JP2006112338A - Drive assist system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a drive assist system issuing refueling instruction to reduce fuel consumption quantity. <P>SOLUTION: A CPU 21a estimates fuel quantity consumed by a vehicle in travel from a filling station to a destination and reports refueling quantity at the filling station based on the estimated fuel consumption quantity and fuel remaining quantity. The CPU 21a searches filling stations on a route from a present location to the destination, reasons fuel consumption quantity from the present location to each filling station and reports the filling station to which fuel consumption quantity is reasoned maximum in the filling stations excluding the filling stations to which fuel consumption quantity exceed remaining fuel quantity. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a driving support system, and more particularly to a driving support system that gives a fueling instruction.

  Conventionally, as a driving support system that performs the above-described refueling instruction, for example, navigation devices described in Patent Documents 1 and 2 are known. For example, in the device described in Patent Document 1, when the remaining fuel is reduced below a predetermined value by the remaining fuel detection means of the vehicle, the driver is notified that the refueling time has come, and guidance to the refueling station on the route is made. I do.

Moreover, in the thing of patent document 2, based on the distance from the present position to the destination, the remaining amount of fuel, and the fuel consumption, it is determined whether or not the fuel runs out before reaching the destination. When it is determined that the fuel has run out before reaching the destination, the driver is notified of this. Further, when it is determined that the fuel runs out, the fuel stations that can be reached with the current remaining fuel amount are searched, and when the searched fuel station number N is a predetermined number N0 or more, the distance from the current position is N0 refueling stations are selected in order from the farthest, and they are output as final refueling candidates.
JP-A-5-71974 Japanese Patent Laid-Open No. 11-14281

  By the way, especially in the delivery trader, the fuel consumption of the delivery vehicle is reflected in the delivery cost. Therefore, in order to reduce the delivery cost, there has been a demand for reducing the fuel consumption for traveling as much as possible. Therefore, when there is a gas station at the business site, the delivery company starts operation without filling up the tank at the time of departure and refueling as much as possible, thereby reducing the total weight of the vehicle and reducing fuel consumption. An attempt was made.

  However, in the invention described in Patent Document 2, it is not instructed how much refueling is necessary to perform the operation only by notifying whether or not the vehicle arrives at the destination with the current remaining fuel amount. Therefore, the driver himself had to judge the required amount of oil before operation and refuel.

  In addition, when refueling is necessary during operation, it is desirable for fuel saving to enter the refueling station with the remaining amount close to zero and refuel from the refueling station for the remaining operation. However, in the invention described in Patent Document 1 or 2, the gas station is not guided from the viewpoint of fuel saving. Also, simply guiding to a gas station does not indicate how much oil is needed at that gas station. Accordingly, in this case as well, the driver himself has to determine the amount of oil necessary for the remaining operation from the gas station and supply the fuel. In any case, conventionally, there has been no instruction for refueling to save fuel.

  Accordingly, the present invention focuses on the above-described problems, and an object thereof is to provide a driving support system that gives a refueling instruction to reduce fuel consumption.

  The invention according to claim 1, which has been made to solve the above-described problem, is an inference means for inferring a fuel consumption amount consumed by a vehicle by operation from a gas station to a destination, and a fuel remaining amount measurement for measuring a fuel remaining amount. And a fuel supply amount notifying means for notifying the fuel supply amount at the filling station based on the inferred fuel consumption amount and the measured remaining fuel amount.

  According to the first aspect of the present invention, the estimating means estimates the fuel consumption consumed by the vehicle by the operation from the gas station to the destination. The fuel supply amount notification means notifies the fuel supply amount at the gas station based on the estimated fuel consumption amount and the remaining fuel amount. Therefore, it is possible to notify the marginal amount of fuel supply that makes the remaining fuel amount the amount of fuel consumption necessary for operation to the destination.

  The invention according to claim 2 is the driving support system according to claim 1, wherein the inference means infers the departure place as the gas station in response to input of operation information including the departure place and the destination. The driving support system is characterized by starting.

  According to the invention described in claim 2, the inference means starts the inference using the departure place as a gas station in response to the input of operation information including the departure place and the destination. Therefore, by starting the inference in response to the input of the operation information, it is possible to notify the optimal fuel supply amount that saves fuel before the operation.

  According to a third aspect of the present invention, there is provided a gas station search means for searching for a gas station on a route from a current position to a destination, and a fuel from the current position to each gas station when a plurality of gas stations are searched. Among the inference means for inferring the consumption, the fuel remaining amount measuring means for measuring the remaining amount of fuel, and the fuel consumption exceeding the measured remaining fuel amount from the plurality of estimated fuel consumptions, the maximum There is a driving support system characterized by comprising a gas station notifying means for informing a fuel station where the amount of fuel consumption is inferred.

  According to the invention described in claim 3, the gas station search means searches for a gas station on the route from the current position to the destination. The inference means infers the fuel consumption from the current position to each gas station when a plurality of gas stations are searched. The gas station notifying means notifies the gas station where the maximum fuel consumption amount is inferred from the estimated fuel consumption amounts excluding the fuel consumption amount exceeding the remaining fuel amount. Therefore, it is possible to notify the gas station that passes when the remaining amount of fuel is closest to zero.

  A fourth aspect of the present invention is the driving support system according to the first aspect, wherein the inference means includes travel route information detection means for detecting travel route information relating to a travel route on which the vehicle is traveling, and the vehicle. Fuel consumption information detection means for detecting the fuel consumption information of the vehicle, and learning means for performing learning using the detected current travel route information as input and outputting the detected current fuel consumption information as output. The driving support system is characterized in that, using the learned result, the driving route information is input, the fuel consumption information is output as an inference, and the fuel consumption is inferred using the inference.

  According to the invention of claim 4, in the inference means, the travel route information detecting means detects travel route information relating to the travel route on which the vehicle is traveling, and the fuel efficiency information detecting means detects the fuel efficiency information of the vehicle, and learning The means performs learning using the detected current travel route information as an input and the detected current fuel consumption information as an output. The inference means uses the learning result performed by the learning means to infer the travel route information as an input and the fuel efficiency information as an output, and infers the fuel consumption using the inference. Therefore, using the detection results of the travel route information detection means and the fuel consumption detection means, learning using the travel route information as input and the fuel consumption information as output is performed, and the fuel consumption is inferred using the learning result. . That is, the relationship between the travel route information and the fuel consumption information can be obtained by learning performed during travel, and it is not necessary to create a map indicating the relationship between the travel route information and the fuel consumption information in advance.

  As described above, according to the first aspect of the present invention, the fuel supply amount can be notified of the fuel supply amount that is the fuel consumption necessary for operation to the destination, so that the driver himself can supply the fuel supply amount. Even if it is not considered, the vehicle can be run with the lightest vehicle weight by refueling according to the refueling amount notification. That is, it is possible to obtain a driving support system capable of giving a refueling instruction that provides the best fuel efficiency.

  According to the second aspect of the invention, since the inference is started in response to the input of the operation information, it is possible to notify the optimum amount of fuel that saves fuel before the operation, so there is a gas station at the departure point. In such a case, it is possible to obtain a driving support system that can start with an optimal amount of refueling.

  According to the invention described in claim 3, since it is possible to notify the gas station that passes when the remaining amount of fuel is closest to zero, it is possible to supply the fuel according to the gas station notification even if the driver himself does not consider the fueling timing. If you do this, you can drive with the lightest vehicle weight. That is, it is possible to obtain a driving support system capable of giving a refueling instruction that provides the best fuel efficiency.

  According to the fourth aspect of the present invention, learning is performed using the detection results of the travel route information detection unit and the fuel consumption detection unit as input of the travel route information and output of the fuel consumption information. Inference of fuel consumption is made. That is, it is possible to obtain the relationship between the travel route information and the fuel consumption information by learning performed during traveling, and it is not necessary to create a map showing the relationship between the travel route information and the fuel consumption information in advance. Thus, it is possible to obtain a driving support system that can be installed without selecting a vehicle.

  Hereinafter, a driving support system of the present invention will be described with reference to the drawings. The driving support system of the present invention is, for example, a system that gives a refueling instruction to a delivery vehicle that collects and delivers a package. FIG. 1 is a block diagram showing an embodiment of a navigation device incorporating the driving support system of the present invention. As shown in the figure, a microcomputer (hereinafter referred to as μCOM) 21 provided in the navigation device 20 of the present invention is supplied with a fuel pulse Pf that is output every time 1 cc of fuel is consumed.

  The μCOM 21 described above also includes a GPS receiver 22 that receives a positioning signal S1 from an artificial satellite constituting a global positioning system using a GPS antenna AT1, and a road traffic information communication system (Vehicle Information and Communication). A VICS receiver 23 that receives road information S2 including traffic congestion information, road regulation information, and the like from the VICS center that constitutes the vehicle, and a weight meter 24 that measures the weight of the vehicle and outputs its own weight information W. And the above-described positioning signal S1, road information S2 and own weight information W are supplied.

  The μCOM 21 also includes a map storage unit 25 in which map data is stored, a display unit 26 including a liquid crystal display, and a fuel remaining amount meter 27 (= fuel remaining amount measuring means) for measuring the remaining amount of fuel. The fuel remaining amount Sf described above is connected.

  The μCOM 21 includes a central processing unit (CPU) 21a that performs various processes according to programs, a ROM 21b that is a read-only memory that stores programs for processes performed by the CPU 21a, a work area and various data that are used in various processes in the CPU 21a. A RAM 21c, which is a readable / writable memory having a data storage area for storing the data, and the like are incorporated.

  The operation of the navigation device having the above-described configuration will be described below with reference to FIGS. In accordance with a fuzzy neuro-network as shown in FIG. 2, the CPU 21a receives the travel route information R, the traffic jam occurrence location, the traffic jam information T including the traffic jam distance and the traffic jam transit time, and the own weight information W as input data, and unit distance (for example, Learning / inference is performed using the fuel consumption α per 100 m) as output data. In the map data, numbers R1, R2,... Are assigned in advance to the travel route, and the number assigned to the route traveled by the vehicle is input as the travel route information R.

  First, the CPU 21a in the navigation device 20 functions as a learning unit and performs the above-described learning. For example, the CPU 21a executes a learning data creation process every time a certain distance such as 100 m is traveled. The processing procedure of the CPU 21a in this learning data creation processing will be described below with reference to the flowchart of FIG. In step S1, the CPU 21a functions as a travel route information detecting unit, obtains the current position from the positioning signal S1 received by the GPS receiver 22, and determines the current travel route from the obtained current position and the map data stored in the map storage unit 25. Information Rp is detected.

  Further, the CPU 21a detects the current traffic jam information Tp from the road information S2 received by the VICS receiver 23. Further, the CPU 21a functions as fuel efficiency information detection means, detects the current fuel consumption amount αp (cc) per 100 m from the fuel pulse Pf, and detects the current weight information Wp from the self-weight meter 24.

In step S2, as shown below, the CPU 21a uses the detected current travel route information Rp, current traffic jam information Tp, and current weight information Wp as input data Iw, and current fuel consumption αp as output data Ow (teacher signal). Create learning data.
Iw = (Rp, Tp, Wp)
Ow = (αp)
Details of learning and inference using the fuzzy neuro of FIG. 2 will be described later.

  Further, when the driver inputs the operation information, the CPU 21a in the navigation device 20 starts the navigation process. As the above-mentioned operation information, for example, it is assumed that the information about the operation to return to the office A after loading X1 kg from the office A at the delivery destination P1 and unloading the X2 kg bag at the delivery destination P2 is described below. To do. In the navigation process, the CPU 21a performs a route search for performing the above-described operation from the map data in the map storage unit 25 (step S10). At this time, the CPU 21a detects a passage prohibition point from the road regulation information included in the road information S2 received by the VICS receiver 23, and performs a route search so as to exclude a route passing the passage prohibition point.

  Next, the CPU 21a works as an inference means, and estimates the fuel consumption for the operation using the fuzzy neuron shown in FIG. 2 (step S11). In step S10, the CPU 21a first creates input data including (travel route information R, traffic jam information T, dead weight information W) for input to the neuro network as shown in FIG. In creating input data, the CPU 21a first obtains the current traffic jam information Tp from the road information S2 received by the VICS receiver 23.

Next, the CPU 21a, for example, in the route search in step S10, as shown in FIG. 5, the route R11 from the office A via the travel route R1 → R2 to the delivery destination P1, and the travel route R1 → R3 → R2. When a plurality of routes with the route R12 reaching the delivery destination P1 via the route are searched, the travel routes R1, R2, R3 constituting the respective routes R11, R12, the current traffic jam information Tp, and the current weight information Wp are obtained. A plurality of patterns of input data I1, I2, and I3 are created.
I1 = (R1, Tp, Wp)
I2 = (R1, Tp, Wp)
I3 = (R3, Tp, Wp)

Similarly, for example, in the route search in step S10, the CPU 21a passes only the route R21 from the delivery destination P1 to the delivery destination P2 via the travel route R4 → R5 and the travel route R6 as shown in FIG. When two travel routes with the route R22 leading to the delivery destination P2 are retrieved, the load amount is added to the travel routes R4, R5, R6 constituting the respective routes R21, R22, the current traffic jam information Tp, and the current own weight information Wp. A plurality of patterns of input data I4, I5, and I6 are created by combining the values obtained by adding X1.
I4 = (R4, Tp, Wp + X1)
I5 = (R5, Tp, Wp + X1)
I6 = (R6, Tp, Wp + X1)

Similarly, for example, when the CPU 21a searches only the route R31 from the delivery destination P2 to the office A via the travel route R5 → R1 as shown in FIG. A plurality of patterns of input data I7 and I8 are generated by combining the travel routes R5 and R1 constituting R31 and the value obtained by adding the load amount X1 and subtracting the unloading amount X2 to the current traffic jam information Tp and the current weight information Wp. .
I7 = (R5, Tp, Wp + X1-X2)
I8 = (R1, Tp, Wp + X1-X2)

  Next, in the CPU 21a, the generated input data I1 to I8 are input to the network as shown in FIG. 3, and inference processing for inferring the fuel consumptions α1 to α8 for the input data I1 to I8 is performed.

  Here, the fuel consumption amount α1 output in response to the input of the input data I1 = (R1, Tp, Wp) is consumed every time the travel route R1 travels a unit distance when the traffic congestion information Tp and the own weight information Wp. It corresponds to the estimated value of fuel consumption. The same applies to the fuel consumption amounts α2 to α8. Therefore, the fuel consumptions α1 to α3 are multiplied by the distances / unit distances of the travel routes R1 to R3 in the routes R11 and R12 to obtain the fuel consumptions α11 and α12 for the travel routes R11 and R12, respectively (for example, the route If R11 is composed of a ym travel route R1 and a zm travel route R2, the fuel consumption amount α11 for travel on the route R11 is α1 × y / unit distance + α2 × z / unit distance (cc). From). Further, based on the fuel consumption amounts α4 to α6, fuel consumption amounts α21 and α22 for traveling on the travel routes R21 and R22 are obtained. Further, based on the fuel consumption amounts α7 and α8, a fuel consumption amount α31 for traveling on the travel route R31 is obtained.

  The CPU 21a adds the smallest fuel consumption amount α1min among the estimated fuel consumption amounts α11 and α12, the smallest fuel consumption amount α2min among the inferred fuel consumption amounts α21 and α22, and the inferred fuel consumption amount α31. Let (= α1min + α2min + α31) be the inferred fuel consumption.

  Thereafter, the CPU 21a starts route guidance using the delivery destination P1 and the delivery destination P2 as a route (step S12). At this time, as a route from the establishment A to the delivery destination P1, for example, of the inferred fuel consumptions α11 and α12, the route R11 is guided if α11 is the minimum value, and the route R12 if α12 is the minimum. To guide you. Similarly, as a route from the delivery destination P2 to the delivery destination P3, for example, among the inferred fuel consumptions α21 and α22, the route R21 is guided if α21 is the smallest, and the route R22 is guided if α22 is the smallest. To do. A route R31 is guided as a route from the delivery destination P2 to the office A.

  Further, the CPU 21a functions as a fuel supply amount notification means, and displays a value obtained by subtracting the fuel remaining amount Sf measured by the fuel remaining amount meter 27 from the inferred fuel consumption obtained in step S10 as a fuel supply amount on the display unit 25 (step 25). S13). As a result, the driver can grasp how much fuel can be supplied at the office A before operation with minimum fuel remaining. In addition, as a fuel supply amount to be displayed, for example, a value obtained by adding a safety margin to a value obtained by subtracting the remaining fuel amount Sf from the estimated fuel consumption may be displayed as the fuel supply amount.

  By displaying the amount of fuel supplied as described above, it is possible to notify the marginal amount of fuel used when the remaining amount of fuel in the vehicle becomes the amount of fuel consumption necessary for operation from the departure place to the destination. As a result, even if the driver himself does not consider the amount of oil before operation, the vehicle can be traveled with the lightest vehicle weight if refueling is performed according to the fuel amount notification. In other words, it is possible to instruct the amount of fuel that provides the best fuel efficiency. In addition, by inferring the fuel consumption amount according to the input of the operation information and notifying the refueling amount, it is possible to notify the optimum refueling amount that saves fuel before the operation. Thereby, when there is a gas station at the departure place, it is possible to start by optimizing the amount of oil supply.

  When the remaining fuel amount Sf becomes equal to or less than the predetermined amount after the operation is started (Y in step S14), the CPU 21a functions as a gas station search unit on the travel route starting guidance from the map storage unit 25 in step S11. A gas station is searched (step S15). Thereafter, the CPU 21a functions as an inference means. For example, when a plurality of gas stations G1 to Gn can be searched, the fuel consumption amounts αg1 to αgn consumed from the current position to the gas stations G1 to Gn are estimated ( Step S16).

  Next, the CPU 21a functions as a gas station notifying unit, and except for the estimated fuel consumptions αg1 to αgn exceeding the current remaining fuel amount Sf, the largest fuel consumption αgm among the estimated fuel consumptions αg1 to αgn excluded. Is instructed to refuel at the gas station Gm corresponding to (step S17). As a result, it is possible to notify the gas station Gm that passes when the fuel remaining amount is closest to zero, and even if the driver himself does not consider the fuel timing, if the fuel is supplied according to the instructed gas station, the vehicle weight is the most. You can drive with lighter. That is, it is possible to perform refueling at a refueling timing at which fuel efficiency is most improved.

  Thereafter, when the CPU 21a determines that it has arrived at the gas station Gm that is instructed to refuel based on the positioning signal S1 (Y in step S18), it works as an inference means, and calculates the fuel consumption for the remaining operation from the gas station Gm. It estimates (step S19), functions as a fuel supply amount notification means, displays a value obtained by subtracting the current fuel remaining amount Sf from the estimated fuel consumption amount as a fuel supply amount on the display (step S20), and returns to step S14. As a result, even if the driver himself does not consider the amount of fuel supplied, the vehicle can be traveled with the lightest vehicle weight if the fuel is supplied according to the information on the amount of fuel supplied. In other words, it is possible to instruct the amount of fuel that provides the best fuel efficiency.

  In contrast, if the CPU 21a determines that it has not arrived at the gas station Gm (N in Step S18), the CPU 21a returns to Step S14 again, and Steps S15 to S18 are repeated. In addition, this navigation processing ends when the delivery vehicle returns to the business office A and ends its operation.

  The learning / inference in the present embodiment uses fuzzy neuro. Fuzzy neuro is a fusion of the advantages of a conventional neural network and fuzzy reasoning. This fuzzified neuro has, as basic components, a filter function called a trapezoidal membership function (hereinafter referred to as MF) generally used in fuzzy inference and an element having a weight w. As shown in FIG. 2, the MF is expressed by approximating the frequency distribution of input data to a normal distribution.

  FIG. 2 shows the network configuration of the fuzzy neuro. The basic network configuration includes an input unit composed of normalization tables NT1 to NT3, a pre-stage unit composed of a three-layer structure of pattern sets PS1 to PS3, pattern tables PT1 and PT2, pattern sets PS4 and PS5, and a normalization table NT4. It has a two-layer structure, and is composed of a rear-stage part that is an inversion of the front-stage part. In the input unit, the input data is converted into normalized data in the normalization tables NT1 to NT3, respectively. Each normalized input data is input to the MF, where it is converted into a matching degree.

  The pattern sets PS1 to PS3 in the next stage are composed of MF aggregates, and the outputs obtained by combining the matching degrees obtained by the MFs using weights are output. In the pattern tables PT1 and PT2 of the output unit, the highest one of the matching degrees output from the plurality of pattern sets PS1 to PS3 is output to the subsequent stage unit. In the subsequent stage, in the pattern sets PS4 and PS5, the outputs from the pattern tables PT1 and PT2 that exceed the threshold are output, and the MF on the link is deformed according to the degree of coincidence, and the normalization table NT4 in the subsequent stage is changed. introduce. In the normalization table NT4, the MF shape obtained by synthesizing the transmitted MF shape is de-fuzzified by taking the center of gravity and the like, and converted into a continuous value having a dimension equivalent to the taught output data.

  In the learning process, the current travel route information Rp, the traffic jam information Tp, and the current weight information Wp created by the learning data creation process are input, and the current fuel consumption amount αp per unit distance travel is used as a teacher signal, and the membership function In this fuzzy neuro, learning is not performed for each teacher signal, but is learned after a certain number of accumulations, so that high-speed learning is possible.

  Further, according to the navigation device described above, the relationship between the travel route and the fuel consumption can be obtained by learning performed while traveling, and it is necessary to create a map indicating the relationship between the travel route and the fuel consumption in advance. In addition, the cost can be reduced and the vehicle can be installed without selecting a vehicle.

  In the above-described embodiment, as shown in FIG. 2, for example, as shown in FIG. 5, based on learning and inference using the travel route information R, the traffic jam information T, and the own weight information W as inputs and the fuel consumption information α as an output. The fuel consumptions α11, α12, α21, α22, and α31 consumed when traveling on the routes R11, R12, R21, R22, and R31 were obtained. However, for example, paying attention to the fact that the speed of the vehicle fluctuates depending on the travel route and traffic conditions, and the fuel consumption varies according to the fluctuation of the speed. Inferring can also be considered.

  Specifically, in the learning data creation process shown in FIG. 4, the CPU 21a functions as a speed detection means, obtains the current speed vp based on the speed pulse from the speed sensor, and inputs the current speed vp as the travel route information Rp. Learning is performed as Iw. Next, a method for estimating the fuel consumption amount α11 consumed when traveling on a route R11 including the traveling routes R1 and R2 shown in FIG. 5 will be described. The CPU 21a in the navigation device 20 estimates average speeds v1 and v2 in the travel of the travel routes R1 and R2 based on the speed limit of the travel routes R1 and R2, the traffic jam information on the travel routes R1 and R2, and the like. The average speeds v1 and v2 are input in place of the travel routes R1 and R2, and the inference is performed in the same manner.

  In this way, by learning and inferring the speed when traveling along the travel route as travel route information, it is easy and accurate without using GPS or map data for detecting the current position of the vehicle. The fuel consumption can be inferred, and the driving support can be performed in a low-cost and surely reducing manner.

  In addition, by inputting the vehicle speed considering current traffic information as travel route information and making inferences, it is possible to infer accurate fuel consumption considering traffic, thus reducing fuel consumption more reliably. Driving assistance can be performed.

  Further, in the above-described embodiment, learning and inference are performed with the travel route R, the traffic jam information T, and the own weight information W as inputs and the fuel consumption amount α per unit distance as an output. However, for example, it is conceivable to perform learning and inference by inputting the driver D in addition to the travel route information R, the traffic jam information T, and the own weight information W. Numbers D1, D2,... Are assigned to the driver in advance, and the number assigned to the driver is input as the driver D. Thereby, the driving skill of the individual driver can be reflected.

Although the present invention has been described based on the above embodiments, the present invention is not limited to the above-described embodiments, and various modifications and applications are possible within the scope of the gist of the present invention. Here, the gist of the present invention is summarized as follows.
(1) an inference means for inferring the amount of fuel consumed by the vehicle from the service station to the destination;
Fuel remaining amount measuring means for measuring the remaining amount of fuel;
A driving assistance system comprising: a refueling amount notifying unit for notifying a refueling amount at the filling station based on the inferred fuel consumption amount and the measured remaining fuel amount.

(2) Gas station search means for searching for a gas station on the route from the current position to the destination;
When a plurality of gas stations are searched, inference means for inferring fuel consumption from the current position to each gas station;
Fuel remaining amount measuring means for measuring the remaining amount of fuel;
A gas station notifying means for notifying a gas station where the maximum fuel consumption was inferred from the estimated plurality of fuel consumptions excluding the fuel consumption exceeding the measured fuel remaining amount was provided. A driving assistance system characterized by

(3) The driving support system according to (1) or (2),
The inference means includes travel route information detection means for detecting travel route information relating to a travel route on which the vehicle is traveling, fuel consumption information detection means for detecting fuel consumption information of the vehicle, and the detected current travel route information. Learning means for outputting the detected current fuel consumption information as an output, and using the learning result performed by the learning means, the travel route information is input and the fuel consumption information is output. A driving support system characterized in that the fuel consumption is inferred using the inference.

(4) The driving support system according to (3),
The travel route information detection means includes a current position detection means for detecting a current position of the vehicle and a map data storage means for storing map data, and the route on the map data with respect to the detected current position A driving support system characterized in that it is detected as travel route information.

(5) The driving support system according to (3) or (4),
The inference means further includes traffic information detecting means for detecting traffic information on the road,
The learning means inputs the detected current travel route information and the detected current traffic jam information as input, performs learning to output the detected current fuel consumption information,
The driving support system, wherein the inference means inputs the travel route information and the traffic jam information, infers the fuel consumption information as an output, and infers the fuel consumption using the inference.

(6) The driving support system according to (3),
The driving route information detecting means includes speed detecting means for detecting the speed of the vehicle, and detects the current speed of the detected vehicle as the driving route information.

(7) The driving support system according to (6),
A traffic information detection means for detecting traffic information on the road;
An input means for inputting, to the inference means, a travel route for which fuel consumption is to be obtained and a vehicle speed corresponding to the traffic jam information on the travel route as the travel route information;
The inference means infers the fuel consumption based on fuel consumption information inferred with respect to an input of the input means.

It is a block diagram which shows one Embodiment of the navigation apparatus incorporating the driving assistance system of this invention. It is an example of a fuzzified neural network used in learning / inference of this embodiment. It is a flowchart which shows the process sequence in the learning data creation process of CPU21a which comprises the navigation apparatus of FIG. It is a flowchart which shows the process sequence in the navigation process of CPU21a which comprises the navigation apparatus of FIG. It is a figure for demonstrating the inference of the fuel consumption amount which a vehicle consumes by operation until it returns to the establishment A via the delivery destinations P1 and P2 from the establishment A.

Explanation of symbols

21a CPU (inference means, oil amount notification means, gas station search means, gas station notification means, travel route information detection means, fuel consumption information detection means, learning means)
27 Fuel Fuel Gauge (Measuring Fuel Level)

Claims (4)

An inference means for inferring the amount of fuel consumed by the vehicle from the service station to the destination;
Fuel remaining amount measuring means for measuring the remaining amount of fuel;
A driving assistance system comprising: a refueling amount notifying unit for notifying a refueling amount at the filling station based on the inferred fuel consumption amount and the measured remaining fuel amount. The driving support system according to claim 1,
The inference means starts an inference using the departure point as the gas station in response to input of operation information including a departure point and a destination. A gas station search means for searching for a gas station on the route from the current position to the destination;
When a plurality of gas stations are searched, inference means for inferring fuel consumption from the current position to each gas station;
Fuel remaining amount measuring means for measuring the remaining amount of fuel;
A gas station notifying means for notifying a gas station where the maximum fuel consumption was inferred from the estimated plurality of fuel consumptions excluding the fuel consumption exceeding the measured fuel remaining amount was provided. A driving assistance system characterized by The driving support system according to any one of claims 1 to 3,
The inference means includes travel route information detection means for detecting travel route information relating to a travel route on which the vehicle is traveling, fuel consumption information detection means for detecting fuel consumption information of the vehicle, and the detected current travel route information. Learning means for outputting the detected current fuel consumption information as an output, and using the learning result performed by the learning means, the travel route information is input and the fuel consumption information is output. A driving support system characterized in that the fuel consumption is inferred using the inference.

Images