JP6961999B2 - Information processing device for vehicles - Google Patents

Description

The present invention relates to an information processing device, and more particularly to a vehicle information processing device mounted on a vehicle.

In recent years, it travels based on satellite navigation that acquires vehicle position information based on signals from navigation satellites and travels, and vehicle position information acquired based on the output values of various sensors mounted on the vehicle. Autonomous navigation and hybrid navigation that uses both are known. Patent Document 1 discloses a technique for using both a navigation satellite and autonomous navigation in combination.

JP-A-2009-41932

In hybrid navigation, when the strength of radio waves received from a navigation satellite is weak, for example, when a vehicle is traveling in a tunnel, the position of the vehicle is acquired by autonomous navigation. In order to realize autonomous navigation, there are vehicles equipped with devices that carry out autonomous navigation. Such a device realizes autonomous navigation based on output values of an angle sensor, an acceleration sensor, or the like. The output values of these sensors may vary depending on how they are mounted on the vehicle and individual differences. Therefore, for example, the position information obtained from the GPS (Global Positioning System) sensor is used as teacher data to learn the correction value for correcting the output value of the sensor.

The device responsible for autonomous navigation changes the output value of the sensor by referring to the change value which is the learning result stored in the non-volatile storage unit or the volatile temporary storage unit. Here, of course, there is no learning result in the initial learning stage before learning the changed value. Also, in the middle of learning, there are only incomplete learning results. Further, when the learning result is stored in the volatile temporary storage unit, the stored contents of the temporary storage unit may be reset due to, for example, a momentary interruption of the power supply of the vehicle or the occurrence of a negative surge. In addition, for example, when the size of the tire installed in the vehicle is changed, it is necessary to relearn the changed value of the sensor. In such a case, it becomes difficult for the vehicle to continue accurate autonomous navigation.

By the way, large long-distance transportation vehicles such as trucks often travel on motorways such as highways. For motorways, the design speed of the road is taken into consideration. Therefore, although it depends on the topographical conditions, the curvature and slope of the road tend to be gentler than those of general roads in urban areas. For example, when learning the angle sensor while traveling on a motorway, the swing width of the output value of the mounted angle sensor is small, which is not suitable for learning the output value. On the other hand, even if the learning value of the angle sensor is not correct, it does not matter much because the curvature of the road is small.

On the other hand, if the vehicle is traveling on a road other than a motorway, it tends to be an environment in which it is easy to learn the output values of various sensors including the angle sensor. In this way, when the learning results regarding the correction of various sensors are lost, it is required to change the response depending on the traveling condition of the vehicle including the road on which the vehicle is traveling.

Therefore, the present invention has been made in view of these points, and provides a coping technique when the learning result regarding the correction of the output value of the in-vehicle sensor is lost in a vehicle that performs autonomous navigation using the in-vehicle sensor. The purpose is.

One aspect of the present invention is a vehicle information processing device for mounting on a vehicle. This device reads the learning result of the corrected value for correcting the output value of the in-vehicle sensor from the non-volatile storage device and stores it in the temporary storage unit, and the learning result stored in the temporary storage unit. Based on the correction unit that corrects the output value of the vehicle-mounted sensor by reference, the map data read from the non-volatile storage device, and the output value of the vehicle-mounted sensor corrected by the correction unit, the vehicle travels in the map data. It includes a position calculation unit that calculates a position, and a navigation control unit that changes whether or not autonomous navigation is continued according to the type of road on which the vehicle is traveling when the learning result disappears from the temporary storage unit. ..

When the learning result disappears from the temporary storage unit, the navigation control unit stores the learning result in the learning result reading unit from the non-volatile storage device when the road on which the vehicle is traveling is an automobile-only road. The unit may be made to read the learning result again, and the autonomous navigation may be continued.

The vehicle information processing device has a satellite positioning unit that acquires position coordinates based on radio waves received from a navigation satellite, and position coordinates calculated from the output values of the in-vehicle sensor are the position coordinates acquired by the satellite positioning unit. As such, a learning unit for learning the correction value for correcting the output value of the angle sensor may be further provided, and the navigation control unit may provide the learning result when the learning result disappears from the temporary storage unit. When the road on which the vehicle is traveling is different from the motorized road, autonomous navigation may be stopped and the learning unit may be made to learn the correction value.

From the start of learning by the learning unit to the completion of the learning, the navigation control unit autonomously travels based on whether or not the road on which the vehicle is traveling is an automobile-only road. You may decide whether or not to continue.

In the navigation control unit, (1) the learning result regarding the angle sensor has disappeared from the temporary storage unit, (2) the road on which the vehicle is traveling is an automobile-only road, and (3) the learning unit. When the learning of the correction value is not completed and (4) the output value of the steering angle sensor for detecting the steering angle of the steering of the vehicle is available, the position is based on the output value of the steering angle sensor. The calculation unit may be made to calculate the traveling position of the vehicle, and the autonomous navigation may be continued.

According to the present invention, in a vehicle that performs autonomous navigation using an in-vehicle sensor, it is possible to provide a coping technique when a learning result regarding correction of an output value of an in-vehicle sensor is lost.

It is a schematic diagram for demonstrating the outline of the vehicle information processing apparatus which concerns on embodiment. It is a figure which shows typically the functional structure of the information processing apparatus for vehicle which concerns on embodiment. It is a flowchart for demonstrating the flow of the process executed by the vehicle information processing apparatus which concerns on embodiment. It is a figure which shows typically the functional structure of the information processing apparatus for vehicle which concerns on 1st modification of embodiment. It is a figure which shows typically the output value conversion graph which shows the relationship between the output value of an angle sensor, and the output value of a steering angle sensor.

<Outline of the embodiment>
An outline of the embodiment will be described with reference to FIG.
FIG. 1 is a schematic diagram for explaining an outline of the vehicle information processing apparatus 1 according to the embodiment. In the example shown in FIG. 1, the vehicle information processing device 1 is mounted on the vehicle V driven by the driver D. The vehicle V includes an in-vehicle sensor 2 and a GPS receiving unit 3 in addition to the vehicle information processing device 1. Hereinafter, the case where the in-vehicle sensor 2 is an angle sensor will be described as “angle sensor 2” as an example, but the in-vehicle sensor is not limited to the angle sensor, and if it is a sensor used for autonomous navigation, it may be another sensor such as an acceleration sensor. There may be.

The angle sensor 2 is realized by, for example, a known gyro sensor or the like, and outputs the inclination of the vehicle V. Although not shown in FIG. 1, the vehicle V also has an acceleration sensor. By integrating the output values of the angle sensor 2 and the acceleration sensor, the vehicle information processing device 1 can realize so-called autonomous navigation in which the locus of the vehicle V moving from the starting position is acquired.

The GPS receiving unit 3 receives radio waves transmitted by each of the plurality of navigation satellites. The vehicle information processing device 1 can also realize so-called satellite navigation in which the current position of the vehicle V equipped with the vehicle information processing device 1 is acquired by analyzing the radio waves received by the GPS receiving unit 3. can.

Here, for example, in a place where radio waves cannot be received from a navigation satellite such as inside a tunnel, the vehicle information processing device 1 cannot execute satellite navigation. On the other hand, since the autonomous navigation uses the output value of each sensor mounted on the vehicle V, the vehicle information processing device 1 basically has an advantage that the autonomous navigation can be executed at any time.

However, the output values of the angle sensor 2 and the acceleration sensor may vary depending on how they are attached and individual differences. Therefore, the vehicle information processing device 1 executes learning to obtain a correction value for correcting the output value of the angle sensor 2 or the acceleration sensor, using, for example, the position acquired by satellite navigation as teacher data. As a result, the vehicle information processing device 1 realizes highly accurate autonomous navigation. The learning process can be realized by using a known method such as optimization using the least squares method or machine learning such as a neutral network.

The vehicle information processing device 1 includes a calculation resource such as a CPU (Central Processing Unit) and a memory, and uses this calculation resource to correct the output value of the sensor. Specifically, the vehicle information processing device 1 stores the output value of the sensor and the learning result for correcting the output value in a temporary storage unit capable of reading and writing at high speed, and corrects the output value. In general, a volatile storage unit is characterized in that it can be configured with a large capacity at a low cost, so that the volatile storage unit is often selected as a storage site for the latest learning results. However, the temporary storage unit is a volatile memory, and the contents may be lost due to a momentary interruption of the power supply of the vehicle V or the occurrence of a negative surge.

Even if the learning result for correcting the output value of the sensor is lost, the vehicle information processing device 1 can continue autonomous navigation if it can be relearned immediately. For example, no matter what kind of road the vehicle V is traveling on, it is considered that the vehicle V frequently accelerates and decelerates. Therefore, re-learning of the output value of the accelerometer is often relatively easy.

On the other hand, when the vehicle V is traveling on a motorway, the frequency and amount of the vehicle V changing the direction of the vehicle body are higher than those when the vehicle V is traveling on other roads. few. This is because the motorway is premised on the vehicle V traveling at high speed, and the curvature in the curve is set small.

In addition, there are fewer intersections and the like on motorways than on roads that do not, and there are fewer opportunities for vehicle V to turn left or right. Therefore, when the vehicle V is traveling on the motorway, the fluctuation range of the output value of the angle sensor is small, and it is difficult to relearn, or even if it can be done, it takes time.

On the other hand, when the vehicle V is traveling on a motorway, the change in the direction of the vehicle body of the vehicle V is small, so that it is less necessary to correct the output value of the angle sensor 2 than when the vehicle V is traveling on a general road. I can say. That is, when the vehicle V is traveling on the motorway, the autonomous navigation can be continued even if the correction accuracy of the output value of the angle sensor is low.

Therefore, the vehicle information processing device 1 according to the embodiment responds to the type of road on which the vehicle V is traveling when the learning result of the correction value for correcting the output value of the angle sensor 2 disappears from the temporary storage unit. Change whether or not autonomous navigation is continued.

Specifically, when the road on which the vehicle V is traveling is an automobile-only road, the vehicle information processing device 1 rereads the past learning results stored in the non-volatile storage device into the temporary storage unit, and autonomous navigation is performed. To continue. When the vehicle V is traveling on a road different from the motorway, the vehicle information processing device 1 also stops autonomous navigation and learns a correction value for correcting the output value of the angle sensor. do.

As a result, the vehicle information processing apparatus 1 according to the embodiment can appropriately deal with the case where the learning result regarding the correction of the output value of the angle sensor 2 is lost.
Hereinafter, the vehicle information processing device 1 according to the embodiment will be described in more detail.

<Functional configuration of vehicle information processing device 1>
FIG. 2 is a diagram schematically showing a functional configuration of the vehicle information processing device 1 according to the embodiment. The vehicle information processing device 1 includes an angle sensor 2, a GPS receiving unit 3, a storage unit 10, and a control unit 20.

The storage unit 10 includes a non-volatile storage device 11 such as an HDD (Hard Disc Drive) or SSD (Solid State Drive), and a temporary storage unit 12 such as a DRAM (Dynamic Random Access Memory). The non-volatile storage device 11 functions as a storage unit for various data such as various programs for realizing the vehicle information processing device 1 according to the embodiment and learning results of correction values for correcting the output value of the sensor. do. The temporary storage unit 12 functions as a working memory of the control unit 20. The non-volatile storage device 11 is a non-volatile memory, and the temporary storage unit 12 is a volatile memory.

The control unit 20 is a processor such as an ECU (Electronic Control Unit) of the vehicle V. By executing the program stored in the non-volatile storage device 11, the control unit 20 executes a learning result reading unit 21, a correction unit 22, a position calculation unit 23, a navigation control unit 24, a satellite positioning unit 25, and a learning unit. Functions as 26.

The learning result reading unit 21 reads the learning result of the corrected value for correcting the output values of the angle sensor 2 and the acceleration sensor from the non-volatile storage device 11 and stores it in the temporary storage unit 12. The correction unit 22 corrects the output values of the angle sensor 2 and the acceleration sensor with reference to the learning result stored in the temporary storage unit 12.

The position calculation unit 23 calculates the traveling position of the vehicle V in the map data based on the map data read from the non-volatile storage device 11 and the output values of the angle sensor 2 and the acceleration sensor corrected by the correction unit 22. When the learning result disappears from the temporary storage unit 12, the navigation control unit 24 changes whether or not the position calculation unit 23 continues the autonomous navigation according to the type of the road on which the vehicle V is traveling.

More specifically, when the learning result disappears from the temporary storage unit 12, the navigation control unit 24 sends the learning result reading unit 21 to the learning result reading unit 21 when the road on which the vehicle V is traveling is an automobile-only road such as an expressway. The learning result is read again from the non-volatile storage device 11 to the temporary storage unit 12, and the autonomous navigation is continued.

The navigation control unit 24 can determine the type of road on which the vehicle V is traveling by collating the current position of the vehicle V with the map data read from the non-volatile storage device 11. When information such as ETC (Electronic Toll Collection) can be used, the navigation control unit 24 also determines whether or not the vehicle V has passed the entrance of the expressway and the exit of the highway. May determine whether or not the vehicle is traveling on the highway.

Here, when the vehicle V travels on a road suitable for learning the angle sensor 2 such as an urban area, a correction value for correcting the output value of the angle sensor is learned, and the learning result is updated. The updated learning result is stored in the temporary storage unit 12, but is stored in the non-volatile storage device 11 at a predetermined timing such as when the engine of the vehicle V is stopped.

Therefore, the learning result stored in the non-volatile storage device 11 may be different from the learning result stored in the temporary storage unit 12. Specifically, the learning result stored in the temporary storage unit 12 may reflect the latest learning than the learning result stored in the non-volatile storage device 11.

Therefore, the learning result that the navigation control unit 24 causes the learning result reading unit 21 to read again into the temporary storage unit 12 may be a past learning result that is not the latest learning result. When the vehicle V is traveling on a motorway, the conditions are not suitable for learning the angle sensor 2. Therefore, when the learning result disappears from the temporary storage unit 12, the past learning result is used as a second best measure. Use. As a result, the vehicle information processing device 1 can continue autonomous navigation.

On the other hand, when the learning result disappears from the temporary storage unit 12, if the road on which the vehicle V is traveling is different from the motorway, the navigation control unit 24 stops the autonomous navigation and the learning unit. Let 26 learn the correction value.

In order to realize this learning, the satellite positioning unit 25 acquires the position coordinates of the vehicle V based on the radio waves received by the GPS receiving unit 3 from the navigation satellite. The learning unit 26 learns a correction value for correcting the output value of the angle sensor 2 so that the position coordinates calculated from the output value of the angle sensor 2 become the position coordinates acquired by the satellite positioning unit 25.

When the road on which the vehicle V travels is not an automobile-only road, the vehicle V often makes a curve or turns left or right, and the output value of the angle sensor 2 has a wide variety of variations. Therefore, even if the learning result disappears from the temporary storage unit 12, the learning unit 26 can finish the re-learning in a short time as compared with the case where the vehicle V is traveling on the motorway. Therefore, when the road on which the vehicle V travels is not an automobile-only road, the navigation control unit 24 can restart autonomous navigation in a short time by having the learning unit 26 relearn.

On the other hand, even when the road on which the vehicle V is traveling is an automobile-only road, the learning unit 26 may be made to learn the correction value. In this case, the learning by the learning unit 26 may be slower than the learning in the case where the road is not a motorway, but the learning will still proceed with time. When the road on which the vehicle V is traveling is an automobile-only road, if the learning by the learning unit 26 progresses to some extent, the correction value in the middle of learning may be used even before the learning is completely completed. be. This is because when the vehicle V is traveling on the motorway, at least the correction while traveling on the motorway can be learned, and since the amount of the correction is small, autonomous navigation is possible.

As described above, the navigation control unit 24 is based on whether or not the road on which the vehicle V is traveling is an automobile-only road from the start of learning by the learning unit 26 to the completion of the learning. , Decide whether to continue autonomous navigation.

<Processing flow of information processing executed by the information processing device 1 for a vehicle>
FIG. 3 is a flowchart for explaining the flow of processing executed by the vehicle information processing apparatus 1 according to the embodiment. The process in this flowchart starts, for example, when the engine of the vehicle V starts.

The learning result reading unit 21 reads the learning result of the corrected value for correcting the output value of the sensor from the non-volatile storage device 11 and stores it in the temporary storage unit 12 (S2). When the learning result stored in the temporary storage unit 12 is not lost (No in S4), the correction unit 22 corrects the output value of the angle sensor 2 with reference to the learning result stored in the temporary storage unit 12. (S6). The position calculation unit 23 calculates the traveling position of the vehicle V in the map data based on the map data read from the non-volatile storage device 11 and the output value of the angle sensor 2 corrected by the correction unit 22 (S8).

When the learning result stored in the temporary storage unit 12 has disappeared (Yes in S4), the navigation control unit 24 determines the type of road on which the vehicle V is traveling. When the vehicle V is traveling on the motorway (Yes in S10), the navigation control unit 24 causes the learning result reading unit 21 to read the learning result again from the non-volatile storage device 11 to the temporary storage unit 12 (S12). ..

The correction unit 22 corrects the output value of the angle sensor 2 with reference to the learning result read out again by the temporary storage unit 12 (S6). The position calculation unit 23 calculates the traveling position of the vehicle V in the map data based on the map data read from the non-volatile storage device 11 and the output value of the angle sensor 2 corrected by the correction unit 22 (S8).

When the vehicle V is traveling on a road different from the motorway (No in S10), the GPS receiving unit 3 receives GPS data from the navigation satellite (S14). The satellite positioning unit 25 calculates a change in the position information of the vehicle V based on the GPS data of the vehicle V (S16). The learning unit 26 learns the correction value for correcting the output value of the angle sensor (S18).

<Effects of the vehicle information processing device 1 according to the embodiment>
As described above, according to the vehicle information processing device 1 according to the embodiment, in a vehicle that performs autonomous navigation using various sensors, learning results regarding correction of output values of each sensor, for example, an angle sensor In the vehicle V that performs autonomous navigation using No. 2, it is possible to provide a coping technique when the learning result regarding the correction of the output value of the angle sensor 2 is lost.

In particular, when the vehicle V is traveling on a motorway, it is difficult to relearn the correction value related to the output value of the angle sensor 2, so that the navigation control unit 24 is stored in the non-volatile storage device 11 in the past. The learning result is read by the learning result reading unit 21. As a result, the vehicle V can continue autonomous navigation.

Further, when the vehicle V is traveling on a road different from the motorway, it is relatively easy to relearn the correction value regarding the output value of the angle sensor 2, so that the navigation control unit 24 performs the autonomous navigation of the vehicle V. Is stopped, and the learning unit 26 is made to learn the correction value related to the sensor output value. As a result, the vehicle V can resume autonomous navigation in a relatively short time.

As described above, according to the vehicle information processing device 1 according to the embodiment, even if the vehicle V unintentionally loses the learning result while traveling on an automobile-only road such as an expressway, it is autonomous with some accuracy. Can navigate. Further, when the learning result is lost while the vehicle V is traveling in an urban area or the like, it is possible to suppress the hindrance to the traveling of the vehicle V due to the error generated by using the autonomous navigation.

Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various changes or improvements can be made to the above embodiments. It is clear from the description of the claims that such modified or improved forms may also be included in the technical scope of the present invention. An example of such a modification will be described below.

<First modification>
FIG. 4 is a diagram schematically showing a functional configuration of the vehicle information processing apparatus 1 according to the first modification of the embodiment. Compared with the vehicle information processing device 1 according to the above-described embodiment, the vehicle information processing device 1 according to the first modification includes a steering angle sensor 4, and the position calculation unit 23 is a steering angle sensor 4. The difference is that you can see the output.
Hereinafter, the vehicle information processing device 1 according to the first modification of the embodiment will be described, but the parts common to the vehicle information processing device 1 according to the embodiment will be appropriately omitted or simplified.

The navigation control unit 24 continues autonomous navigation when the vehicle V satisfies the following four conditions. That is,
(Condition 1) The learning result has disappeared from the temporary storage unit 12.
(Condition 2) The road on which vehicle V is traveling is a motorway.
(Condition 3) Learning of the correction value by the learning unit 26 is incomplete.
(Condition 4) The output value of the steering angle sensor 4 that detects the steering angle of the steering of the vehicle V is available.
There are four conditions.

When these four conditions are satisfied, the navigation control unit 24 causes the position calculation unit 23 to calculate the traveling position of the vehicle V based on the output value of the steering angle sensor 4, and continues the autonomous navigation. Hereinafter, the condition 4 will be described in more detail.

The vehicle V changes its direction when the driver D operates the steering. Further, the larger the steering operation amount, the larger the change in the direction of the vehicle V. That is, it is considered that there is a correlation between the steering operation amount of the vehicle V (that is, the output value of the steering angle sensor 4) and the change in the direction of the vehicle V (that is, the output value of the angle sensor 2). Therefore, for example, if the non-volatile storage device 11 stores information indicating the correspondence between the output value of the steering angle sensor 4 and the output value of the angle sensor 2 in advance, the output value of the angle sensor 2 can be stored in the steering angle sensor 4. Can be replaced by the output value of.

FIG. 5 is a diagram schematically showing an output value conversion graph showing the relationship between the output value of the angle sensor 2 and the output value of the steering angle sensor 4. The output value conversion graph shown in FIG. 5 is stored in the non-volatile storage device 11 and is referred to by the position calculation unit 23. The output value conversion graph is measured before shipment of the vehicle V and stored in the non-volatile storage device 11, for example, by the manufacturer of the vehicle V.

As shown in FIG. 5, since the output value of the steering angle sensor 4 and the output value of the angle sensor 2 have a positive correlation, the position calculation unit 23 can refer to the output value conversion graph to obtain the steering angle sensor 4. The output value can be converted into the output value of the angle sensor 2. The position calculation unit 23 can calculate the position information of the vehicle V by using the converted value. As a result, even if the learning result is lost from the temporary storage unit 12, the road on which the vehicle V is traveling is an automobile-only road, and the learning of the correction value by the learning unit 26 is not completed, the vehicle V is Autonomous navigation can be continued.

<Second modification>
In the above, the learning unit 26 has mainly described the case where the learning unit 26 learns the correction amount of the output value of the angle sensor 2 using the position information calculated by the satellite positioning unit 25 as the teacher data. Here, the information used by the learning unit 26 as teacher data may be information other than GPS information. For example, when the learning unit 26 associates the road curvature information with the map data stored in the non-volatile storage device 11, the learning unit 26 uses the inclination of the vehicle predicted from the information as the training data of the angle sensor 2. You may learn the correction amount of the output value.

1 ... Vehicle information processing device 2 ... Angle sensor 3 ... GPS receiving unit 4 ... Steering angle sensor 10 ... Storage unit 11 ... Non-volatile storage device 12 ... Temporary storage unit 20 ... Control unit 21 ... Learning result reading unit 22 ... Correction unit 23 ... Position calculation unit 24 ... Navigation control unit 25 ... Satellite positioning unit 26 ... Learning unit V ... ·vehicle

Claims (5)

It is a vehicle information treatment device for mounting on a vehicle.
A learning result reading unit that reads the learning result of the correction value for correcting the output value of the angle sensor that outputs the inclination of the vehicle from the non-volatile storage device and stores it in the temporary storage unit.
A correction unit that corrects the output value of the angle sensor by referring to the learning result stored in the temporary storage unit, and a correction unit.
A position calculation unit that calculates the traveling position of the vehicle in the map data based on the map data read from the non-volatile storage device and the output value of the angle sensor corrected by the correction unit.
When the learning result disappears from the temporary storage unit, a navigation control unit that changes whether or not autonomous navigation is continued according to the type of road on which the vehicle is traveling, and a navigation control unit.
Information processing device for vehicles equipped with. When the learning result disappears from the temporary storage unit, the navigation control unit stores the learning result in the learning result reading unit from the non-volatile storage device when the road on which the vehicle is traveling is an automobile-only road. Have the department read the learning result again and continue the autonomous navigation.
The vehicle information processing device according to claim 1. A satellite positioning unit that acquires position coordinates based on radio waves received from navigation satellites,
A learning unit for learning a correction value for correcting the output value of the angle sensor is further provided so that the position coordinates calculated from the output value of the angle sensor become the position coordinates acquired by the satellite positioning unit.
When the learning result disappears from the temporary storage unit, the navigation control unit stops the autonomous navigation and informs the learning unit when the road on which the vehicle is traveling is different from the motorway. To learn the correction value,
The vehicle information processing device according to claim 1 or 2. From the start of learning by the learning unit to the completion of the learning, the navigation control unit performs the autonomous navigation based on whether or not the road on which the vehicle is traveling is an automobile-only road. Decide whether to continue,
The vehicle information processing device according to claim 3. In the navigation control unit, (1) the learning result regarding the angle sensor that outputs the inclination of the vehicle has disappeared from the temporary storage unit, and (2) the road on which the vehicle is traveling is an automobile-only road. (3) When the learning of the correction value by the learning unit is not completed and (4) the output value of the steering angle sensor for detecting the steering angle of the steering of the vehicle is available, the steering angle sensor of the steering angle sensor Let the position calculation unit calculate the traveling position of the vehicle based on the output value, and continue the autonomous navigation.
The vehicle information processing device according to claim 3 or 4.

Images