mobile terminal or an authorized third party) one ormore risk scores indicative of accident probability, calculated based ondetermined exposures to unsafe driving situations.

[0009] Preferred embodiments of the different aspects of the invention are discussedbelow. The features of these preferred embodiments may apply to all aspects of theinvention unless it is clear from the context that this is not the case.

[0010] The motion observations could be logged with a frequency of at least 0.2 Hz(corresponding to a trackpoint every 5 s). Higher frequencies may be preferred , e.g.0.33 Hz, 0.5 Hz, 1 Hz, or still higher. The frequency with which the motion observationsare logged could also be dynamically adjusted depending on vehicle acceleration(including longitudinal and lateral acceleration of the vehicle).

[0011] The motion observations could include data collected by on-board sensors,e.g., information from smart tyres, shifting patterns, rotational speed, etc. Such vehicledata are preferably retrieved from the vehicle’s onboard communication system(s). Any data connection between the mobile terminal and the vehicle (e.g. the vehicle’s internalcommunications network, the CAN bus, a wireless communications interface of thevehicles, or the like) could be established over a wire connection or via a wireless link(e.g. Bluetooth™). Successful establishment of the data connection with the vehiclecould trigger the capturing of the motion observations and the rupture of the dataconnection with the vehicle could terminate the capturing of the motion observations.

[0012] Preferably, the motion observations are organized in trips, and a unique tripidentifier is associated with the motion observations captured during a continuous timeinterval starting with successful establishment of the (data) connection with the vehicleand ending with the rupture of the (data) connection. In other words, as long as a (data)connection between the mobile terminal and the vehicle uninterruptedly exists allmotion observations captured are associated with the same unique trip identifier. Inthis context, it may be worthwhile noting that the trip identifier and the vehicle and/ormobile terminal identifier could be combined into a complex identifier containing bothpieces of information.

[0013] The motion observations could be transmitted on-the-fly to the data collectionplatform. Alternatively or additionally, the mobile terminal could buffer the loggedmotion observations in a memory and transmit the buffered motion observations batch-wise to the data collection platform. The mobile terminal may be configured such thatit buffers the logged motion observations only when on-the-fly transmission is notpossible. Alternatively, buffered transmission could be the default option.

[0014] Preferably, the motion observations include, for each timestamped vehicleposition, at least one of vehicle speed, vehicle heading, vehicle acceleration, rate ofturn and engine rotational speed. When vehicle speed, vehicle heading and vehicleacceleration are not part of the raw data, they can be computed based on the loggedmotion observations. The determination whether the vehicle was exposed to unsafedriving situations is preferably also based on vehicle speed, vehicle heading andvehicle acceleration.

[0015] As used herein, the expression “situational data” refers to data correlating, interms of time and position, with the motion observations, so that they describe specificaspects of the situation in which the motion observations were made. The situationaldata used for augmenting the motion observations could include speed limits, roadtopology (e.g. slope, curvature), road type (e.g. motorway, rural road, urban road), number of lanes, traffic signs and traffic information (e.g. real-time traffic data orhistorical traffic data, including for instance, average speed of vehicles on a certainroad link for a certain date and time, etc.) The situational data could also includemeteorological data obtained by querying a meteorological database. Themeteorological database could be separate from the map database of integratedtherein, e.g. as one or more “layers”.

[0016] Exposure of the vehicle to unsafe driving situations could be tested byprocessing a list of unsafe driving situations statistically correlating with road accidentsand determining based on the contextualized motion observations whether and howoften a listed unsafe driving situation occurred. In practice, such a list may beimplemented as a series of tests and/or one or more decision trees.

[0017] The listed unsafe driving situations could include: o breaches of traffic regulations (such as, e.g., speeding, illegal turns, illegal Il-iums, running a stop sign, etc.) and o potentially dangerous manoeuvers or driver behaviour (such as, e.g., highbraking, high steering, harsh acceleration, fatigue driving, driving faster than thetraffic flow, etc.) [0018] In the calculation of the risk scores, each exposure to an unsafe drivingsituation is preferably accounted for according to the statistical probability of thisunsafe driving situation contributing to accidents. This statistical probability may bedetermined on the basis of road safety statistics and be stored as a parameter in thesoftware. In the calculation of the risk scores, the severity of the accidents (e.g. fatal,serious, slight) may be taken into account by weighting each exposure to an unsafedriving situation according to the statistical probabilities of this unsafe driving situationcontributing to accidents of the different severities.

[0019] Preferably, the one or more risk scores indicative of accident probability arescaled by spatial and/or temporal exposure factors that are indicative of exposure torisk considering geographical accident density and temporal accident density withrespect to time of day, respectively.

[0020] The contextualization of the motion observations could further comprise thedetermination of adverse circumstances (requiring the driver to exercise particularcaution), e.g. rain, fog, driving against the sun, high traffic density, etc. Unsafe driving situations imputable to the driver occurring in such adverse circumstances could beweighted more highly in calculation of the one or more risk scores indicative of accidentprobability (if accident statistics corroborate such higher weighting). Certain adversecircumstances may be directly available among the contextualization data. Otherscould be derived by combining directly available motion observations and/orcontextualization data. For instance, when the vehicle is driving under a clear sky(derivable from meteorological data) on a motorway (derivable from the “road type”information), glare by the sun could be detected by inputting vehicle position andheading, date and time into a sun position calculator.

[0021] Preferably, in the calculation of the one or more risk scores indicative ofaccident probability, unsafe driving situations imputable to the driver are taken intoaccount depending on the travelled distance over which the unsafe driving situationsexisted.

[0022] It may be worthwhile noting that the present invention makes possible moretargeted education of drivers having a risky driving style. The communication of therisk scores could be made to the driver (e.g. via the mobile terminal) and could includerecommendations for reducing the riskiness of their driving style based on thedetermined unsafe driving situations imputable to the driver. For instance, if it isdetected that a driver takes turns with relatively high speed, the driver could beinformed about how much their risk score (and, possibly, their insurance premium)could be reduced if they adopted a more prudent driving style.

Brief Description of the Drawings [0023] The accompanying drawing illustrates several aspects of the present inventionand, together with the detailed description, serves to explain the principles thereof. Inthe drawings:

Fig. 1 : is a schematic illustration of an embodiment of a vehicular motion assessmentmethod in accordance with the invention.

Detailed Description of a Preferred Embodiment [0024] The proliferation of mobile sensing and telematics systems in connectedvehicles have enabled the big-data industry in mobility. In particular driver profiling forinsurance purposes arises as a must-have for setting up UBI systems. In the preferred embodiment of the invention discussed below, driver profile correlation to objectivedriver risk is presented. It should be noted, however, that the invention is not limited tothis application, which has been chosen only for the purpose of illustration. Anotherpossible application of the invention could, for instance, be predictive maintenance.

[0025] According to the preferred embodiment, objective risk scores are providedbased on behavioural, spatial and temporal factors computed over contextualizedvehicular motion observations, which may be as simple as GNSS (Global NavigationSatellite System) tracks and/or contain further data measurable within the vehicle (e.g.speed, acceleration, vibrations, etc.) To compute risk scores, the probabilities of thesefactors being observed in real accidents, which are extracted from publicly availableroad safety statistics, serve as the empirical, objective basis.

[0026] There is a need to understand how driving behaviour variables impact thedriver’s risk of having an accident. Such understanding could be obtained bycorrelation analysis of driving data (i.e., telematics data) and real insurance claims.However, the required data are not readily available and even less so to the broaderpublic. Specifically, generating such a dataset would require a long time and importantinvestments. In the context of the present embodiment of the invention, historical roadsafety statistics are used to circumvent the above difficulty. Road safety reportspresent important amounts of information about accidents. To establish a link betweenvehicular motion observations and accident risk, reports dealing with the main causesof accidents have been considered. Specifically, a contextualization of the raw motionobservations is carried out. The contextualization comprises augmenting the rawmotion observations (i.e. the measurements made in the vehicle) with map data(situational data) obtained by querying a map database (e.g. HERE, Google Maps,OpenStreetMap) and extracting a set of risk-based telematics variables from thecontextualized vehicular motion observations.

[0027] Prior to analyzing motion observations and determining risk scores, a list oftelematics metrics or “unsafe driving situations” is determined that have well definedand documented links to risk. This list of telematics metrics (TM) can be computed inadvance and the rules to compute their values may then be stored in the software.These rules need not be updated frequently but updates may be advisable if new roadsafety reports become available of if new TM are to be computed.

[0028] A list of TM examples used in the context of the present embodiment of theinvention is provided in table 1 below. It should be noted that this list is not exhaustiveand could be extended (or reduced) in accordance with the needs of the specificapplication.

Table 1

[0029] Of the listed TM, TM1-TM18 as well as TM21-TM24 and TM35-TM36represent unsafe driving situations imputable to the driver (behavioural TM). TM19 andTM20 depend on the types of roads driven on. TM25 to TM30 are spatial (TM25-TM27)and temporal (TM28-TM30) exposure factors indicative of exposure to risk consideringgeographical accident density and temporal accident density with respect to time ofday, respectively.

[0030] The inventors identified the above listed TM by studying the ContributoryFactors (CF) to past road accidents. Specifically, in the context of the presentembodiment, the inventors adopted the methodology proposed by the UK Departmentfor Transport (https://www.qov.uk/qovernment/statistical-data-sets/ras50-contributory-factors). CF represent a measure of the main causes that led directly to an accident ofa given severity (fatal, serious and slight). On every accident reported, the authorities(e.g., police officer) fill a form (called STATS19) where the CF observed in the accidentare marked. A detailed explanation of each individual CF is given in the STATS20document (“Instructions for the Completion of Road Accident Reports from non-CRASH Sources”, available online under https://www.qov.uk/qovernment/uploads/system/uploads/attachment data/file/230596/stats20-2011.pdf). The above official documents are mentioned for the purpose ofillustration. Any other road safety report that follows a similar CF approach could beused in the context of the present invention, which is not limited to the use of the above-mentioned road safety report.

[0031] Out of the 78 CF presented in STATS19, a subset of at least 21 CF that canbe measured through TM was identified. Table 2 below indicates the 21 identified CFmeasurable with TM. Again, it should be noted that Table 2 is not exhaustive and thatthe used CFs could be adapted depending on the needs of the application.

Table 2

[0032] The proposed methodology aims at predicting, for every trip, which of thoseOF would have been triggered in a hypothetical accident. This represents an a priorijudgement of the driver behaviour during the trip by using the same methodology asfor police reported accident.

[0033] In order to do so, each measurable CF is computed as a binary variable (i.e.,enabled or disabled) using a logical combination of TM constrained by predefinedthresholds. This combination is done in a way to well-represent the CF involved. Forinstance, as illustrated in Table 2, CF 306, ’’Exceeding Speed Limit”, is computed usingTM1 (Speeding average) and TM2 (Speeding proportion). Also, CF 601, “Aggressivedriving”, takes into account TM8 (High steering), TM10 (Positive Kinetic Energy) andTM11 (Negative Kinetic Energy). These metrics have been proven to be highlycorrelated to aggressive driving in the literature, see G. Castignani, T. Derrmann, R.Frank, and T. Engel, “Validation study of risky event classification using driving patternfactors,” in 2015 IEEE Symposium on Communications and Vehicular Technology inthe Benelux (SCVT), pp. 1-6, Nov. 2015 and D. A. Johnson and M. M. Trivedi, “Drivingstyle recognition using a smartphone as a sensor platform,” in 2011 14th InternationalIEEE Conference on Intelligent Transportation Systems (ITSC), pp. 1609- 1615,Oct. 2011. More complex CF, like CF 302, ’’Disobeyed Give Way or Stop”, needsconsideration of the traffic signs information coming from the contextualizationprocess, in combination with TM14 and TM15, which measure the driver’s attitudewhile approaching yield and stop signs.

[0034] In the present embodiment of the invention, in order to compute an objectivemeasure representing the vehicle’s exposure to risk (i.e. a risk score), the CFpresented above are linked with their corresponding occurrences in accidents given bystatistical reports that show information about the presence of CF in accidentsaccording to their severity (i.e. fatal, serious, slight) and to the road type where theyoccurred (i.e. motorway, urban and rural roads). This calculation is performed for everytrip of a vehicle in accordance with Eq. T.

(Eq. 1)

In Eq. 1, N is the number of CF and ac. is a binary variable which represents whetherthe ith CF has been enabled in the trip or not. As stated above, this is measured usinga combination of TM (see Table 2). If a given CF has been observed in the trip, theexposure for that CF is computed using its related statistics. Firstly, the exposureaccording to the road typej (j = 1,..., M) is computed using whjch is the probabilityof the ith CF being involved in an accident on a road of type Rj. M could be 3 with j = 1,2 or 3 meaning motorway, urban or rural road, respectively. dR. is the proportion ofdistance driven on each road type j. Then, this value is used along with the statisticsregarding accident severity, where Wp \ Wscel and 14^É are the probabilities of the ith CFbeing involved in fatal, serious and slight accidents, respectively. Finally, the sum iscomputed over all CF, giving as a result the vector sB = (sB,sBe,sBl )r (superscript “T”meaning transposition), which represents the behavioural (i.e. driver-imputable)exposure to fatal, serious and slight accidents for the given trip. It is worthwhile notingthat Eq. 1 could be easily adapted if the accident categories (here: fatal, severe andslight) changed.

[0035] The exposures are then combined in order to get a risk score. This can bedone by using accident cost information from road safety reports (e.g. “Accident andcasualty costs (RAS60)” available under https://www.qov.uk/qovernment/statistical-data-sets/ras60-averaqe-value-of-preventinq-road-accidents). Specifically, in thisexample, we compute C = (CF,CSe,Csl )T, representing the average normalized costof fatal, serious and slight accidents. Then, the risk score of a trip, that takes intoaccount behavioural exposure only may be calculated by:

(Eq. 2)where “·” represents the scalar product.

[0036] Parameters WFCi, Wscj and (i = 1_____17) as well as CF,CSe,Csl are calculated in advance. Like the rules for computing the TM, these parameters need notbe changed frequently but updates can be made at larger intervals (e.g. every year).[0037] Factors other than behavioural ones may have an impact on the risk score. Inparticular, the route taken as well as the time and length of the trip might increase ordecrease the potential exposure to have an accident. By using the history of accidents

reported, R^rip can be extended using spatial and temporal scaling to provide the finalmetric RTrip. This may be done by defining diagonal matrices (see Eq. 3 and Eq. 4below), where each component is computed using TM25 to TM30 defined in Table 1and computing RTrip as indicated in Eq. 6: (Eq. 4) (Eq. 5) (Eq. 5) [0038] The diagonal components of Sspatiai and Stemporat preferably followexponential distributions with values ranging from 0.5 to 1.5. This allows obtaining anoverall trip risk score RTrip that is expressed as a scaling of the behavioural factor withspatial and temporal weighting factors. Therefore, Æ®rip is scaled up or down accordingto the individual route, time and length of the trip.

[0039] For the spatial weighting matrix Sspatiai, road segments (i.e. road links of themap database) where accidents of different severities have been reported are takeninto account. For the temporal weighting matric Stemporai the time slots of thoseaccidents are taken into account. In other words, the spatial and temporal weightingmatrices depend on the geographical local density of past accidents and on thetemporal density, with respect to time of day, respectively. The effect of the spatial andtemporal weighting matrices may be illustrated by considering two drivers having thesame behavioural exposure sB and driving trips of equal length. Supposing that thetrips take place simultaneously (resulting in identical Stemporal matrices for bothdrivers), the driver who drives on road segments where accidents have been reportedin the past will obtain a higher risk score than his fellow who drives on road segmentswhere no accidents have happened. Supposing that the trips take place on the sameroads (resulting in identical Sspatiai matrices for both trips) but at different times (e.g.on different days of the week or at different times of the day), the driver who drives ata time at which accidents are more frequent will obtain a higher risk score than thedriver who drives at a time at which accidents are less frequent.

[0040] Fig. 1 summarizes the overall process according to the illustrative embodimentof the invention. Illustrations of the different steps are provided on the left-hand sideand the corresponding data made available are shown in the test boxes on the right-hand side.

[0041] Motion observations are recorded by a mobile terminal 10 on-board a vehicle12. The mobile terminal 10 is in this case represented as a smartphone (for the purposeof illustration). The mobile terminal 10 includes a GNSS receiver or is connected withthe GNSS receiver of the vehicle 12 and logs the vehicle position with a frequency of,e.g., 1 Hz. The recording starts when the mobile terminal has established a dataconnection 13 (e.g. a Bluetooth™ connection) with the vehicle’s wirelesscommunication interface 14. Optionally, an additional condition for the start of therecording could be that an initial position change is detected. As long as the data linkexists without interruption, all motion observations are deemed to belong to the sametrip and are stored under the same trip identifier (tripID). The recording ends when thedata connection 13 is terminated. The corresponding trip is closed in consequence andthe next trip will be given another TripID. In the drawing, the raw motion observationsare represented by a file having a header with the vehicle identifier (vehiclelD) and thetripID and a matrix wherein each line corresponds to one recording instant.

[0042] Regarding the representation in matrix form it should be noted that thisrepresentation was chosen because it is convenient for illustration but is not meant toimply any particular data structure. For instance, the motion observations could berecorded in an XML file. In the illustrated embodiment, each data point of the rawmotion observations includes the time (tz), the position (xt), the velocity (v^) obtainedfrom the GNSS receiver, and, possibly, readings from other sensors (not shown in thedrawing), e.g. accelerations and turn rates obtained by an IMU. It may be worthwhilenoting that the file could contain other metadata, such as, e.g. identifiers of the mobileterminal, the driver, the (type of) GNSS receiver, etc.

[0043] The mobile terminal 10 transmits the motion observations to a data collectionplatform 16 via a secure communication link. The management of the securecommunication link is preferably one of the tasks carried out by the application (“app”)that also manages data connection with the vehicle and the collection of the motionobservations.

[0044] The data collection platform 16 is connected to a map database 18, which itqueries in order to map-match the raw motion observations. The map-matching stepcomprises finding the road links (of the map) that correspond to the measuredpositions. Due to possible measurement errors, some measured positions could lie off-road. In this case, the map-matching step returns the road links (in the form of thecorresponding road link identifier “UnklDi”) and corrected positions (%corr)i, whichsatisfies the constraint that it lies on the ith road link of the map) that best fit with theraw motion observations. The data collection platform 16 further augments the motionobservations with map data retrieved from the map database. These additional mapdata (contextualization data) serve to explain the situation in which the motionobservations were made, which allows assessing the motion observations in theircontext. Contextualization data include, for instance, the speed limits (v_maxi) in forceon the road links, road type, (historic) traffic information (local traffic density, localaverage speed at the time of the observations), information on traffic signs (e.g. “noovertaking”, “no U-turn”, “yield”, “stop”, “pedestrian crossing”, “slippery road”, etc.),historic weather data, information on past geographical and temporal accident density.In order not to overload the drawing, only the speed limit information is explicitly shownthereon.

[0045] The next step of the process comprises the analysis of the contextualizedmotion observations (“profiling”). That analysis involves computing the telematicsmetrics (TM1-TM30, cf. Table 1) for each trip. Specifically, the data collection platform16 processes the list of telematics metrics TM1-TM30 (which are linked to ContributionFactors statistically correlating with accident probabilities, cf. Table 2) and determinesthe value of each telematics metrics for the trip under examination. The analysis stepfurther comprises determining the different risk scores. In the illustrated example, sBand RTrip are determined via Equations 1 and 5. Finally, risk integration is carried out:this step comprises calculating an overall risk score Roverau taking into account all tripsof a given period.

[0046] Finally, the different risk scores are communicated to the customers. In theillustrated case, these include the driver, who receives his scores on their smartphone 10, a third party 20 or both. The third party could be a fleet managementcompany or an insurer. It should be noted that the data communicated to third partiescould be anonymized, if necessary.

[0047] It is worthwhile noting that the data collection platform could be implementedas a cloud computing platform. Preferably, it is divided into different functional blocks,comprising, in particular, a map-matching and contextualization block 22 and a profilingblock 24.

[0048] Risk-scores could also be used for coaching purposes. Drivers with riskydriving behaviour could be intelligently guided with driving advice related to their profile.Beyond insurance applications, road safety associations and authorities could set updriving campaigns based on the proposed risk score to increase awareness in roadsecurity and safety.

[0049] While a specific embodiment and a specific example have been describedherein in detail, those skilled in the art will appreciate that various modifications andalternatives to those details could be developed in light of the overall teachings of thedisclosure. Accordingly, the particular arrangements disclosed are meant to beillustrative only and not limiting as to the scope of the invention, which is to be giventhe full breadth of the appended claims and any and all equivalents thereof.

Claims

A vehicle motion evaluation method, comprising: a. capturing motion observations with a mobile terminal embarked on a vehicle, the mobile terminal including or being connected to a GNSS receiver, the motion observations including the timestamped positions of the vehicle measured by the GNSS receiver during a trip; b. the recording of motion observations; vs. mapping the motion observations so as to identify, for each position of the vehicle, a road link of a route network recorded in a map database as well as a map-referenced position on the road link; d. the contextualization of the motion observations by the increase thereof with situational data obtained by querying the cartographic database and / or another database of geographical information; e. the determination, based on the contextualized observations of movement, if the vehicle was exposed, during the journey, to dangerous driving situations; and F. the communication of one or more risk scores indicative of a probability of accident, calculated on the basis of the exposure to determined dangerous driving situations.

2. A vehicle motion evaluation method, comprising: capturing motion observations with a mobile terminal embedded in a vehicle, the mobile terminal including or being connected to a GNSS receiver, the motion observations including the timestamped positions of the vehicle; transported by the GNSS receiver during a trip; the recording of motion observations; establishing a secure communication link with a data collection platform configured to perform steps c., d., e. and F. defined in claim 1; the transmission of the recorded motion observations via the communication link; wherein the mobile terminal connects with the vehicle and labels the captured motion observations while said connection exists with an identifier of the mobile terminal and / or known vehicle of the data collection platform.

3. The vehicle motion evaluation method as claimed in claim 2, wherein the successful establishment of the connection with the vehicle triggers the capture of motion observations, in which the breaking of the connection with the vehicle terminates. to the capture of observations of movement.

4. The vehicle motion evaluation method as claimed in claim 2 or 3, wherein the connection established by the mobile terminal with the vehicle is a data connection.

The vehicle motion evaluation method as claimed in any one of claims 1 to 4, wherein the motion observations are organized into paths, and wherein a unique object identifier is associated with motion observations captured during a continuous interval of time starting with the successful establishment of a data connection with the vehicle and ending with the termination of the data connection.

The vehicle motion evaluation method as claimed in any one of claims 2 to 5, wherein the motion observations are transmitted on the fly to the data collection platform.

The vehicle motion evaluation method as claimed in any one of claims 2 to 6, wherein the mobile terminal encapsulates motion observations recorded in a memory and transmits the batch buffered motion observations to the data collection platform.

The vehicle motion evaluation method as claimed in any one of claims 1 to 7, wherein the motion observations include, for each timestamped position of the vehicle, at least one of the following: vehicle speed, vehicle heading, vehicle acceleration, cornering frequency and engine rotational speed.

9. The vehicle motion evaluation method as claimed in any one of claims 1 to 8, wherein the motion observations are recorded at a frequency of at least 0.2 Hz during portions of the path.

The vehicle motion evaluation method as claimed in any one of claims 1 to 9, wherein the frequency at which the motion observations are recorded is dynamically adjusted depending on the acceleration of the vehicle.

A vehicle motion evaluation method, comprising: obtaining motion observations recorded on a vehicle by a mobile terminal, the motion observations including the timestamped positions of the vehicle; determining whether the motion observations obtained are organized and, if they are not, dividing it into paths by detecting spatial and / or temporal discontinuities and / or a conductor change in the motion observations obtained; mapping the motion observations in such a way as to identify, for each position of the vehicle, a road link of a road network recorded in a map database as well as a map-referenced position on the road link; contextualizing the motion observations by increasing it with situational data obtained by query from the datapartographic database and / or another database of geographical information; the determination, based on the contextualized observations of movement, if the vehicle was exposed, during the trip, to dangerous driving situations, and the communication of one or more risk scores indicative of an accident probability, calculated on the basis of exposure to determined hazardous situations.

The vehicle motion evaluation method as claimed in any one of claims 1 to 11, wherein the situational data used to increase the motion observations include speed limits, a route topology, a route type. , number of channels, signaling panels and / or traffic information.

The vehicle motion evaluation method as claimed in any one of claims 1 to 12, wherein the situational data used to increase the motion observations include weather data.

The vehicle motion evaluation method as claimed in any one of claims 1 to 13, wherein the recorded movement observations include a vehicle speed, a vehicle heading and an acceleration of the vehicle, or a speed of the vehicle, a heading of the vehicle and an acceleration of the vehicle are calculated on the basis of the recorded motion observations, and in which the determination whether the vehicle has been exposed to dangerous driving situations is also based on a vehicle speed, a heading of the vehicle and a acceleration of the vehicle.

The vehicle motion evaluation method as claimed in any one of claims 1 to 14, wherein the recorded motion observations include data collected by embedded sensors, e.g. eg intelligent tire information, speed change patterns, rotational speed, etc.

16. The vehicle motion evaluation method as claimed in any one of claims 1 to 15, wherein the exposure of the vehicle to dangerous driving behaviors is tested by processing a list of statistically dangerous driving conditions. with road accidents and determination, based on contextualized observations, whether, and how often, a dangerous driving situation listed has occurred.

17. The vehicle motion evaluation method as claimed in claim 16, wherein the list of dangerous driving situations includes dangerous driving situations attributable to the driver.

18. The vehicle motion evaluation method as claimed in claim 16 or 17, wherein the dangerous driving situations listed include: o traffic violations (such as, for example, excess speed, turns, etc.); illegal, illegal U-turns, passing a stop signal, etc.) and o potentially dangerous maneuvers or conductor behavior (such as, eg, steep braking, sharp bends, large acceleration, driving while tired, etc.) .)

19. The vehicle motion evaluation method as claimed in any one of claims 1 to 18, wherein the one or more incidental indicative scores of the accident probability are scaled by exposure factors. spatial and temporal factors, the spatial exposure factors being indicative of the exposure to a risk considering the geographical density of accident, the temporal exposure factors being indicative of the exposure to a risk considering the temporal density of accident compared to at a time of the day.

20. The vehicle motion evaluation method as claimed in any one of claims 1 to 19, wherein the contextualization of the motion observations comprises the determination of reverse circumstances and in which the dangerous driving situations attributable to the driver have occurred. in such adverse circumstances have more weight in the calculation of one or more risk scores indicative of the probability of accident.

21. The vehicle motion evaluation method as claimed in any one of claims 1 to 20, wherein, in the calculation of one or more risk scores indicative of the probability of an accident, the situations of dangerous driving are taken. depending on the distance traveled on which dangerous driving situations existed.

22. An application comprising instructions, which, when executed by a processor of a mobile terminal, such as, e.g. ex. a smart phone, a tablet, a tablettophone, a laptop computer, a diagnostic board unit or the like, cause the mobile electronic device to perform the method as claimed in any one of claims 1 to 21.