JP2010257234A - Information exhibition device for vehicle - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To intuitively recognize whether a risk in a periphery is got properly or not, even under the state where a driver is concentrated in drive. <P>SOLUTION: This information exhibition device for a vehicle investigates a risk difference ΔRD between a risk level got by the driver and a risk level recognized by a system, based on an output from the recognition system, and changes vertical and lateral sizes of a pattern displayed on a display, in response to the risk difference ΔRD, to be expanded vertically and laterally around the gravity center of the pattern as the center. Respective RGB components for displaying the pattern are changed at the same time. Confirmation is thereby facilitated in a peripheral view by the driver, without moving a sight line, a burden for the driver is reduced therein, and the driver gets intuitively a deviation between an own risk recognition state and a risk recognition state of the system, under the state where the driver is concentrated in the drive. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to a vehicular information presentation device that estimates the risk of an accident occurring while driving a vehicle and displays the risk information.

  In vehicles such as automobiles, in order to support safe driving, there is a demand for a device that estimates the risk of an accident occurring in the driving environment and presents the risk information to the driver. For this reason, conventionally, various proposals have been made regarding techniques for presenting risk level information to the driver.

  For example, Patent Literature 1 discloses a technique for presenting information to a driver by detecting a danger such as an obstacle and displaying it on a head-up display. Patent Document 2 discloses a technique for grasping a surrounding danger level by wireless communication and presenting a danger direction by a line light source around the windshield.

Japanese Patent Laid-Open No. 11-245683 JP 2005-242526 A

  As disclosed in Patent Document 1 and Patent Document 2, conventional techniques for presenting risk information specifically present the positions of other vehicles, obstacles, etc. on the display, or in the vehicle front image. Presented by drawing in layers. However, reading the contents displayed on the display in detail is an act of applying a load, which may hinder driving.

  In addition, the techniques disclosed in Patent Documents 1 and 2 are both techniques that inform the driver of the existence and direction of specific dangers, and do not present the degree of danger lurking in the driving environment to the driver. It does not consider whether the driver properly knows the surrounding risk level.

  The present invention has been made in view of the above circumstances, and provides a vehicle information presentation apparatus that can intuitively recognize whether or not the driver can properly grasp the surrounding danger even when the driver concentrates on driving. It is intended to provide.

  In order to achieve the above object, an information presentation device for a vehicle according to the present invention includes a risk estimation unit that estimates the risk of occurrence of an accident while driving a vehicle, and an occupant according to the risk estimated by the risk estimation unit. And a display control unit that changes a display size and a display color of the risk level information presented in FIG.

  According to the present invention, it is possible to intuitively recognize whether or not the driver can properly grasp the surrounding danger even when the driver concentrates on driving.

System configuration diagram of information presentation device Explanatory drawing which shows the learning phase and estimation phase of a recognition system Explanatory diagram showing the network of operation features and self-organizing maps Explanatory diagram showing stochastic state transition Graph showing state transition probability after learning Graph showing output probability after learning Explanatory diagram showing algorithm for state estimation Explanatory drawing showing the probability distribution when the reliability of estimation is high Explanatory drawing showing the probability distribution when the reliability of estimation is low Explanatory diagram showing the difference in reliability depending on the winner unit distance Illustration of total unit distance ratio Graph showing calculation example of reliability index Explanatory diagram showing estimation test results Explanatory diagram showing a display screen example when the risk difference is small Explanatory drawing showing an example of the display screen when the risk difference is slightly small Explanatory drawing showing an example of the display screen when the risk difference is slightly large Explanatory diagram showing a display screen example when the risk difference is large Explanatory diagram showing the relationship between the size of drawn figures and the risk difference Explanatory diagram showing the relationship between the color of drawn figures and the risk difference Explanatory diagram showing the relationship between the reliability of estimation and the blur width of the figure

Embodiments of the present invention will be described below with reference to the drawings.
As shown in FIG. 1, an information presentation device 1 mounted on a vehicle such as an automobile includes a recognition system 1 a as a risk estimation unit that estimates the risk of occurrence of an accident during driving of the vehicle, and a recognition system 1 a Based on the output, the display control unit 1b that controls the display content of the risk information and the display device 1c that displays the risk information from the display control unit 1b and presents it to the occupant are configured. The display device 1c is a color display having a predetermined resolution. In the present embodiment, the display device 1c is installed at a position where it can be visually recognized in the peripheral visual field of the driver.

  The recognition system 1a is composed of a single on-board computer system or a plurality of computer systems connected via a network or the like. Specifically, the recognition system 1a includes an external environment recognition unit 2 for recognizing a risk (running environment risk) included in the external environment around the vehicle from external information obtained by a sensing device such as a camera or a radar, and driving operation data of the driver. Operation feature quantization unit 3 that quantizes the feature, model learning unit 4 that learns the correspondence between driving operation (operation feature) and recognition environment (risk level), learned model and current operation data A state estimation unit 5 that estimates the internal state of the driver from the relevance to the environment outside the vehicle, estimates the risk recognized by the driver, and a reliability evaluation that evaluates the reliability of the internal state estimation of the driver A portion 6 is provided. In the following, an in-vehicle camera is used as a sensing device for the external environment. As will be described later, the reliability evaluation unit 6 may be configured as part of the operation feature quantization unit 3 or the state estimation unit 5.

  For such a recognition system 1a, the display control unit 1b includes a risk recognized by the vehicle exterior environment recognition unit 2 (corresponding to a travel environment risk level estimation unit that estimates the risk level of the travel environment of the vehicle), and state estimation. Display content (risk level information) to be displayed on the display device 1c according to the difference from the driver's grasping risk estimated by the unit 5 (corresponding to the grasping risk degree estimating unit for estimating the risk grasped by the driver) By changing the display size and the display color, it is possible to intuitively recognize whether or not the driver can properly grasp the surrounding danger.

  First, the system operation of the recognition system 1a will be described. For convenience, the system operation of the recognition system 1a includes, as shown in FIG. 2, a “learning phase” for learning a model of the internal state of the driver and an “estimation phase” for estimating the internal state of the driver based on the obtained model. And divided.

  In the learning phase, when the vehicle front is imaged with an in-vehicle camera, and the risk level of the driving environment is recognized by learning, the correspondence between the driving environment risk level and the operation feature data obtained by quantizing the feature data of the driver's driving operation data Learn relationships, get learned parameters and build learning models.

  In the estimation phase, the relationship between the operation feature amount and the travel environment risk level is acquired using the learned model parameters, and the current internal state of the driver is estimated. The estimated current internal state of the driver is compared with the current driving environment risk level to assess whether the vehicle is inherently safe or dangerous.

  The learning phase and the estimation phase do not actually proceed separately from each other, but both proceed simultaneously. As a result, it is possible to realize a function that can adapt to changes in the environment in which the driver is driving and changes in the characteristics of the driver itself, and to provide a system that increases the performance as the vehicle travels. Can do. In addition, the model parameters in the learning phase can all be acquired by online learning while driving. However, it is recognized that the learning speed can be improved by using offline learning in part with a simulator. An improvement in accuracy can be expected.

  Next, the function of each part of the recognition system 1a will be described. The exterior environment recognition unit 2 degenerates the state of the exterior environment into a single scalar value (or vector) by learning the relationship between the feature quantity of the image obtained from the in-vehicle camera and the risk level at that time. And transmitted to the model learning unit 4.

  For the recognition of the risk level from the image feature amount, for example, the technology of the online risk learning system proposed in Japanese Patent Application No. 2007-77625 by the present applicant can be adopted. As described in detail in Japanese Patent Application No. 2007-77625, this technique is based on an image feature amount (edge information, motion information, color information, etc.) of an N-dimensional vector depending on an event such as a sudden accelerator return operation or a brake depression. Is converted into a one-dimensional state, and the risk contained in the environment is learned and recognized from the correlation between this state and the teacher information created from the vehicle information (driver operation information).

  In the present embodiment, an example using the risk level extracted from the image feature amount will be described. However, the risk level is not limited to this, and for example, the risk level is extracted from the inter-vehicle distance or the like. Anyway.

  The operation feature quantity quantization unit 3 quantizes the data from the sensor or the operation data of the driver such as the accelerator, the brake, the steering, etc. acquired via the in-vehicle network (not shown) according to the feature of the measurement frequency, This is transmitted to the model learning unit 4. In other words, the driving operation data has a very large amount of information as it is, and it is difficult to handle the relationship with the risk. For this reason, statistical processing to learn features while preventing loss of information contained in the data by appropriately quantizing in consideration of the distribution (appearance tendency) of the observed data Is possible.

  Quantization of observation data can be performed by data division or data degeneration using thresholds. In this embodiment, driving operation data is quantized using a self-organizing map (SOM). . SOM is a type of neural network that models the visual cortex of the cerebral cortex of living organisms. Each unit arranged in M dimensions has a vector value (usually called the weight of the connection with the input). The winner unit is determined based on the vector distance.

  Then, the reference vector values of the winner unit and the surrounding units are updated so as to approach the input vector. By repeating this, competitive learning is performed so that the entire distribution of the input data can be expressed optimally, the dimensions of the input information are compressed based on this competitive learning, and clustering and visualization are performed according to the characteristics of the data Can do.

  In this embodiment, an example in which input data is degenerated by unsupervised competitive learning using S0M will be described. However, a vector quantization (LVQ; Learning Vector Quantization) model that is supervised competitive learning can also be used. It is.

  Examples of SOM parameters are shown below. The feature values adopted are the steering angular speed, accelerator opening, brake pressure, accelerator opening change, brake pressure change, and vehicle speed. However, the absolute value is used for the rudder angular velocity, and the accelerator opening and the brake pressure are normalized to be dimensionless amounts from -100 (brake pressure maximum) to +100 (accelerator fully open). The change amount of the accelerator and the brake is also expressed as the change amount of the normalized value. As a result, the dimension of the input feature quantity is 4, which is compressed to one dimension by SOM and quantized to 256 units.

[SOM parameters]
Number of SOM dimensions 1
256 units
Input feature value ADSTR (steering angular velocity absolute value)
PEDAL (accelerator / brake operation normalized amount)
DPEDAL (PEDAL value change amount)
SPEED (vehicle speed)

  FIG. 3 shows data learned by SOM (however, only three of the four input dimensions), and data obtained by traveling in an urban area (corresponding to 5-hour driving) is learned by SOM. The measurement data is plotted like a cloud, and the one-dimensional SOM network is arranged in a string shape. It can be seen from FIG. 3 that learning is performed according to the density and distribution of measurement data, and that units are appropriately arranged. The measured data is quantized and reduced to one-dimensional data represented by a unit number by being approximated by the nearest SOM unit.

  The unit arrangement of the SOM is determined by learning measured driving data, and it can be expected that the same person will adapt to changes in driving characteristics due to time variations even for the same person.

  The model learning unit 4 acquires the relationship between the operation feature quantity and the risk level by learning, and enables probabilistic calculation for estimating the internal state of the driver. As shown in FIG. 4A, human behavior changes according to mental states such as security, tension, anxiety, impatience, and anger, and transitions thereof, and is not necessarily deterministic but expressed as probabilistic behavior. can do. Similarly, as shown in FIG. 4 (b), the driver's driving behavior includes a stochastic operation output for scenes such as following a preceding vehicle, passing, parking, lane change, and merging. It appears.

  Therefore, the model learning unit 4 models the internal state of the driver using a hidden Markov model (HMM), which is a kind of probabilistic state transition model, as a reference model for expressing the probabilistic behavior of human behavior. Turn into. The HMM is a model that assumes that a target internal state (state) transitions by a probabilistic conditional branch and that a signal is output to the outside with a different probability depending on the transitioned state.

  In the model using the HMM, in the task of estimating the risk level that the driver is aware of, the risk level that is currently conscious corresponds to the state of the HMM, as shown in FIG. Observed driving operation data corresponds to a signal output to the outside. FIG. 4C illustrates an example in which the risk levels are set to 5 levels and numbers 1 to 5 are assigned to the respective states. The number 1 recognizes that the risk of the external environment is the lowest. The state, number 5, indicates a state where the driver recognizes that the risk of the external environment is the highest.

  In this way, the driving operation data is discretized, the appearance tendency of the data is obtained, and the internal state of the driver is approximated as a probabilistic model, so that it is deterministically derived from the external environment like the operation data in actual driving. It is possible to appropriately handle information that cannot be handled. However, in order to estimate from which state the operation data observed at the time of estimation is output, it is necessary to perform two probability calculations: a state transition probability and an operation output probability.

  For this reason, the model learning unit 4 first learns the state transition probability by a statistical method based on the scalar value transmitted from the vehicle exterior environment recognition unit 2, and then uses the data from the operation feature quantization unit 3. Based on this, the observation probability distribution (operation output probability) of the operation feature amount for each state is learned. For example, the steering angle, the accelerator opening, the brake pressure, and the speed, yaw rate, acceleration, and the like that reflect the operation are discretized as appropriate, and the number of observations for each discrete value is counted to statistically calculate the probability.

  Hereinafter, calculation processing of the state transition probability and the operation output probability using the HMM will be described.

[Specification example of HMM]
Drive frequency 3Hz
Number of states 10
Output signal SOM unit number (0 to 255)
Network structure All-state interconnection type

[Calculation of state transition probability]
In general, when driving a car, it is unlikely that there will be a driver who always causes an accident even though it is unintentional every time the car is driven. In other words, it can be regarded macroscopically that the driver is appropriately performing a driving operation corresponding to the risk level of the driving environment. Based on these assumptions, when data is collected and statistically processed over a relatively long time range, it is assumed that the transition of the internal state of the driver in the HMM depends on the transition of the risk level of the driving environment. Can do.

Therefore, the transition probability is calculated according to the following procedures (1-1) to (1-5), and the transition probability of the driver internal state is calculated by obtaining the transition probability of the risk level at the time of learning.
(1-1) Define the drive frequency of the state transition model (for example, 3 Hz)
(1-2) Define the number of internal states (for example, 10 states)
(1-3) Discrete the risk level by the number of states (1-4) Count the number of transitions between each state (1-5) Calculate the statistical transition probability between each state

  In a simple example, if the time step of the state transition is fixed to a constant value and the internal state of the driver transitions in synchronization with the transition of the environmental state, the calculation becomes simple. Alternatively, it is possible to define a state separately according to the length of time for stopping in a specific scalar value range.

  FIG. 5 shows a graph of the state transition probability of the HMM obtained by learning from the measurement data in the urban area. The larger the state number, the higher the risk level. From this graph, in the framework of the HMM drive frequency of 3 Hz, the self-transition (transition staying in the same numbered state), the transition probability for one state above and below is large, and the transition probability that the risk level suddenly decreases in the high risk state It can be seen that it is relatively large. This is generally equivalent to the fact that moderate and moderate risks rise and fall continuously, and high risk factors disappear rapidly with the passing of the vehicle. It can be judged that there is nothing.

[Calculation of output signal probability]
The SOM described above is used for learning the output probability of the operation data feature in the state transitioned to a certain state. The measured operation data is dimensionally compressed and quantized into SOM unit numbers, and the statistical output signal probability is calculated by counting the number of times each unit number is observed. Since the output probability of each unit obtained for each state is different, it can be modeled that the operation tendency changes depending on the risk level, and the output probability for each state as shown in FIG. 6 can be obtained.

  When the above state transition probability and output probability are acquired by learning, the state estimation unit 5 next estimates the internal state of the driver using both pieces of information. The internal state is estimated using a forward algorithm that forwards the trellis between the event and each state in consideration of online application.

  Specifically, the forward probability (state existence probability) α is calculated by performing sequential calculation according to the following steps (2-1) and (2-2). In the following equations, π: prior probability, a: state transition probability, b: output signal probability, o: measured operation data, and subscript 1 of each variable indicates an initial value.

(2-1) The forward probability is initialized for each state i = 1,.
α ₁ (i) = π ₁ b ₁ (o ₁ )
(2-2) For each time t = 1,..., T−1 and each state j = 1,. Note that Σ in the recursive calculation is the sum for j = 1 to N.
α _{t + 1} (j) = [Σα _t (i) a _ij ] b _j (o _{t + 1} )

  In the state estimation by this forward algorithm, as shown in FIG. 7, all transition probabilities are calculated at each step of time t = 0, 1, 2, 3, 4,. Therefore, the internal state can be estimated with high definition. In the first step of probability calculation, the prior probability obtained from the state transition probability of the HMM is used as the existence probability in each state.

From the state existence probability α for each state obtained by the sequential calculation, an expected value μ is calculated as shown below. The expected value μ is output as a driver internal state in which the state number is precisely expressed by a continuous numerical value instead of a discrete value, and becomes a risk level that the driver is aware of. Note that x is the value of the random variable (here, the state number), and Σ is the sum of i = 1 to N.
μ = Σx _i α _i

  In addition, the internal state of the driver estimated by the state estimation unit 5 is evaluated by the reliability evaluation unit 6, and uncertain estimation output is suppressed. As shown in the following (3-1) and (3-2), this reliability is evaluated by a method of evaluating in consideration of the probability distribution shape between states, and an error in quantizing the operation feature amount. The estimation reliability of the driver internal state is evaluated using both or any one of these evaluation methods.

  The reliability evaluation unit 6 may be a part of the state estimation unit 5 and the operation feature quantity quantization unit 3. The state estimation unit 5 performs reliability evaluation based on the probability distribution shape between states, and operates characteristics. The quantity quantization unit 3 may evaluate the reliability based on the quantization error of the operation feature quantity.

(3-1) Reliability Evaluation from Probability Distribution Shape When the estimation is performed normally, as shown in FIG. 8, there is a high probability distribution peak near the expected value, and the other probabilities are low. Ideally. In this state, it can be said that the estimation is performed with certainty. On the other hand, as a typical example of when the certainty of estimation is lowered, there is an example as shown in FIG. That is, there is a case where no clear peak exists in the probability distribution as shown in FIG. 9A, or a plurality of peaks exist in the probability distribution as shown in FIG. 9B.

  Therefore, by expressing the difference in the shape of the probability distribution numerically, not only the estimation result of the driver internal state but also the reliability of the estimation result can be output. As an index for evaluating the reliability by quantifying the shape of the probability distribution, as shown in the following (a), (b), and (c), the state having entropy, variance, and the maximum existence probability and the adjacent state The total probability or the like can be used, and the reliability is evaluated using all or at least one of these indices.

(A) Entropy The entropy H of the probability distribution is calculated by the following formula, and the reliability is evaluated. Entropy is maximized when the probability distribution is uniform, and it can be evaluated that the smaller the entropy, the higher the reliability.
H = Σp _i logp _i
Where p _{i is the} probability of existence of state i
N: Number of states
Σ: Sum of i = 1 to N

(B) Variance The variance V of the probability distribution is calculated by the following formula, and the reliability is evaluated. The variance is minimized when the probability of the state having the maximum existence probability is 1. Therefore, it can be evaluated that the smaller the variance, the higher the reliability.
V = Σ (x _i −μ) ² p _i
Where p _{i is the} probability of existence of state i
N: Number of states
x _i : Risk level value of state i
Σ: Sum of i = 1 to N

(C) Total Probability of State with Maximum Existence Probability and Adjacent State The total probability Psum of the state with the maximum existence probability and the adjacent state is calculated by the following formula, and the reliability is evaluated. The total probability Psum is 1 when the state having the maximum existence probability has the probability 1 or the adjacent state has all the remaining existence probabilities. Therefore, it can be evaluated that the larger the value, the sharper the probability distribution, and the higher the reliability.
Psum = Σp _i
However, Σ: i = K−1 to K + 1
K: State number with maximum existence probability

(3-2) Reliability Evaluation Based on Operation Feature Quantity Quantization Error As described above, the operation feature quantity quantization unit 3 learns the distribution of input operation data using the SOM, and changes the distribution shape into the distribution shape. By arranging the units along the line, the data is compressed and quantized, and it plays a role of compressing various combinations of driving operations to a level that is easy to handle in estimating the internal state. The quantization by the SOM is performed by representing the operation data with the SOM unit closest to the observed operation data input. At this time, the representative unit is the “winner unit”.

  Therefore, the distance in the feature amount space between the winner unit and the input operation data is defined as “winner unit distance”, and this winner unit distance is one of the indexes for evaluating the reliability of the estimation result in the state estimation unit 5. Used as The winner unit distance corresponds to a quantization error when the input data is quantized, and the error is small when the distance is small, and the error is large when the distance is large. When an output having a large error is input to the state estimation unit 5 in the subsequent stage, it can be said that the reliability of the estimation result is inevitably lower than that of an input having a small error. Therefore, this winner unit distance can be used as one of the reliability evaluation indexes.

  For example, when the same unit is a winner but the winner unit distance is different, as shown in FIG. 10A, when the distance d from the input data to the winner unit is small, the approximation / compression during learning is performed. It is performed well and the quantization error is small. On the other hand, as shown in FIG. 10B, when the distance d from the input data to the winner unit is large, data different from the distribution of the operation data at the time of learning is input, and the quantization error is large. I mean. Therefore, it can be considered that the reliability of the driver internal state estimation in such a state is low.

In addition to using the “winner unit distance” as a reliability evaluation index, the total of the “ratio of the distance between the winner unit distance and other units” can also be used as the reliability evaluation index. Therefore, as shown in FIG. 11, the distance from the input data to the winner unit is dw, the distance to the other units is di, and the index S is defined by the sum of the unit distance ratio di / dw as follows: To do.
S = Σ (di / dw)
However, Σ: Sum of i = 1 to N−1
N: Total number of units

  As shown in FIG. 11A, when there is a unit that appropriately quantizes the input in the feature amount space, the index S takes a large value, and as shown in FIG. When an input is observed in a distant space, the index S has a small value. Therefore, it can be considered that the reliability is high when the value of the index S is large, and the reliability is low when the value of the index S is small.

  Compared with the method using the winner unit distance directly, the method using the index S considers the arrangement in the feature amount space of the entire SOM unit. Even when the distance is small, the distance to many units is almost the same, and the case where the quantization is unstable can be detected. That is, it is possible to calculate the reliability of the estimation result in the state estimation unit 5 in the subsequent stage from the viewpoint of the stability evaluation of quantization.

  FIG. 12 shows a calculation example of the reliability index for the state estimation. In FIG. 12, together with the risk level of the external environment and the driver recognition risk level estimated to be recognized by the driver, the SOM winner unit distance is shown as an estimated reliability index, and the SOM winner unit distance is When the reliability is relatively small, the adjacent state total probability is large. Conversely, when the SOM winner unit distance is large and the reliability is relatively low, the adjacent state total probability is small.

[Output of the driver's conscious risk level]
The expected value calculated from the existence probability in each state as the internal state of the driver by the state estimation unit 5 is filtered by a first-order low-pass filter (for example, a cut-off frequency of 0.3 Hz) and then displayed from the state estimation unit 5. Is output to the unit 1b. This output value corresponds to the risk level that the driver is aware of and can be regarded as the risk level that the driver deals with. By comparing the output value with the driving environment risk level value, the vehicle is essentially It is possible to evaluate whether it is safe or dangerous.

  That is, as a result of comparison in the display control unit 1b, if the state estimated by the state estimation unit 5 is the same as the state to which the scalar value currently obtained from the vehicle exterior environment recognition unit 2 belongs, the driver recognizes the environment normally. It is determined that a normal operation is performed. On the other hand, when the state estimated by the state estimation unit 5 is different from the state to which the scalar value currently obtained from the vehicle environment recognition unit 2 belongs, it is determined that the driver state is inconsistent with the level required by the environment. Is done.

  For example, if the risk level of the estimated state is lower than the risk level obtained from the outside environment recognition unit 2, it is determined that the driver's risk recognition level is low and the safety is likely to be impaired, The display output from the display control unit 1b is changed so that the driver can reliably recognize the risk. Conversely, when the estimated risk level of the state is higher than the risk level obtained from the outside environment recognition unit 2, it is estimated that the driver is excessively tensioned, and the safety may be similarly impaired. The display output from the display control unit 1b is adjusted because of high performance.

  FIG. 13 shows a part of data measured in the state estimation running test. From S1 street (one side lane) to the S2 street (one lane) through the narrow path (no center line) indicated by the symbols A, B, C, and further from the position indicated by symbol D, S3 street ( Changes in the environmental risk level and the internal state risk level when traveling up to one lane on one side are shown together with changes in the operation feature amount.

  In the test results shown in FIG. 13, the driver is driving with a normal arousal level and a sense of tension based on the relationship between the operation feature amount and the risk level, and corresponds to a high risk level situation such as an intersection or a narrow road. Can be confirmed from the estimated internal state, that is, the risk level perceived by the driver is high. In particular, the points A, B, C, and D shown in the graph are characteristic high-risk events, mainly intersections and narrow streets. When the other risk level is high, it is mainly a portion where a pedestrian, a bicycle, an oncoming vehicle, or the like is encountered, and it can be seen that the same estimation result is obtained also in this portion.

  Based on such an estimation result, the display control unit 1b changes display content to be output to the display device 1c, and presents to the driver whether or not the driver can properly grasp the surrounding danger level. As the display device 1c, a display of a navigation device, a display installed in an instrument panel, a head-up display, or the like can be used. There is no hindrance to information transmission due to noise or the like, and a driver and a passenger for information presentation There is no risk of forcibly interrupting the conversation. In the present embodiment, as the display content displayed on the display device 1c, a relatively simple figure is mainly used. Based on the risk difference between the risk recognized by the system and the risk recognized by the driver. The size of the figure to be displayed (display size) and the display color are changed simultaneously.

  When the risk difference between the risk recognized by the system and the risk grasped by the driver is large, that is, when it is estimated that an accident is likely to occur, the display control unit 1b seems to increase the size of the figure. When the risk difference is small, that is, when it is estimated that an accident is unlikely to occur, the figure size is changed to be small. At the same time, when the risk difference is large, the figure color is also displayed in warning colors such as red, orange, and yellow, and when the risk difference is small, it is gradually changed in colors that are not warning colors such as blue and green. Let

  In this case, the size of the graphic is changed so that the driver can recognize the change in the degree of danger in the peripheral vision. Also, the reason for changing the color of the graphic is to make it possible to intuitively understand the degree of danger without performing complicated recognition of characters and shapes.

  That is, human peripheral vision is different from central vision in that it deals with size and movement instead of color and shape. Therefore, by changing the size of the figure using the effect of perspective and changing the display color of the figure, the driver notices the change in the risk level without moving the line of sight and using central vision. Will be able to.

  In other words, the larger the displayed figure, the closer the danger, that is, the risk that the driver knows is far from the risk that the system recognizes, and the driver is more likely to have an accident. Is easy to understand intuitively. In addition, the smaller the figure, the easier it is for the driver to intuitively understand that a faraway danger, that is, the risk grasped by the driver is smaller and safer than the risk recognized by the system.

  Specifically, risk information as shown in FIGS. 14 to 17 is displayed on the display device 1c, for example. For example, when the display of the navigation device is used as the display device 1c, the risk information is displayed on a child screen provided in a part of the parent screen that displays map information and the like. In this display screen example, a device name or the like is displayed in a region T at the top of the screen, and a quadrangular figure Z whose size and display color changes is arranged in the center of the screen. In the lower part of the screen, a risk level Rsys recognized by the system and a risk level (risk level estimated from the internal state of the driver) Rdriver recognized by the driver are displayed side by side.

  The risk level Rsys recognized by the system and the risk level Rdriver recognized by the driver are each expressed by a numerical value from 0 to 100. The larger the numerical value, the higher the possibility of an accident. It is shown that.

  The size of the figure to be drawn and the display color are changed with reference to the maps of the characteristics shown in FIGS. FIG. 18 shows the value of the risk difference ΔRD (ΔRD = Rdriver−Rsys) between the risk level Rdriver recognized by the driver and the risk level Rsys recognized by the system, and the vertical and horizontal sizes of the figure. The vertical axis shows the relative ratio when the largest value is 100%. According to the characteristic shown in FIG. 18, the size of the graphic is changed so as to spread vertically and horizontally around the center of gravity of the graphic according to the value of the risk difference ΔRD. Further, FIG. 19 shows the risk difference ΔRD as a horizontal axis and RGB components as a vertical axis, with a ratio from 0 to 100 for each RGB component. The color of the figure changes each component of RGB (R: red, G: green, B: blue) according to the value of the risk difference ΔRD according to the characteristics shown in FIG. If all the component values are 0, it represents black, and 100 represents white.

  The risk difference ΔRD can take a value from −100 to +100, but the graphic size is −25 or less or 50 or more has the same value (100%).

  18 and 19, the change in the size and color of the figure with respect to the change in ΔRD is larger when the risk difference is on the negative side than on the positive side. This is because when the risk grasped by the driver is insufficient, there is a high risk of overlooking the danger, and there is a higher risk of accidents than when the risk is felt excessively. In addition, in FIG. 19, a point where the curve changes discontinuously (for example, an R component whose risk difference ΔRD on the horizontal axis is around 40) is displayed so that the color change looks natural when displayed on the screen. This is a value adjusted (adjusted in consideration of display characteristics, video signal noise, etc.).

  In the display screen examples shown in FIGS. 14 to 17, when the risk difference ΔRD is small, as shown in FIG. 14, the size of the figure Z displayed on the display device 1 c is a size near the minimum size. Displayed in a color tone mainly composed of the G component. Further, when the risk difference is small but the risk difference is slightly larger than the case of FIG. 14, as shown in FIG. 15, the size of the figure Z is relatively larger than that of FIG. And B component and the main color tone.

  Further, when the risk difference ΔRD is slightly large, as shown in FIG. 16, the graphic Z is enlarged vertically and horizontally and displayed in a color tone mainly including the B component and the R component, and alerts the driver. Further, when the risk difference ΔRD increases, as shown in FIG. 17, the size of the figure Z approaches the maximum size and changes to a color tone mainly composed of the R component, giving a warning to the driver.

  As described above, the information presentation apparatus 1 according to the present embodiment estimates the difference between the risk recognized by the system and the risk recognized by the driver, and presents the risk to the driver according to the estimated risk difference. The display size and display color of information are changed simultaneously. This makes it easy to check with peripheral vision without the driver moving his / her line of sight, reducing the burden on the driver and keeping the driver's focus on driving and his / her risk recognition state and system risk recognition state. It is possible to intuitively grasp the deviation.

  Further, since the reliability output by the reliability evaluation unit 6 can be used, when the reliability decreases, it is possible to take measures such as changing the figure displayed on the display device 1c or discarding the estimation result. It is possible to present more accurate risk information to the driver.

  As a method of changing the display of the figure, the outline of the figure is clearly displayed when the reliability is high, and the outline of the figure is blurred when the reliability is low. The characteristic map shown in FIG. 20 is stored in the system in advance, and is changed with reference to this map. FIG. 20 shows the blur width corresponding to the reliability, with the reliability value on the horizontal axis and the width for blurring the outline on the vertical axis. The degree of outline blurring allows the driver to intuitively understand the reliability of the estimated value of the system. Alternatively, when the reliability is equal to or less than a certain value, the estimated value may be discarded and the display may not be changed.

DESCRIPTION OF SYMBOLS 1 Information presentation apparatus 1a Recognition system 1b Display control part 1c Display apparatus 2 Car exterior environment recognition part 3 Operation feature-quantization part 4 Model learning part 5 State estimation part 6 Reliability evaluation part

Claims (9)

A risk estimator that estimates the risk of an accident occurring while driving the vehicle;
A vehicle information presentation device, comprising: a display control unit that changes a display size and a display color of the risk level information to be presented to the occupant according to the risk level estimated by the risk level estimation unit. The risk estimation part
A driving environment risk estimation unit that estimates the risk of the driving environment of the vehicle;
And a grasping risk level estimation unit that estimates the risk level that the driver knows,
The display control unit
The display size and display color of the graphic representing the risk information are changed according to the difference between the estimated values of the risk of the driving environment and the risk known to the driver. The vehicle information presentation device described.   3. The vehicle information presentation apparatus according to claim 2, wherein the display control unit changes the size of the graphic as the difference in the estimated value of the risk increases.   4. The vehicle information presentation apparatus according to claim 3, wherein the display control unit changes the display color of the graphic stepwise so as to approach red as the difference in the estimated value of the risk increases.   5. The vehicle information presentation apparatus according to claim 3, wherein the graphic is a quadrangle.   The risk level estimation unit includes a reliability level evaluation unit that evaluates the reliability level of the estimation result obtained by the grasping risk level estimation unit, and the display control unit is configured to display risk level information to be presented to a passenger according to the reliability level. 6. The vehicle information presentation device according to claim 2, wherein the display is changed.   The vehicular information presentation device according to claim 6, wherein the display control unit blurs an outline of a figure to be displayed as the reliability decreases.   The vehicle information presentation apparatus according to claim 2, wherein the graphic is displayed on a part of a child screen of a display screen of the car navigation apparatus.   The vehicle information presentation apparatus according to claim 2, wherein the graphic is displayed in an instrument panel.