JP2006213276A - Driving intention estimation device, vehicular driving operation supporting device, and vehicle having the same - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a driving intention estimation device capable of estimating the driving intention of a driver with high accuracy according to the running situation of a preceding vehicle. <P>SOLUTION: The driving intention estimation device sets a plurality of imaginary drivers having each driving intention, and calculates the driven operational quantity of each imaginary driver based on the vehicular state and the condition around the self vehicle. By determining the order of approximation by comparing the calculated driving operational quantity of the imaginary driver with the actual driving operational quantity of an actual driver, the driving intention of the actual driver is estimated. Since the driving operational quantity of the actual driver when changing the lane is changed according to the running situation of the preceding vehicle, the standard of estimation when estimating the driving intention is changed according to the running situation of the preceding vehicle. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a driving intention estimation device that estimates a driving behavior intention of a driving driver and a vehicle driving operation assistance device that assists a driver in accordance with the driving intention.

  A conventional driving intention estimation apparatus estimates driving intention using a driver's gaze behavior (see, for example, Patent Document 1). This apparatus projects the driver's line-of-sight direction on the front projection plane, and estimates the driver's driving intention using the line-of-sight direction frequency distribution in a plurality of divided areas on the projection plane.

Prior art documents related to the present invention include the following.
JP 2002-331850 A

  The above-described conventional device can estimate the driver's intention of driving behavior using the driver's line-of-sight direction, the gaze gaze frequency, and the like. However, the driver's gaze behavior is affected by differences in the driving environment of the vehicle, and there is also a problem that the driver's individual differences are large and the accuracy of intention estimation varies. Is desired.

A driving intention estimation device according to the present invention includes a vehicle surrounding state detection unit that detects a vehicle surrounding state of a host vehicle, a driving operation amount detection unit that detects a driving operation amount by an actual driver, and a plurality of driving intentions. Virtual driver driving operation amount calculation means for calculating a driving operation amount necessary for each virtual driver to perform a driving intention based on the vehicle surrounding state detected by the vehicle surrounding state detection means for different virtual drivers; The degree of approximation between the driving operation amount of the plurality of virtual drivers calculated by the virtual driver driving operation amount calculating means and the actual driving operation amount of the driver detected by the driving operation amount detecting means (hereinafter, the driving operation amount approximation degree) Driving operation amount approximation degree calculating means for calculating the driving operation amount approximation degree calculating means and a plurality of driving operations calculated by the driving operation amount approximation degree calculating means. Driving intention estimation means for estimating the driving intention of the actual driver based on the degree of approximation, obstacle condition detection means for detecting the obstacle situation in front of the host vehicle, and obstacle status detected by the obstacle situation detection means And a driving intention estimation reference changing means for changing the driving intention estimation reference in the driving intention estimation means.
A driving intention estimation device according to the present invention includes a vehicle surrounding state detection unit that detects a vehicle surrounding state of a host vehicle, a driving operation amount detection unit that detects a driving operation amount by an actual driver, and a plurality of driving intentions. Virtual driver driving operation amount calculation means for calculating a driving operation amount necessary for each virtual driver to perform a driving intention based on the vehicle surrounding state detected by the vehicle surrounding state detection means for different virtual drivers; Approximate degree of the driving operation amount of the plurality of virtual drivers calculated by the virtual driver driving operation amount calculating means and the actual driving operation amount of the actual driver detected by the driving operation amount detecting means (hereinafter referred to as driving operation amount approximation) Driving operation amount approximation degree calculation means for calculating the degree of driving) and a plurality of driving operations calculated by the driving operation amount approximation degree calculation means. Calculated by the driving intention estimating means for estimating the actual driving intention of the driver, the obstacle situation detecting means for detecting the obstacle situation ahead of the host vehicle, and the virtual driver driving operation amount calculating means based on the degree of approximation of the work amount. Virtual driver driving operation amount correcting means for correcting the driving operation amount of the virtual driver based on the obstacle state detected by the obstacle state detecting means.
A vehicle driving operation assistance device according to the present invention includes a driving intention estimation device, an obstacle detection means for detecting an obstacle situation around the own vehicle, and a risk potential around the own vehicle based on a detection result by the obstacle detection means. Calculated by the risk potential calculating means, the operation reaction force calculating means for calculating the operation reaction force generated in the accelerator pedal based on the risk potential calculated by the risk potential calculating means, and the operation reaction force calculating means. Based on the operation reaction force generating means for generating the operation reaction force on the accelerator pedal, the driving intention estimation result by the driving intention estimation means, and the driving intention estimation reference set by the driving intention estimation reference variable setting means, the accelerator pedal And a correction means for correcting the operation reaction force generated at the same time.

  According to the present invention, for a plurality of different virtual drivers given a driving intention, a driving operation amount necessary for performing the driving intention based on the vehicle surrounding state is calculated, respectively, The driving intention is estimated based on the degree of approximation. At this time, the driving intention estimation standard or the driving amount of the virtual driver is corrected in consideration of the influence of the obstacle situation ahead of the host vehicle on the actual driving operation of the driver, so that the driving intention can be estimated with high accuracy. .

<< First Embodiment >>
A driving intention estimation apparatus according to a first embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a system diagram showing a configuration of a driving intention estimation device 1 according to the first embodiment of the present invention. First, the configuration of the driving intention estimation device 1 according to the first embodiment will be described.

  The driving intention estimation device 1 includes a driving operation amount detection unit 10 that detects a driving operation amount by a driver's operation, a vehicle surrounding state detection unit 20 that detects a state around the host vehicle, and a vehicle state detection unit that detects a vehicle state. 30, a virtual driver driving operation amount calculation unit 40, a virtual driver driving operation amount approximation degree calculation unit 50, a driving intention estimation reference variable setting unit 60, and a driving intention estimation unit 70.

  The driving intention estimation device 1 sets a plurality of virtual drivers having driving intentions, and compares the actual driving operation of the driver with the driving operation of the virtual driver. Then, the driving intention is estimated based on how close the actual driving operation of the driver and the driving operation of the virtual driver are. At this time, the driving intention is estimated based on the sequential approximation degree of the driving operation in the predetermined time from the present to the past.

  The driving operation amount detection unit 10 includes, for example, a steering angle sensor incorporated in a steering system, and detects the steering angle of the host vehicle. The vehicle surrounding state detection unit 20 includes, for example, a front camera, a yaw angle sensor, a yaw rate sensor, and the like that acquire a front road condition of the host vehicle as an image, and a lateral position in the lane of the host vehicle, a yaw angle between the host vehicle and the lane. The yaw rate acting on the host vehicle is detected. Furthermore, the traveling state of the preceding vehicle existing in front of the host vehicle is also detected. In addition, the vehicle surrounding state detection unit 20 includes an image processing device that performs image processing on an image signal acquired by the front camera. The vehicle state detection unit 30 includes a vehicle speed sensor that detects the vehicle speed, for example.

  The virtual driver driving operation amount calculation unit 40, the virtual driver driving operation amount approximation degree calculation unit 50, the driving intention estimation reference variable setting unit 60, and the driving intention estimation unit 70 are each configured by a microcomputer, for example. Alternatively, in a controller composed of a CPU and CPU peripheral components such as a ROM and a RAM, each can be configured by a software form of the CPU.

  The virtual driver driving operation amount calculation unit 40 calculates a driving operation amount necessary for a plurality of virtual drivers given different driving intentions to fulfill their driving intentions. Specifically, the virtual driver driving operation amount calculation unit 40 is based on the relative relationship between the lane marker (lane identification line) of the lane in which the host vehicle travels and the host vehicle detected by the vehicle surrounding state detection unit 10. To calculate the driving operation amounts of a plurality of virtual drivers.

  The virtual driver driving operation amount approximation degree calculation unit 50 includes a plurality of virtual driver driving operation amounts calculated by the virtual driver driving operation amount calculation unit 40 and an actual driver driving operation detected by the driving operation amount detection unit 10. The degree of approximation with the quantity is calculated. The driving intention estimation reference variable setting unit 60 sets a driving intention estimation reference used when estimating the actual driving intention of the driver based on the vehicle surrounding state detected by the vehicle surrounding state detection unit 20.

  The driving intention estimation unit 70 uses the driving intention estimation criteria set by the driving intention estimation criterion variable setting unit 60 and the driving operation amounts of a plurality of virtual drivers calculated by the virtual driver driving operation amount approximation degree calculation unit 50. Based on the degree of approximation with the actual driving operation amount of the driver, the actual driving intention of the driver is estimated.

Next, operation | movement of the driving intention estimation apparatus 1 by 1st Embodiment is demonstrated. First, the outline will be described.
The driving intention estimation device 1 sets a target position ahead of the host vehicle according to the driving intention, and assumes that the actual driver performs a driving operation so that the host vehicle reaches the target position. The driving operation amount of the virtual driver having the intention is calculated. However, in the actual driving situation, the amount of driving operation required to fulfill the driving intention changes depending on the driving situation of the preceding vehicle.

  Specifically, when a lane change is to be made, the amount of driving operation required for the host vehicle to change lanes depending on the driving conditions such as the lateral position and width of the preceding vehicle existing ahead of the host vehicle. Is different. 2 (a) to 2 (c), when the host vehicle changes the lane to the right lane and overtakes the preceding vehicle, the preceding vehicle travels in the center of the lane, the lane left region, and the lane right region. An example of the traveling locus of the host vehicle when traveling is shown.

  As shown in FIG. 2A, when the preceding vehicle is traveling in the center of the lane, the host vehicle approaches the preceding vehicle and then steers to the right to change the lane. On the other hand, when the preceding vehicle is traveling in the left lane area as shown in FIG. 2B, it is necessary to start the lane change as shown by the broken line if the steering operation is started from the same point. The steering amount is small. On the other hand, when the preceding vehicle is traveling in the right lane region as shown in FIG. 2 (c), the steering amount required for starting the lane change is large as shown by the broken line.

  In the device that estimates the driving intention using the approximate degree of the driving amount of the actual driver and the driving amount of the virtual driver, if the driving amount of the actual driver changes depending on the driving situation of the preceding vehicle, the driving intention is It becomes difficult to estimate well. Therefore, in the first embodiment, the driving intention estimation reference variable setting unit 60 variably sets the driving intention estimation reference according to the traveling state of the preceding vehicle, thereby reducing erroneous estimation of the driving intention. To do.

  Below, operation | movement of the driving intention estimation apparatus 1 by 1st Embodiment is demonstrated in detail using FIG. FIG. 3 is a flowchart showing the processing procedure of the driving intention estimation processing program in the driving intention estimation device 1. The processing content of the processing shown in FIG. 3 is continuously performed at regular intervals (for example, 50 msec).

  In step S101, the current lateral position x of the host vehicle and the yaw angle ψ of the host vehicle are detected. As shown in FIG. 4, the lateral position x in the lane is a lateral (lateral) distance from the lane center line of the own lane to the own vehicle center point O, and the yaw angle ψ is the self-direction relative to the straight direction of the lane. This is the rotation angle of the vehicle. The lateral position x in the lane of the host vehicle is represented by a positive value on the right side and a negative value on the left side from the center of the lane.

  In step S102, the virtual driver driving operation amount calculator 40 calculates driving operation amounts of a plurality of virtual drivers. Here, in order to set up three virtual drivers with driving intentions of lane keeping (LK), right lane change (LCR), and left lane change (LCL), and for each virtual driver to fulfill its driving intention Calculate the required driving operation amount Oid. The steering angle θid of the steering operation performed by the virtual driver is calculated as the driving operation amount Oid. A method for calculating the driving operation amount Oid of the virtual driver will be described below.

(1) When the driving intention of the virtual driver is lane keeping In order to calculate the steering angle θid of the virtual driver, the front reference point LK (i) is first set as the target position when the driving intention of the virtual driver is lane keeping. Then, the lateral position p_lk of the forward reference point LK (i) is calculated. The number of the forward reference points LK (i) is arbitrary, but here, a case where two forward reference points LK1 and LK2 are set on the front-rear direction center line of the host vehicle will be described as an example. As shown in FIG. 4, the distance px (i) from the vehicle center point O to the forward reference points LK1, LK2 is set to px (1) = 10 m, px (2) = 30 m, for example (px = {10 m , 30m}). The distance px (i) can be set according to the vehicle speed, for example.

The lateral distance lat_pos (px (i)) from the center line of the lane in which the host vehicle currently travels to the forward reference point LK (i) is the distance px (y) between the yaw angle ψ of the host vehicle and the forward point LK (i). Depending on i), for example, it can be calculated based on the image signal from the front camera. The lateral position p_lk (px (i)) of the forward reference point LK (i) in the case of lane keeping can be expressed by the following (Equation 1).
p_lk (px (i)) = lat_pos (px (i)) i = {1, ..., n} (Formula 1)
Here, n = 2.

Using the lateral position p_lk (px (i)) of the forward reference point LK (i), the steering angle θid_lk of the virtual driver in the case of lane keeping can be calculated from the following (Equation 2).
θid_lk = Σ {a (i) × p_lk (px (i))} (Formula 2)
Here, a (i) is a weighting coefficient for weighting the lateral position p_lk (px (i)) at the forward reference point LK (i), and an appropriate value is set in advance.

(2) When the driving intention of the virtual driver is the right lane change In order to calculate the steering angle θid of the virtual driver, the target position when the driving intention of the virtual driver is the right lane change is set to the front reference point LCR (i). Set. FIG. 4 shows an example in which two front reference points LCR1 and LCR2 are set in front of the host vehicle.

The lateral position p_lcr (px (i)) of the forward reference point LCR (i) in the case of changing the right lane is the left and right of the forward reference point LK (i) in the case of maintaining the lane, as expressed by the following (Equation 3). It can be calculated by adding the offset amount lc_offset_lcr to the direction distance lat_pos (px (i)).
p_lcr (px (i)) = lat_pos (px (i)) + lc_offset_lcr i = {1, ..., n} (Formula 3)
Here, n = 2. The offset amount lc_offset_lcr is set to an appropriate value in advance, for example, lc_offset_lcr = −1.75 in order to set the lateral position p_lcr (px (i)) of the forward reference point LCR (i) in the case of changing the right lane.

Using the lateral position p_lcr (px (i)) in the lane of the forward reference point LCR (i), the steering angle θid_lcr in the case of changing the right lane can be calculated from the following (Equation 4).
θid_lcr = Σ {a (i) × p_lcr (px (i))} (Formula 4)
Here, a (i) is a weighting coefficient for weighting the lateral position p_lcr (px (i)) in the lane at the forward reference point LCR (i), and an appropriate value is set in advance.

(3) When the driving intention of the virtual driver is the left lane change In order to calculate the steering angle θid of the virtual driver, the target position when the driving intention of the virtual driver is the left lane change is set to the front reference point LCL (i). Set. FIG. 4 shows an example in which two front reference points LCL1 and LCL2 are set in front of the host vehicle.

The lateral position p_lcl (px (i)) of the forward reference point LCL (i) in the case of the left lane change is expressed by the left and right of the forward reference point LK (i) in the case of lane keeping, as expressed by the following (Equation 5). It can be calculated by adding the offset amount lc_offset_lcl to the direction distance lat_pos (px (i)).
p_lcl (px (i)) = lat_pos (px (i)) + lc_offset_lcl i = {1, ..., n} (Formula 5)
Here, n = 2. The offset amount lc_offset_lcl is set in advance to an appropriate value, for example, lc_offset_lcl = 1.75, in order to set the lateral position p_lcl (px (i)) of the forward reference point LCL (i) when changing the left lane.

Using the lateral position p_lcl (px (i)) in the lane of the forward reference point LCL (i), the steering angle θid_lcl of the virtual driver in the case of changing the left lane can be calculated from the following (Equation 6).
θid_lcl = Σ {a (i) × p_lcl (px (i))} (Expression 6)
Here, a (i) is a weighting coefficient for weighting the lateral position p_lcl (px (i)) in the lane at the forward reference point LCL (i), and an appropriate value is set in advance.

  In step S103, the current steering angle θrd detected by the driving operation amount detector 10 is read as the actual driving operation amount Ord of the driver.

  In step S104, the virtual driver's driving operation amount Oid for each driving intention calculated in step S102 and the actual driver's driving operation amount Ord detected in step S102 are used to calculate the virtual driver's driving operation amount approximation degree Pid. calculate.

  Here, in order to simplify the explanation, the approximate degrees Pid_lk, Pid_lcr, and Pid_lcl when the driving intention is lane keeping, right lane change, and left lane change are collectively expressed as Pid. Similarly, the steering angles θid_lk, θid_lcr, θid_lcl of the virtual driver when the driving intention is lane keeping, right lane change, and left lane change are collectively expressed as θid.

The virtual driver driving operation amount approximation degree Pid is a normalized (normalized) value of the steering angle θid of the virtual driver with respect to a normal distribution in which the steering angle θrd of the actual driver is an average value and the predetermined value ρrd is a standard deviation. The log probability can be calculated from the following (Equation 7).
Pid = log {Probn ((θid_1−θrd) / ρrd)} (Expression 7)
Here, Probn is a probability density conversion function for calculating the probability that a given sample is observed from a population represented by a normal distribution.

  As described above, in step S104, the approximate degree Pid_lk in the case of maintaining the lane, the approximate degree Pid_lcr in the case of changing the right lane, and the approximate degree Pid_lcl in the case of changing the left lane are calculated using (Equation 7). These approximation degrees Pid_lk, Pid_lcr, and Pid_lcl are represented as Pid (t) because they are the first virtual driver operation amount approximation degrees at the current time t.

ここで、Πは、現時点ｔでの仮想ドライバ運転操作量近似度合Pid(t)から過去の時点（ｔ−ｍ＋１）での仮想ドライバ運転操作量近似度合Pid(t-m+1)までを全て積算した積和を表す。 In step S105, the series of driving operation amount approximation degrees Pids from the present to the past predetermined time are calculated using the driving operation amount approximation degrees Pid of the virtual driver calculated in step S104. Here, m virtual driver driving operation amount approximation degrees Pid calculated from the past time point (t−m + 1) to the present time t and stored in the memory of the virtual driver driving operation amount calculation unit 40 are used to The driving operation amount series approximation degree Pids for the driving intention is calculated. Here, when the driving intention is lane keeping, when the right lane is changed, and when the left lane is changed, the driving operation amount series approximation degrees Pids_lk, Pids_lcr, and Pids_lcl are collectively expressed as Pids. The driving operation amount series approximation degree Pids can be calculated from the following (Equation 8).

Here, Π is all from the virtual driver driving operation amount approximation degree Pid (t) at the current time t to the virtual driver driving operation amount approximation degree Pid (t−m + 1) at the past time point (t−m + 1). Represents the accumulated product sum.

  In addition, as shown in FIG. 5, when calculating the driving operation amount sequence approximation degree Pids_lk in the case of lane keeping, the lane keeping approximation degree Pid_lk calculated between the present time t and the past time point (t−m + 1). (t) to Pid_lk (t-m + 1) are used. Similarly, when calculating the driving operation amount series approximation degree Pids_lcr in the case of the right lane change, the right lane change approximation degree Pid_lcr (t) ˜ calculated from the present time t to the past time point (t−m + 1). When Pid_lcr (t-m + 1) is used to calculate the driving operation amount series approximation degree Pids_lcl in the case of a left lane change, the left lane change calculated between the present time t and the past time point (tm + 1) The approximate degrees Pid_lcl (t) to Pid_lcl (t−m + 1) are used.

In this way, in step S105, using (Equation 8), the driving operation amount sequence approximation degree Pids_lk in the case of lane keeping, and the driving operation amount series approximation degrees Pids_lcr and Pids_lcl in the case of right lane change and left lane change are respectively obtained. calculate. Here, as shown in (Equation 9), the maximum values of the series approximation degree Pids_lcr in the case of the right lane change and the series approximation degree Pids_lcl in the case of the left lane change are set as the series approximation degree Pids_lc in the case of the lane change. .
Pids_lc = max {Pids_lcr, Pids_lcl} (Formula 9)

  Note that the sequence approximation degree Pids_lk in the case of lane maintenance represents the likelihood that the actual driver will maintain the lane (lane maintenance likelihood Pr (LK)), and the series approximation degree Pids_lc in the case of lane change is the actual driver Represents the likelihood of lane change (lane change likelihood Pr (LC)). After calculating the actual driving intention likelihood of the driver in this way, the process proceeds to step S106.

  In step S106, the traveling state of the preceding vehicle existing ahead of the host vehicle is detected. Specifically, as shown in FIG. 6, the distance from the center of the lane to the center point Pl in the left-right direction of the preceding vehicle is detected as the lateral position xls in the lane of the preceding vehicle. The lateral position xls in the lane of the preceding vehicle is represented by a positive value on the right side and a negative value on the left side from the center of the lane.

  In subsequent step S107, a driving intention estimation criterion used when estimating the actual driving intention of the driver is set based on the traveling state of the preceding vehicle detected in step S106. Specifically, the lane change intention estimation threshold value T is set based on the lateral position xls in the lane of the preceding vehicle. FIG. 7 shows the relationship between the lateral position xls in the lane of the preceding vehicle and the lane change intention estimation threshold value T.

  As shown in FIG. 2B, when the preceding vehicle is traveling in the left side area of the lane, that is, when the lateral position xls in the lane is a negative value, it is necessary when the host vehicle changes the lane to the right side. The steering amount becomes small, and it becomes difficult to distinguish between a lane change intention and a lane keeping intention. Therefore, as indicated by a broken line in FIG. 7, when the in-lane lateral position xls exceeds a predetermined value −xls0, the threshold value T for estimating the right lane change intention is gradually increased. On the other hand, since the amount of steering required when the host vehicle changes the lane to the left side becomes large, it is easy to discriminate between the lane change intention and the lane keeping intention. Therefore, as shown by the solid line, the threshold value T for estimating the left lane change intention is gradually reduced.

  Similarly, as shown in FIG. 2C, when the preceding vehicle is traveling in the right region of the lane, that is, when the in-lane lateral position xls is a positive value, the in-lane lateral position xls is a predetermined value + xls0. As shown by the solid line, the threshold value T for estimating the left lane change intention is gradually increased, and as shown by the broken line, the threshold value T for estimating the right lane change intention is gradually increased. Make it smaller.

  As shown in FIG. 7, when the preceding vehicle is traveling in the lane center region with -xls0 <xls <+ xls0, the lane change intention estimation threshold T is set to a predetermined value T0 (for example, T0 = 0.5). ).

（式１０）で算出される車線変更意図スコアＳｃは、０〜１の間で連続的に変化し、車線変更の確信度（確率）が車線維持の確信度よりも相対的に高いほど大きな値をとる。例えば車線変更と車線維持の確信度が５０：５０のときに、スコアＳｃ＝０．５となり、車線変更の確信度が１００％のときに、スコアＳｃ＝１となる。 In step S108, the actual driving intention of the driver is estimated. First, the lane change intention score Sc is calculated from the following (Equation 10) using the lane keeping likelihood Pr (LK) and the lane change likelihood Pr (LC) calculated in step S105.

The lane change intention score Sc calculated by (Equation 10) continuously changes between 0 and 1, and the higher the lane change certainty (probability) is relatively higher than the lane maintenance certainty. Take. For example, when the certainty of lane change and lane maintenance is 50:50, the score Sc = 0.5, and when the certainty of lane change is 100%, the score Sc = 1.

  Next, the lane change intention score Sc is compared with the lane change intention estimation threshold T set in step S107. If the score Sc is larger than the lane change intention estimation threshold value T, it is estimated that the driving intention is a lane change, and if the score Sc is equal to or less than the threshold value T, it is estimated that the driving intention is lane keeping. Therefore, when the threshold value T is larger, it is possible to reduce erroneous estimation that the intention is a lane change when the intention is to maintain the lane. Moreover, the estimated timing of the lane change intention can be made earlier as the threshold value T is smaller. When the right steering is performed, the right lane change intention estimation threshold indicated by a broken line in FIG. 7 is used. When the left steering is performed, the left lane change intention estimation illustrated by the solid line is estimated. Use the threshold.

  In step S109, the estimation result of the actual driving intention of the driver estimated in step S108 is output. Thus, the current process is terminated.

Thus, in the first embodiment described above, the following operational effects can be achieved.
(1) The driving intention estimation device 1 is necessary for each virtual driver to perform the driving intention given to a plurality of different virtual drivers given the driving intention based on the vehicle surrounding state of the host vehicle. The driving operation amount Oid is calculated, and the approximate degrees of the calculated driving operation amounts Oid of the plurality of virtual drivers and the actual driving operation amount Ord of the driver are respectively calculated. Then, the actual driving intention of the driver is estimated based on the plurality of driving operation amount approximation degrees. The driving intention estimation reference variable setting unit 60 changes the driving intention estimation reference in the driving intention estimation unit 70 based on the obstacle situation ahead of the host vehicle. Accordingly, it is possible to accurately estimate the driving intention in consideration of the influence of the obstacle situation ahead of the host vehicle on the actual driving operation of the driver.
(2) The driving intention estimation reference variable setting unit 60 changes the driving intention estimation reference based on the traveling situation of the preceding vehicle ahead of the host vehicle as the obstacle situation. As a result, it is possible to accurately estimate the driving intention in consideration of the actual driving characteristics of the driver according to the traveling state of the preceding vehicle.
(3) The driving intention estimation reference variable setting unit 60 sets the driving intention estimation reference according to the lateral position xls in the lane of the preceding vehicle. As a result, it is possible to accurately estimate the driving intention in consideration of the actual driving characteristics of the driver in accordance with the traveling state of the preceding vehicle.
(4) The driving intention estimation reference variable setting unit 60 changes the lane so that the estimated sensitivity of the intention to change the lane toward the lane edge increases as the lateral position xls of the preceding vehicle approaches the lane edge on either the left or right. Reduce driving intention estimation criteria for intentions. For example, as shown by the solid line in FIG. 7, the estimated threshold value T for the intention to change the left lane decreases as the lateral position xls of the preceding vehicle approaches the left lane edge. Thereby, a lane change intention can be estimated at an early timing.
(5) The driving intention estimation reference variable setting unit 60 increases the estimation accuracy of the intention to change the lane in the direction opposite to the lane edge as the lateral position xls of the preceding vehicle approaches the lane edge on either side. In addition, increase the driving intention estimation criteria for lane change intentions. For example, as shown by a broken line in FIG. 7, the estimated threshold value T for the intention to change the right lane is increased as the lateral position xls of the preceding lane approaches the left lane edge. Thereby, it can reduce that it presumes that it is a lane change intention in the case of lane maintenance.

<< Second Embodiment >>
A driving intention estimation apparatus according to a second embodiment of the present invention will be described with reference to the drawings. The basic configuration of the driving intention estimation apparatus according to the second embodiment is the same as that of the first embodiment shown in FIG. Here, differences from the first embodiment will be mainly described.

  In the second embodiment, the lane change intention estimation threshold value T is set based on the distance from the lane marker (lane edge) to the preceding vehicle. Specifically, as shown in FIG. 8, the distance xlm from the lane edge of the road on which the host vehicle travels to the vehicle body end portion in the left-right direction of the preceding vehicle existing in front of the host vehicle is detected. The distance from the right edge of the preceding vehicle to the right lane edge is represented as xlmr, and the distance from the left edge to the left lane edge is represented as xlml.

  FIG. 9 shows the relationship between the distance xlm from the vehicle body end of the preceding vehicle to the lane edge and the lane change intention estimation threshold T. FIG. 9 collectively shows the distance xlmr to the right lane edge and the distance xlml to the left lane edge. Threshold T when estimating right lane change intention according to distance xlmr to right lane edge, and threshold when estimating left lane change intention according to distance xlml to left lane edge Set the value T.

  As shown in FIG. 9, when the distance xlm is greater than or equal to a predetermined value xlm0, that is, when the preceding vehicle is away from the lane edge, the threshold value T is set to a predetermined value T0 (for example, T0 = 0.5). When the distance xlm falls below the predetermined value xlm0, the threshold value T is decreased as the distance xlm decreases. When the preceding vehicle is approaching the lane edge, the amount of steering required when the host vehicle changes the lane increases, and it becomes easy to distinguish between the intention to change the lane and the intention to maintain the lane. To make it possible to estimate the lane change intention at an early timing.

As described above, in the second embodiment described above, the following operational effects can be obtained.
(1) The driving intention estimation reference variable setting unit 60 sets the driving intention estimation reference according to the distance xlm between the vehicle body end and the lane end in the lateral direction of the preceding vehicle. As a result, it is possible to accurately estimate the driving intention in consideration of the actual driving characteristics of the driver according to the traveling state of the preceding vehicle.
(2) The driving intention estimation reference variable setting unit 60 sets the lane change intention so that the estimated sensitivity of the lane change intention toward the lane edge direction increases as the distance xlm between the vehicle body edge portion and the lane edge of the preceding vehicle decreases. Reduce the driving intention estimation criteria for For example, as shown in FIG. 9, the lane change intention estimation threshold value T is decreased as the distance xlm decreases. Thereby, the intention to change lanes can be estimated at an early timing.
(3) The driving intention estimation reference variable setting unit 60 increases the estimation accuracy of the lane change intention in the direction opposite to the lane edge as the distance xlm between the vehicle body edge and the lane edge of the preceding vehicle decreases. Increase driving intention estimation criteria for lane change intentions. For example, when the distance xlmr between the vehicle body edge and the right lane edge decreases, the distance xlml between the vehicle body edge and the left lane edge increases, and the estimated threshold value T for the left lane change intention increases. Thereby, it can reduce that it presumes that it is a lane change intention in the case of lane maintenance.

<< Third Embodiment >>
A driving intention estimation apparatus according to a third embodiment of the present invention will be described with reference to the drawings. The basic configuration of the driving intention estimation apparatus according to the third embodiment is the same as that of the first embodiment shown in FIG. Here, differences from the first embodiment will be mainly described.

  In the third embodiment, the lane change intention estimation threshold T is set based on a distance obtained by adding an offset amount to the distance from the lane edge to the vehicle body edge of the preceding vehicle. Specifically, as shown in FIG. 10, the distance xlm from the lane edge of the road on which the host vehicle travels to the vehicle body end portion in the left-right direction of the preceding vehicle existing in front of the host vehicle is detected. Then, a distance xlmoff is set by adding an offset amount xloff to the distance xlm from the vehicle body end to the lane edge of the preceding vehicle. A distance obtained by adding the offset amount xloff to the distance from the right end portion of the preceding vehicle to the right lane end is represented by xlmoff_r, and a distance obtained by adding the offset amount xloff to the distance from the left end portion to the left lane end is represented by xlmoff_l.

  As the vehicle width Wl of the preceding vehicle is larger, the host vehicle tends to change lanes so as to largely avoid the preceding vehicle. Therefore, the offset amount xloff is set according to the vehicle body width (vehicle width) Wl of the preceding vehicle. FIG. 11 shows the relationship between the vehicle width Wl of the preceding vehicle and the offset amount xloff. The offset amount xloff is set to increase as the vehicle width Wl of the preceding vehicle increases.

  FIG. 12 shows the relationship between the distance xlmoff obtained by adding the offset amount xloff to the distance xlm from the vehicle body end to the lane edge of the preceding vehicle and the lane change intention estimation threshold T. FIG. 12 collectively shows the distance xlmoff_r obtained by adding the offset amount xloff to the distance xlmr to the right lane edge and the distance xlmoff_l obtained by adding the offset amount xloff to the distance xlml to the left lane edge. A threshold T for estimating the right lane change intention is set according to the right distance xlmoff_r, and a threshold T for estimating the left lane change intention is set according to the left distance xlmoff_l.

  As shown in FIG. 12, when the distance xlmoff is greater than or equal to a predetermined value xlmoff0, the threshold value T is set to a predetermined value T0 (for example, T0 = 0.5). When the distance xlmoff is smaller than the predetermined value xlmoff0, the threshold value T is decreased as the distance xlmoff is decreased. When the preceding vehicle is approaching the lane edge or the vehicle width Wl of the preceding vehicle is large, the amount of steering required when the host vehicle changes lanes becomes large, and discrimination between lane change intention and lane maintenance intention Therefore, the threshold value T is reduced so that the intention to change lanes can be estimated at an early timing.

As described above, in the third embodiment described above, the following operational effects can be obtained.
(1) The driving intention estimation reference variable setting unit 60 sets the driving intention estimation reference using a value corrected by adding an offset amount (correction value) xloff to the distance xlm between the vehicle body end and the lane edge of the preceding vehicle. To do. Thereby, the driving intention can be estimated with higher accuracy in consideration of the actual driving characteristics of the driver.
(2) Since the offset amount xloff is set according to the vehicle width Wl of the preceding vehicle, the driving intention estimation criterion is set in consideration of the influence of the vehicle width Wl of the preceding vehicle on the actual driver when changing the lane. Can be set.
(3) As shown in FIG. 11, the offset amount xloff is set so as to increase as the vehicle width Wl of the preceding vehicle increases. Accordingly, it is possible to estimate the driving intention with higher accuracy in consideration of the driving characteristics of the actual driver who changes the lane so that the preceding vehicle is largely avoided as the vehicle width Wl of the preceding vehicle increases.

<< Fourth Embodiment >>
A driving intention estimation apparatus according to a fourth embodiment of the present invention will be described with reference to the drawings. The basic configuration of the driving intention estimation apparatus according to the fourth embodiment is the same as that of the first embodiment shown in FIG. Here, differences from the first embodiment will be mainly described.

  In the fourth embodiment, the lane change intention estimation threshold value T is set based on the lateral position x of the host vehicle and the lateral position xls of the preceding vehicle. Specifically, as shown in FIG. 13, a distance xr from the center position Px in the left-right direction of the host vehicle to the center position Pl in the left-right direction of the preceding vehicle is detected. The distance between center positions xr is expressed as a positive value when the center position Pl of the preceding vehicle is offset to the right side from the center position Px of the host vehicle, and is expressed as a negative value when it is offset to the left side. FIG. 14 shows the relationship between the center position distance xr between the host vehicle and the preceding vehicle and the lane change intention estimation threshold value T.

  When the center position distance xr is a positive value and the preceding vehicle is offset to the right side as shown in FIG. 13, the steering amount required when the host vehicle changes the lane to the left side decreases, and the lane change occurs. It becomes difficult to distinguish between an intention and a lane keeping intention. Therefore, as indicated by a solid line in FIG. 14, when the distance between center positions xr exceeds a predetermined value + xr0, the threshold T for estimating the left lane change intention is gradually increased. On the other hand, since the amount of steering required when the host vehicle changes lanes to the right side becomes large, it is easy to discriminate between lane change intentions and lane keeping intentions. Therefore, as shown by the broken line, the threshold T when estimating the right lane change intention is gradually reduced.

  Similarly, if the distance between center positions xr is a negative value and the preceding vehicle is offset to the left side, if the distance between center positions xr exceeds a predetermined value -xr0, the intention to change the right lane is indicated as shown by a broken line. The threshold value T for estimation is gradually increased, and the threshold value T for estimation of the left lane change intention is gradually decreased as shown by the solid line.

  As shown in FIG. 14, when −xr0 <xr <+ xr0 and the deviation in the vehicle width direction between the host vehicle and the preceding vehicle is small, the lane change intention estimation threshold T is set to a predetermined value T0 (for example, T0 = 0.5).

As described above, in the fourth embodiment described above, the following operational effects can be obtained.
(1) The driving intention estimation reference variable setting unit 60 changes the driving intention estimation reference based on the preceding vehicle ahead of the host vehicle and the lateral position in the lane of the host vehicle. Thereby, it is possible to accurately estimate the driving intention in consideration of the relative relationship between the host vehicle and the preceding vehicle.
(2) The driving intention estimation reference variable setting unit 60 sets the driving intention estimation reference according to the center position distance xr between the lateral center position Pl of the preceding vehicle and the lateral center position Px of the host vehicle. Set. Thereby, based on the relative relationship between the host vehicle and the preceding vehicle, it is possible to accurately estimate the driving intention while considering the influence of the traveling state of the preceding vehicle on the actual driving operation of the driver.
(3) The driving intention estimation reference variable setting unit 60 increases the estimation sensitivity of the intention to change the lane in the direction in which the center position Pl of the preceding vehicle exists with respect to the center position Px of the host vehicle as the distance xr between the center positions increases. Reduce the driving intention estimation standard regarding the intention to change lanes so as to be higher. For example, as shown by a solid line in FIG. 14, when the preceding vehicle is offset to the left, the estimated threshold value T for the intention to change the left lane decreases as the distance xr between the center position values increases. Thereby, the intention to change lanes can be estimated at an early timing.
(4) The driving intention estimation reference variable setting unit 60 intends to change the lane in the direction opposite to the direction in which the center position Pl of the preceding vehicle exists with respect to the center position Px of the host vehicle as the distance between center positions xr increases. The driving intention estimation criterion for the lane change intention is increased so that the estimation accuracy of the vehicle is increased. For example, as indicated by a broken line in FIG. 14, when the preceding vehicle is offset to the left side, the estimated threshold value T for the intention to change the right lane increases as the distance between center positions xr increases. Thereby, it can reduce that it presumes that it is a lane change intention in the case of lane maintenance.

<< Fifth Embodiment >>
A driving intention estimation apparatus according to a fifth embodiment of the present invention will be described with reference to the drawings. The basic configuration of the driving intention estimation apparatus according to the fourth embodiment is the same as that of the first embodiment shown in FIG. Here, differences from the first embodiment will be mainly described.

  In the fifth embodiment, the lane change intention estimation threshold T is set based on the distance from the left and right end of the host vehicle to the left and right end of the preceding vehicle. Specifically, as shown in FIG. 15, when viewed from the rear of the host vehicle, the left and right sides of the preceding vehicle from the ends (outer end portions) that do not overlap the preceding vehicle among the left and right ends of the host vehicle. The distance xrw to the end portion (outer end portion) that does not overlap with the host vehicle among both ends in the direction is detected. The outer end portion distance xrw is expressed as a positive value when the center position Pl of the preceding vehicle is offset to the right side from the center position Px of the host vehicle, and is expressed as a negative value when it is offset to the left side. FIG. 16 shows the relationship between the outer end distance xrw between the host vehicle and the preceding vehicle and the lane change intention estimation threshold value T.

  If the outer end distance xrw is a positive value and the preceding vehicle is offset to the right side as shown in FIG. 15, the steering amount required when the host vehicle changes the lane to the left side becomes small, and the lane change It becomes difficult to distinguish between an intention and a lane keeping intention. Therefore, as shown by a solid line in FIG. 16, when the outer end portion distance xrw increases from the vehicle width w of the host vehicle, the threshold value T for estimating the left lane change intention is set to a predetermined value T0 (for example, T0 = 0.0). Gradually increase from 5). On the other hand, since the amount of steering required when the host vehicle changes lanes to the right side becomes large, it is easy to discriminate between lane change intentions and lane keeping intentions. Therefore, as shown by the broken line, the threshold T when estimating the right lane change intention is gradually reduced.

  Similarly, when the outer end portion distance xrw is a negative value and the preceding vehicle is offset to the left side, if the outer end portion distance xrw increases from the value −w corresponding to the vehicle width w of the host vehicle, As shown, the threshold T for estimating the right lane change intention is gradually increased from the predetermined value T0, and the threshold T for estimating the left lane change intention is gradually decreased as shown by the solid line. .

As described above, in the fifth embodiment described above, the following operational effects can be obtained.
(1) The driving intention estimation reference variable setting unit 60 sets the driving intention estimation reference according to the outer end distance xrw between the lateral outer end of the preceding vehicle and the lateral outer end of the host vehicle. Set. Thereby, based on the relative relationship between the host vehicle and the preceding vehicle, it is possible to accurately estimate the driving intention while considering the influence of the traveling state of the preceding vehicle on the actual driving operation of the driver.
(2) The drive intention estimation reference variable setting unit 60 sets the lane change in such a manner that the greater the outer end distance xrw is, the higher the estimated sensitivity of the lane change intention in the direction in which the preceding vehicle is offset with respect to the host vehicle. Reduce the driving intention estimation criteria for the intention to change. For example, as indicated by a solid line in FIG. 16, when the preceding vehicle is offset to the left, the estimated threshold value T for changing the left lane is decreased as the outer end distance xrw increases. Thereby, the intention to change lanes can be estimated at an early timing.
(3) The driving intention estimation reference variable setting unit 60 increases the estimation accuracy of the intention to change the lane in the direction opposite to the direction in which the preceding vehicle is offset with respect to the host vehicle as the outer end portion distance xrw increases. As described above, the driving intention estimation standard related to the lane change intention is increased. For example, as indicated by a broken line in FIG. 16, when the preceding vehicle is offset to the left side, the estimated threshold value T for the intention to change the right lane increases as the outer end portion distance xrw increases. Thereby, it can reduce that it presumes that it is a lane change intention in the case of lane maintenance.

<< Sixth Embodiment >>
A driving intention estimation apparatus according to a sixth embodiment of the present invention will be described with reference to the drawings. FIG. 17 shows a system diagram of the driving intention estimation device 2 according to the sixth embodiment. In FIG. 17, parts having the same functions as those in the first embodiment shown in FIG. Here, differences from the first embodiment will be mainly described.

  The driving intention estimation apparatus 2 according to the sixth embodiment further includes a virtual driver driving operation amount correction unit 90 that corrects the driving operation amount Oid of the virtual driver calculated by the virtual driver driving operation amount calculation unit 40. In the sixth embodiment, instead of variably setting the lane change intention estimation threshold value T, which is a driving intention estimation reference, according to the driving situation of the preceding vehicle, a virtual driver calculated according to the vehicle surrounding state By correcting the driving operation amount Oid in accordance with the traveling state of the preceding vehicle, it is possible to reduce erroneous estimation of the driving intention.

  Below, operation | movement of the driving intention estimation apparatus 2 by 6th Embodiment is demonstrated in detail using FIG. FIG. 18 is a flowchart showing a processing procedure of a driving intention estimation processing program in the driving intention estimation device 2. The processing content of the processing shown in FIG. 18 is continuously performed at regular intervals (for example, 50 msec).

  In step S201, the current lateral position x of the host vehicle and the yaw angle ψ of the host vehicle are detected. In step S202, the traveling state of the preceding vehicle existing ahead of the host vehicle, specifically, the lateral position xls in the lane of the preceding vehicle is detected.

  In step S203, parameters used for calculating the driving operation amount Oid of the virtual driver are set based on the traveling state of the preceding vehicle detected in step S202. Specifically, a correction coefficient Kxl for correcting the steering angle θid_lc of a virtual driver (lane change intention model) having a lane change intention is set based on the lateral position xls of the preceding vehicle. FIG. 19 shows the relationship between the lateral position xls in the lane of the preceding vehicle and the steering angle correction coefficient Kxl of the virtual driver who intends to change lanes.

  When the preceding vehicle is traveling in the left side area of the lane, that is, when the lateral position xls in the lane is a negative value, the steering amount required when the host vehicle changes the lane to the right side becomes small. Therefore, as indicated by a solid line in FIG. 19, when the in-lane lateral position xls exceeds a predetermined value -xls0, the steering angle correction coefficient Kxllc_r of the right lane change intention model is gradually reduced. On the other hand, since the steering amount required when the host vehicle changes the lane to the left side increases, the steering angle correction coefficient Kxllc_l of the left lane change intention model is gradually increased as shown by the broken line. By setting the correction coefficient Kxl in this way, the steering angle θid_lc of the lane change intention model is matched with the actual driving behavior of the driver.

  Similarly, when the preceding vehicle is traveling in the right side area of the lane, that is, when the lateral position xls in the lane is a positive value, if the lateral position xls in the lane exceeds a predetermined value + xls0, as shown by the solid line The steering angle correction coefficient Kxllc_r of the right lane change intention model is gradually increased, and the operation nucleus correction coefficient Kxllc_l of the left lane change intention model is gradually decreased as indicated by the broken line.

  As shown in FIG. 19, when the preceding vehicle is traveling in the lane center region with −xls0 <xls <+ xls0, the steering angle correction coefficients Kxllc_l and Kxllc_r of the left / right lane change intention model are set to 1.

  In step S204, the virtual driver driving operation amount calculation unit 40 calculates the driving operation amounts θid_lk, θid_lcr, and θid_lcl of the virtual driver of each driving intention model using the above-described (Expression 1) to (Expression 6). Furthermore, the steering angle correction coefficients Kxllc_r and Kxllc_l of the left and right lane change intention model calculated in step S203 are respectively multiplied by the driving operation amounts θid_lcr and θid_lcl of the virtual driver of the left and right lane change intention model, thereby obtaining the steering angle of the lane change intention model. Correct θid_lc.

  In step S205, the current steering angle θrd detected by the driving operation amount detector 10 is read as the actual driving operation amount Ord of the driver. In step S206, the above-described (Equation 7) is used using the driving operation amount Oid of the virtual driver for each driving intention calculated and corrected in step S204 and the actual driving operation amount Ord of the driver detected in step S205. The driving operation amount approximation degree Pid of the virtual driver is calculated.

In step S207, using the virtual driver's driving operation amount approximation degree Pid calculated in step S206, a series of driving operation amount approximation degrees Pids from the present to the past predetermined time is calculated from (Equation 8) described above. . In step S208, the lane change intention score Sc is calculated from (Equation 10) using the driving operation amount series approximation degree Pids calculated in step S207, and this is compared with a preset lane change intention estimation threshold T. Thus, the actual driving intention of the driver is estimated. The lane change intention estimation threshold value T is, for example, T = 0.5.
In step S209, the estimation result of the actual driver's driving intention estimated in step S208 is output. Thus, the current process is terminated.

Thus, in the sixth embodiment described above, the following operational effects can be achieved.
(1) The driving intention estimation device 1 is necessary for each virtual driver to perform the driving intention given to a plurality of different virtual drivers given the driving intention based on the vehicle surrounding state of the host vehicle. The driving operation amount Oid is calculated, and the approximate degrees of the calculated driving operation amounts Oid of the plurality of virtual drivers and the actual driving operation amount Ord of the driver are respectively calculated. Then, the actual driving intention of the driver is estimated based on the plurality of driving operation amount approximation degrees. The virtual driver driving operation amount correction unit 90 corrects the driving operation amount Oid of the virtual driver calculated by the virtual driver driving operation amount calculation unit 40 based on the obstacle situation ahead of the host vehicle. Accordingly, it is possible to accurately estimate the driving intention in consideration of the influence of the obstacle situation ahead of the host vehicle on the actual driving operation of the driver.
(2) The virtual driver driving operation amount correction unit 90 corrects the obstacle based on the traveling state of the preceding vehicle ahead of the host vehicle. As a result, it is possible to accurately estimate the driving intention in consideration of the actual driving characteristics of the driver according to the traveling state of the preceding vehicle.
(3) The virtual driver driving operation amount correction unit 90 sets the target position for calculating the driving operation amount θid_lc of the virtual driver given the lane change intention among the plurality of virtual drivers in the horizontal direction in the lane of the preceding vehicle. The driving operation amount θid_lc of the virtual driver is corrected by changing according to the position xls. Specifically, the forward reference points LCL (i) and LCR (i) intended to change lanes as shown in FIG. 4 are moved in the vehicle width (left and right) direction according to the lateral position xls in the lane of the preceding vehicle. Then, the steering angle θid_lc of the lane change intention model is multiplied by the correction coefficient Kxl. In this way, by changing the target position that is the calculation reference for the driving operation amount θid_lc of the virtual driver who intends to change lanes, that is, the front reference points LCL (i), LCR (i), it changes according to the driving situation of the preceding vehicle It is possible to estimate the driving intention that matches the actual driving behavior of the driver.
(4) The virtual driver driving operation amount correction unit 90 sets the target position of the lane change intention in the lane edge direction as the lateral position xls in the lane of the preceding vehicle approaches the lane edge on either the left or right side. Keep away from position. For example, as shown in FIG. 2C, when the in-lane lateral position xls of the preceding vehicle is approaching the right lane edge, the forward reference point LCR (i) that is the target position of the right lane change intention is maintained as the lane. Set to move away from the intended forward reference point LK (i). Thereby, the driving operation amount θid_lc of the virtual driver that matches the driving operation of the driver as indicated by the broken line can be calculated.
(5) The virtual driver driving operation amount correction unit 90 sets the target position of the lane change intention in the direction opposite to the lane edge direction as the lateral position xls in the lane of the preceding vehicle approaches the left or right lane edge. Move closer to the target position of the position intention. For example, as shown in FIG. 2B, when the in-lane lateral position xls of the preceding vehicle is approaching the left lane edge, the front reference point LCR (i), which is the target position of the right lane change intention, is maintained as the lane. Set to approach the intended forward reference point LK (i). Thereby, the driving operation amount θid_lc of the virtual driver that matches the driving operation of the driver as indicated by the broken line can be calculated.
(6) The target position is changed by the virtual driver driving operation amount correction unit 90, specifically, as shown in FIG. 19, as the in-lane lateral position xls increases, the lane change intention model is steered toward the lane edge direction. This can be realized by gradually increasing the angle correction coefficient Kxl and gradually decreasing the steering angle correction coefficient Kxl of the lane change intention model in the opposite direction. By multiplying the steering angle correction coefficient Kxl, the steering angle θid_lc of the lane change intention model changes, so that it is possible to estimate the driving intention that matches the actual driving behavior of the driver that changes according to the driving situation of the preceding vehicle.

<< Seventh Embodiment >>
A driving intention estimation apparatus according to a seventh embodiment of the present invention will be described with reference to the drawings. The basic configuration of the driving intention estimation apparatus according to the seventh embodiment is the same as that of the sixth embodiment shown in FIG. Here, differences from the sixth embodiment will be mainly described.

  In the seventh embodiment, the steering angle correction coefficient Kxl of the lane change intention model is set based on the distance from the lane edge to the preceding vehicle. Specifically, the distance xlm from the lane edge of the road on which the host vehicle travels to the vehicle body end portion in the left-right direction of the preceding vehicle existing ahead of the host vehicle is detected (see FIG. 8). The distance from the right edge of the preceding vehicle to the right lane edge is xlmr, and the distance from the left edge to the left lane edge is xlml.

  FIG. 20 shows the relationship between the distance xlm from the vehicle body end to the lane edge of the preceding vehicle and the steering angle correction coefficient Kxl of the lane change intention model. FIG. 20 collectively shows the distance xlmr to the right lane edge and the distance xlml to the left lane edge. Set the steering angle correction coefficient Kxl_lcr for the right lane change intention model according to the distance xlmr to the right lane edge, and set the steering angle correction coefficient Kxl_lcl for the left lane change intention model according to the distance xlml to the left lane edge To do.

  For example, if the preceding vehicle is running close to the right lane edge, the steering amount required when the host vehicle changes lanes to the right increases and the steering amount required when lane changes to the left Becomes smaller. Therefore, as shown in FIG. 20, when the distance xlm from the vehicle body end to the lane edge of the preceding vehicle is smaller than the predetermined value xlm1, the steering angle correction coefficient of the virtual driver having the intention to change the lane in the lane edge direction. Increase Kxl gradually. On the other hand, when the distance xlm to the lane edge is larger than the predetermined value xlm2, the steering angle correction coefficient Kxl is gradually reduced.

  When xlm1 <xlm <xlm2 and the preceding vehicle is traveling in the lane center region, the steering angle correction coefficient Kxl of the lane change intention model is set to 1.

As described above, in the seventh embodiment described above, the following effects can be obtained.
(1) The virtual driver driving operation amount correction unit 90 sets the target position for calculating the driving operation amount θid_lc of a virtual driver given a lane change intention among a plurality of virtual drivers as the vehicle body end in the lateral direction of the preceding vehicle. The driving operation amount θid_lc of the virtual driver is corrected by changing according to the distance xlm between the vehicle and the lane edge. Specifically, the forward reference points LCL (i) and LCR (i) intended to change lanes as shown in FIG. 4 are set in the vehicle width (left and right) direction according to the distance xlm from the vehicle body edge to the lane edge of the preceding vehicle. So that the steering angle θid_lc of the lane change intention model is multiplied by the correction coefficient Kxl. In this way, by changing the target position that is the calculation reference for the driving operation amount θid_lc of the virtual driver who intends to change lanes, that is, the front reference points LCL (i), LCR (i), it changes according to the driving situation of the preceding vehicle It is possible to estimate the driving intention that matches the actual driving behavior of the driver.
(2) The change of the target position by the virtual driver driving operation amount correction unit 90 is more specifically, as the distance xlm from the vehicle body end to the lane end of the preceding vehicle becomes smaller, as shown in FIG. This can be realized by gradually increasing the steering angle correction coefficient Kxl of the lane change intention model toward the lane and gradually decreasing the steering angle correction coefficient Kxl of the lane change intention model in the opposite direction. By multiplying the steering angle correction coefficient Kxl, the steering angle θid_lc of the lane change intention model changes, so that it is possible to estimate the driving intention that matches the actual driving behavior of the driver that changes according to the driving situation of the preceding vehicle.

<< Eighth Embodiment >>
A driving intention estimation apparatus according to an eighth embodiment of the present invention will be described with reference to the drawings. The basic configuration of the driving intention estimation apparatus according to the eighth embodiment is the same as that of the sixth embodiment shown in FIG. Here, differences from the sixth embodiment will be mainly described.

In the eighth embodiment, the steering angle correction coefficient Kxl of the lane change intention model is set based on a distance obtained by adding an offset amount to the distance from the lane edge to the preceding vehicle. Specifically, a distance xlmoff obtained by detecting a distance xlm from a lane edge of a road on which the host vehicle travels to a vehicle body end portion in the left-right direction of a preceding vehicle existing ahead of the host vehicle, and adding an offset amount xloff to the distance xlm. Is set (see FIG. 10). A distance xlmr from the right end portion of the preceding vehicle to the right lane edge is added to the offset amount xloff, and xlmoff_r is a distance xlml from the left end portion to the left lane end and the offset amount xloff is added to xlmoff_l.
The offset amount xloff is set according to the vehicle width Wl of the preceding vehicle as shown in FIG.

  FIG. 21 shows the relationship between the distance xlmoff obtained by adding the offset amount xloff to the distance xlm from the vehicle body edge to the lane edge of the preceding vehicle and the steering angle correction coefficient Kxl of the lane change intention model. FIG. 21 collectively shows a distance xlmoff_r obtained by adding the offset amount xloff to the distance xlmr to the right lane edge and a distance xlmoff_l obtained by adding the offset amount xloff to the distance xlml to the left lane edge. The steering angle correction coefficient Kxl_lcr of the right lane change intention model is set according to the distance xlmoff_r related to the right lane edge, and the steering angle correction coefficient Kxl_lcl of the left lane change intention model is set according to the distance xlmoff_l related to the left lane edge.

  For example, if the preceding vehicle is running close to the right lane edge, or if the preceding vehicle has a large vehicle width Wl, the steering amount required when the host vehicle changes lanes to the right side increases. The amount of steering required when changing the lane is reduced. Therefore, as shown in FIG. 21, when the distance xlmoff obtained by adding the offset amount xloff to the distance xlm from the vehicle body end to the lane edge of the preceding vehicle is smaller than a predetermined value xlmoff1, the intention to change the lane toward the lane edge The steering angle correction coefficient Kxl of the virtual driver having is gradually increased. On the other hand, when the distance xlmoff obtained by adding the offset amount xloff to the distance xlm to the lane edge becomes larger than the predetermined value xlmoff2, the steering angle correction coefficient Kxl is gradually decreased.

  In the case of xlmoff1 <xlmoff <xlmoff2, the steering angle correction coefficient Kxl of the lane change intention model is set to 1.

Thus, in the eighth embodiment described above, the following operational effects can be achieved.
(1) The virtual driver driving operation amount correction unit 90 uses the value xlmoff corrected by adding an offset amount (correction value) xloff to the distance between the vehicle body end of the preceding vehicle and the lane edge, and the target of the lane change intention model Set the position. As shown in FIG. 11, the target position is set by adding an offset amount xloff set according to the vehicle width Wl of the preceding vehicle, so that it matches the actual driving behavior of the driver that changes according to the vehicle width of the preceding vehicle. Driving intent can be estimated.
(2) Specifically, the target position is changed by the virtual driver driving operation amount correction unit 90 as shown in FIG. 21 at an offset amount (correction value) xloff at a distance xlm from the vehicle body end to the lane end of the preceding vehicle. This can be realized by setting the steering angle correction coefficient Kxl of the lane change intention model in accordance with the distance xlmoff added.

<< Ninth embodiment >>
Next, a vehicle driving assistance device according to a ninth embodiment of the present invention will be described with reference to the drawings. FIG. 22 is a system diagram showing a configuration of a vehicle driving assistance device 100 according to the ninth embodiment of the present invention, and FIG. 23 is a configuration diagram of a vehicle on which the vehicle driving assistance device 100 is mounted. . The vehicle driving operation assistance device 100 assists an actual driver's driving operation based on the driving intention estimation results of the driving intention estimation devices 1 and 2 described in the first to eighth embodiments.

First, the configuration of the vehicle driving operation assistance device 100 will be described.
The laser radar 110 is attached to the front grill or bumper of the vehicle, and scans the front area of the host vehicle by irradiating infrared light pulses in the horizontal direction. The laser radar 110 measures the reflected wave of the infrared light pulse reflected by a plurality of front reflectors (usually the rear end of the preceding vehicle), and determines the inter-vehicle distance to the preceding vehicle from the arrival time of the reflected wave. Detect relative speed. The detected inter-vehicle distance and relative speed are output to the controller 150. The forward area scanned by the laser radar 110 is about ± 6 deg with respect to the front of the host vehicle, and a forward object existing in this range is detected.

  The front camera 120 is a small CCD camera, a CMOS camera, or the like attached to the upper part of the front window, and detects the state of the front road as an image. The image signal from the front camera 120 is subjected to image processing by the image processing device 130 and output to the controller 150. The detection area by the front camera 120 is about ± 30 deg in the horizontal direction with respect to the front-rear direction center line of the vehicle, and the front road scenery included in this area is captured as an image.

  The vehicle speed sensor 140 detects the vehicle speed of the host vehicle by measuring the number of wheel rotations and the number of rotations on the output side of the transmission, and outputs the detected host vehicle speed to the controller 150.

  Furthermore, the actual driver's driving intention estimation result estimated by the driving intention estimation apparatus 1 according to any one of the first to fifth embodiments described above is input to the controller 150. Of course, the estimation result of the driving intention estimation device 2 according to any of the sixth to eighth embodiments may be used.

  The controller 150 includes a CPU and CPU peripheral components such as a ROM and a RAM. The controller 150 configures a risk potential calculation unit 151, an accelerator pedal reaction force command value calculation unit 152, and an accelerator pedal reaction force command value correction unit 153, for example, depending on the software form of the CPU.

  The risk potential calculation unit 151 uses the host vehicle speed, the inter-vehicle distance, the relative vehicle speed relative to the preceding vehicle input from the laser radar 110 and the vehicle speed sensor 140, and the image information around the vehicle input from the image processing device 130. The surrounding risk potential RP is calculated. The accelerator pedal reaction force command value calculation unit 152 calculates a command value FA of the accelerator pedal reaction force generated by the accelerator pedal 160 based on the risk potential RP calculated by the risk potential calculation unit 151.

  The accelerator pedal reaction force command value correction unit 153 corrects the accelerator pedal reaction force command value FA calculated by the accelerator pedal reaction force command value calculation unit 152 based on the driving intention estimation result input from the driving intention estimation device 1. To do. The accelerator pedal reaction force command value FA corrected by the accelerator pedal reaction force command value correction unit 153 is output to the accelerator pedal reaction force control device 170.

  The accelerator pedal reaction force control device 170 controls the accelerator pedal operation reaction force according to a command value from the controller 150. A servo motor 180 and an accelerator pedal stroke sensor 181 are connected to the accelerator pedal 160 via a link mechanism (see FIG. 24). The servo motor 180 controls the torque and the rotation angle in accordance with a command from the accelerator pedal reaction force control device 170, and arbitrarily controls the operation reaction force generated when the driver operates the accelerator pedal 160. The accelerator pedal stroke sensor 181 detects the stroke amount (operation amount) AS of the accelerator pedal 160 converted into the rotation angle of the servo motor 180 via the link mechanism.

  Note that the normal accelerator pedal reaction force characteristic when the accelerator pedal reaction force control is not performed is set such that, for example, the accelerator pedal reaction force increases linearly as the operation amount AS increases. The normal accelerator pedal reaction force characteristic can be realized by the spring force of a torsion spring (not shown) provided at the center of rotation of the accelerator pedal 160, for example.

Next, the operation of the vehicle driving assistance device 100 according to the ninth embodiment will be described. First, the outline will be described.
The controller 150 controls the accelerator pedal reaction force generated in the accelerator pedal 160 based on the risk potential RP around the host vehicle, specifically, the risk potential with respect to the preceding vehicle. Here, when the driver approaches the preceding vehicle with the intention of changing the lane, if the accelerator pedal reaction force is increased in accordance with the increase in the risk potential RP, the driver's driving operation may be hindered or the driver may feel uncomfortable. is there. Therefore, when the driver's intention to change the lane is estimated by the driving intention estimation device 1, the accelerator pedal reaction force is made smaller than when the intention to change the lane is not estimated. Further, the accelerator pedal reaction force is adjusted based on the lane change estimation threshold value T used for driving intention estimation.

  As described above, by setting the lane change estimation threshold value T to be large, the frequency of erroneous estimation that the lane change is occurring while the lane is maintained is reduced. However, while the estimation accuracy of the lane change intention is increased, the timing for estimating the lane change intention is delayed. On the other hand, if the lane change estimation threshold value T is set small, the sensitivity for estimating the intention of lane change is increased and the estimation timing is advanced, but the frequency of erroneous estimation that the lane change is increased.

  Therefore, when it is estimated that the driver's driving intention is a lane change, the accelerator pedal reaction force is adjusted so as to compensate for a delay in the lane change estimation timing when the lane change estimation threshold value T is large.

  Below, operation | movement of the driving operation assistance apparatus 100 for vehicles is demonstrated in detail using the flowchart of FIG. FIG. 25 is a flowchart showing the processing procedure of the driving operation assistance control program in the controller 150. This processing content is continuously performed at regular intervals (for example, 50 msec).

  In step S401, an environmental state quantity representing the traveling environment around the host vehicle detected by the laser radar 110, the front camera 120, and the vehicle speed sensor 140 is read. Specifically, the inter-vehicle distance D between the host vehicle and the preceding vehicle, the preceding vehicle speed V2, and the host vehicle speed V1 are read. In step S402, the risk potential RP around the host vehicle is calculated based on the travel environment data read in step S401. Here, in order to calculate the risk potential RP around the host vehicle, a margin time TTC and an inter-vehicle time THW for the preceding vehicle are calculated.

The margin time TTC is a physical quantity indicating the current degree of proximity of the host vehicle with respect to the preceding vehicle. The allowance time TTC is the number of seconds after which the inter-vehicle distance D becomes zero when the current traveling state continues, that is, when the host vehicle speed V1, the preceding vehicle speed V2, and the relative vehicle speed Vr (Vr = V2-V1) are constant. And a value indicating whether or not the preceding vehicle is in contact. The margin time TTC is obtained by the following (Equation 11).
TTC = −D / Vr (Formula 11)

  The smaller the margin time TTC value, the closer the contact with the preceding vehicle, and the greater the degree of approach to the preceding vehicle. For example, when approaching a preceding vehicle, it is known that most drivers start a deceleration action before the margin time TTC becomes 4 seconds or less.

The inter-vehicle time THW is an effect when it is assumed that the degree of influence on the margin time TTC due to a change in the vehicle speed of the assumed vehicle ahead, that is, the relative vehicle speed Vr changes when the host vehicle is following the preceding vehicle. It is a physical quantity indicating the degree. The inter-vehicle time THW is expressed by the following (formula 12).
THW = D / V1 (Formula 12)

  The inter-vehicle time THW is obtained by dividing the inter-vehicle distance D by the own vehicle speed V1, and indicates the time until the own vehicle reaches the current position of the preceding vehicle. The greater the inter-vehicle time THW, the smaller the predicted influence level with respect to the surrounding environmental changes. That is, when the inter-vehicle time THW is large, even if the vehicle speed of the preceding vehicle changes in the future, the degree of approach to the preceding vehicle is not greatly affected, and the margin time TTC does not change so much. When the own vehicle follows the preceding vehicle and the own vehicle speed V1 = the preceding vehicle speed V2, the inter-vehicle time THW can be calculated using the preceding vehicle speed V2 instead of the own vehicle speed V1 in (Equation 12).

Then, the risk potential RP for the preceding vehicle is calculated using the calculated margin time TTC and the inter-vehicle time THW. The risk potential RP for the preceding vehicle can be calculated using the following (Equation 13).
RP = a / THW + b / TTC (Formula 13)

  As shown in (Formula 13), the risk potential RP is a physical quantity that is continuously expressed from the margin time TTC and the inter-vehicle time THW. Here, a and b are constants for appropriately weighting the inter-vehicle time THW and the margin time TTC, and appropriate values are set in advance. The constants a and b are set to, for example, a = 1 and b = 8 (a <b).

  In step S403, the stroke amount S of the accelerator pedal 160 detected by the accelerator pedal stroke sensor 181 is read. In step S404, an accelerator pedal reaction force command value FA is calculated based on the risk potential RP calculated in step S402. First, the reaction force increase amount ΔF corresponding to the risk potential RP is calculated.

  FIG. 26 shows the relationship between the risk potential RP for the preceding vehicle and the reaction force increase amount ΔF. As shown in FIG. 26, when the risk potential RP is less than or equal to the minimum value RPmin, the reaction force increase amount ΔF is set to zero. This is to avoid annoying the driver by increasing the accelerator pedal reaction force FA when the risk potential RP around the host vehicle is very small. As the minimum value RPmin, an appropriate value is set in advance.

In the region where the risk potential RP exceeds the minimum value RPmin, the reaction force increase amount ΔF is set to increase exponentially according to the risk potential RP. The reaction force increase amount ΔF is expressed by the following (formula 14).
ΔF = k · RP ⁿ (Expression 14)
Here, the constants k and n are different depending on the vehicle type and the like, and are appropriately set in advance so that the risk potential RP can be effectively converted into the reaction force increase amount ΔF based on the results obtained by a drive simulator or a field test. Keep it.

  Further, the accelerator pedal reaction force command value FA is calculated by adding the reaction force increase amount ΔF calculated according to (Equation 14) to the normal reaction force characteristic corresponding to the accelerator pedal stroke amount S.

  In step S405, the estimation result of the driving intention by the driving intention estimation device 1 is read, and it is determined whether or not the estimation result is a lane change. If it is estimated that the driver's driving intention is a lane change, the process proceeds to step S406. In step S406, the lane change estimation threshold value T when the driving intention estimation device 1 estimates that the lane change has occurred is read. Here, if it is estimated that the driving intention is a lane change before the current cycle, the lane change estimation threshold T when the lane change intention is estimated for the first time is used as it is.

  In the subsequent step S407, when the intention to change the lane is estimated, the accelerator pedal reaction force command value FA calculated in step S404 is corrected based on the estimated lane change threshold value T. Specifically, the accelerator pedal reaction force command value FA calculated in step S404 is subjected to filter processing such as a low-pass filter to be attenuated.

The corrected accelerator pedal reaction force command value FA can be expressed using the following (Equation 15). In (Equation 15), the corrected reaction force command value FA is expressed as FAc as a control reaction force command value.
FAc = gf (FA)
= Kf · {1 / (1 + Kfdx · a · Tsf)} · FA (Expression 15)
Here, a is an appropriately set constant, and Tsf is a time constant for attenuating the reaction force command value FA. Kfdx is a correction coefficient applied to the time constant Tsf for correcting the accelerator pedal reaction force command value FA, and is set according to the lane change intention estimation threshold value T as shown in FIG.

When the lane change estimated threshold value T is smaller than the predetermined value T1 (<T0), the estimation timing of the lane change intention is advanced, so that the correction coefficient Kfdx is gradually increased as shown in FIG. When the lane change estimated threshold value T is larger than the predetermined value T2 (> T0), the estimation timing of the lane change intention is delayed, so the correction coefficient Kfdx is gradually reduced. In the case of T1 ≦ T ≦ T2, the correction coefficient Kfdx = 1 is set. Thus, as the estimated threshold value T increases, the time constant term (Kfdx · a · Tsf) decreases, and the accelerator pedal reaction force can be quickly attenuated.
Of course, it is possible to directly set the time constant Tsf in accordance with the estimated threshold value T.

  On the other hand, if it is determined in step S405 that the driving intention estimated by the driving intention estimation apparatus 1 is not a lane change, the process proceeds to step S408, and the accelerator pedal reaction force command value FA calculated in step S404 is used as it is for control. Set as command value FAc.

  In step S409, the accelerator pedal reaction force command value FAc set in step S407 or S408 is output to the accelerator pedal reaction force control device 170. The accelerator pedal reaction force control device 170 controls the servo motor 180 in accordance with a command input from the controller 150. Thus, the current process is terminated.

Thus, in the ninth embodiment described above, the following operational effects can be achieved.
(1) The controller 150 calculates the risk potential RP based on the obstacle situation around the host vehicle, and performs accelerator pedal operation reaction force control based on the risk potential RP. At this time, the operation reaction force generated in the accelerator pedal 160 is corrected based on the estimation result by the driving intention estimation device 1 and the lane change estimation threshold value T. Thereby, the operation reaction force control suitable for the driver's driving intention can be performed while the risk potential RP around the host vehicle is transmitted to the driver as the operation reaction force of the accelerator pedal 160 which is a vehicle operation device. Furthermore, the system performance can be compensated according to the situation when the driving intention estimation apparatus 1 estimates the intention to change lanes.
(2) The controller 150 corrects the relationship between the risk potential RP and the operation reaction force, that is, the accelerator pedal reaction force command value FA, based on the driving intention estimation result and the lane change estimation threshold value T. Specifically, when the driving intention estimation device 1 estimates that the driver's driving intention is a lane change, the accelerator pedal reaction force command value FA is reduced as compared to a case where the driving intention is estimated to be other than a lane change. When the threshold value T is large, the accelerator pedal reaction force command value FA is lowered than when the threshold value T is small. By lowering the accelerator pedal reaction force command value FA when the driving intention is a lane change, the driver's driving operation for changing the lane is not hindered. However, if the threshold value T is large, the estimation accuracy of the lane change intention is increased and the erroneous estimation is reduced, but the estimation timing of the lane change intention is delayed. Therefore, as the threshold value T increases, the coefficient Kfdx applied to the time constant Tsf is decreased as shown in FIG. 27 so that the accelerator pedal operation reaction force is quickly attenuated after the intention to change the lane is estimated. As a result, it is possible to achieve both reduction in erroneous estimation of lane change intention and securing of accelerator pedal reaction force control performance.

<< Tenth Embodiment >>
A vehicle operation assistance device according to a tenth embodiment of the present invention will be described with reference to the drawings. FIG. 28 is a system diagram showing a configuration of a vehicle driving assistance device 200 according to the tenth embodiment of the present invention. In FIG. 28, portions having the same functions as those of the ninth embodiment shown in FIG. 22 are denoted by the same reference numerals. Here, differences from the ninth embodiment will be mainly described.

  In the tenth embodiment, when the driver's intention to change lanes is estimated by the driving intention estimation device 1, the risk potential RP around the host vehicle is corrected. Therefore, the controller 150A of the vehicle driving assistance device 200 includes a risk potential calculation unit 151, a risk potential correction unit 154, and an accelerator pedal reaction force command value calculation unit 155.

  Next, the operation of the vehicle driving assistance device 200 according to the tenth embodiment will be described in detail with reference to FIG. FIG. 29 is a flowchart showing the processing procedure of the driving operation assistance control program in the controller 150A. This processing content is continuously performed at regular intervals (for example, 50 msec). The processing in steps S501 and S502 is the same as the processing in steps S401 and S402 in the flowchart of FIG.

  In step S503, the estimation result of the driving intention by the driving intention estimation device 1 is read, and it is determined whether or not the estimation result is a lane change. If it is estimated that the driver's driving intention is a lane change, the process proceeds to step S504. In step S504, the lane change estimation threshold value T when the driving intention estimation device 1 starts to estimate that the lane change has occurred is read.

  In the subsequent step S505, when the intention to change the lane is estimated, the risk potential RP calculated in step S502 is corrected based on the lane change estimated threshold value T read in step S504. Specifically, the risk potential RP calculated in step S502 is attenuated by applying a filter process such as a low-pass filter.

The risk potential RP after the filter processing can be expressed using the following (Equation 16). In (Expression 16), the corrected risk potential actually used for control is represented by RPc.
RPc = gr (RP)
= Kr · {1 / (1 + Krdx · a · Tsr)} · RP (Expression 16)
Here, a is an appropriately set constant, and Tsr is a time constant when the risk potential RP is attenuated. Krdx is a correction coefficient applied to the time constant Tsr in order to correct the risk potential RP, and is set according to the lane change intention estimation threshold T as shown in FIG.

When the lane change estimated threshold value T is smaller than the predetermined value T1 (<T0), the estimation timing of the lane change intention is advanced, so that the correction coefficient Krdx is gradually increased as shown in FIG. When the lane change estimated threshold value T is larger than the predetermined value T2 (> T0), the estimation timing of the lane change intention is delayed, so the correction coefficient Krdx is gradually reduced. In the case of T1 ≦ T ≦ T2, the correction coefficient Krdx = 1 is set. As a result, the time constant term (Krdx · a · Tsr) decreases as the estimated threshold value T increases, so that the accelerator pedal reaction force can be quickly attenuated.
It is of course possible to directly set the time constant Tsr according to the estimated threshold value T.

  On the other hand, if it is determined in step S503 that the driving intention estimated by the driving intention estimation device 1 is lane keeping, the process proceeds to step S506, and the risk potential RP calculated in step S502 is directly used as the risk potential RPc for control. Set.

  In step S507, the accelerator pedal stroke amount S detected by the accelerator pedal stroke sensor 181 is read. In step S508, the accelerator pedal reaction force command value FA is calculated based on the risk potential RPc set in step S505 or step S506. Here, as in the ninth embodiment described above, the accelerator pedal reaction force command value FA is calculated according to, for example, the map of FIG. However, RP → RPc. In step S509, the accelerator pedal reaction force command value FA calculated in step S508 is output to the accelerator pedal reaction force control device 170. Thus, the current process is terminated.

Thus, in the tenth embodiment described above, the following operational effects can be achieved.
Based on the driving intention estimation result and the lane change estimation threshold value T, the controller 150A corrects the relationship between the risk potential RP and the operation reaction force, that is, the accelerator pedal reaction force command value FA. Specifically, when it is estimated by the driving intention estimation device 1 that the driver's driving intention is a lane change, the risk potential RP is reduced as compared to a case where the driving intention is estimated to be other than a lane change, and a threshold value is set. When T is large, the risk potential RP is lowered than when the threshold value T is small. When the driving intention is a lane change, the accelerator pedal reaction force command value FA is reduced by lowering the risk potential RP, and the driving operation of the driver who wants to change the lane is not hindered. However, if the threshold value T is large, the estimation accuracy of the lane change intention is increased and the erroneous estimation is reduced, but the estimation timing of the lane change intention is delayed. Therefore, when the threshold value T is large, the coefficient Krdx applied to the time constant Tsr is decreased as shown in FIG. 30 so that the risk potential RP is quickly attenuated after the intention to change the lane is estimated. As a result, it is possible to achieve both reduction in erroneous estimation of lane change intention and ensuring performance of accelerator pedal reaction force control according to the risk potential RP.

  In the driving intention estimation device 2 according to the sixth to eighth embodiments, the lane change intention estimation threshold value T is a fixed value, so that the driving intention estimation result is the vehicle according to the ninth or tenth embodiment. When used in the driving operation assisting devices 100, 200, it is not necessary to correct the accelerator pedal reaction force command value FA or the risk potential RP according to the threshold value T.

  In the first to eighth embodiments described above, the influence of the traveling state of the preceding vehicle or the relative positional relationship between the own vehicle and the preceding vehicle on the actual driving behavior when the own vehicle changes lanes is considered. Thus, the lane change intention estimation threshold T and the steering angle θid_lc of the lane change intention model are changed. Of course, it is possible to use parameters other than those used in the first to eighth embodiments described above for the traveling state of the preceding vehicle or the relative positional relationship between the host vehicle and the preceding vehicle.

  In the above-described first to eighth embodiments, a series of driving operation amount approximation degrees Pids from the present time to the past predetermined time of the virtual driver and the actual driver are calculated, and based on the series approximation degree Pids, The lane change intention score Sc was calculated from (Equation 10). However, the present invention is not limited to this, and it is possible to estimate the driving intention by calculating the lane change intention score Sc based on the current driving operation amount approximation degree Pid of the virtual driver and the actual driver. is there.

  Further, instead of calculating the lane change intention likelihood score Sc, the lane maintenance intention likelihood score is calculated from the lane change intention likelihood Pr (LC) and the lane maintenance intention likelihood Pr (LK). It is also possible to estimate the lane keeping intention compared to the threshold. Furthermore, the driving intention of the virtual driver having the largest driving operation amount sequence approximation degree Pids can be estimated as the actual driving intention of the driver without calculating the score Sc.

  In the ninth and tenth embodiments described above, the risk potential RP is calculated using the margin time TTC and the inter-vehicle time THW between the host vehicle and the preceding vehicle. However, the present invention is not limited to this. For example, the reciprocal of the margin time TTC can be used as the risk potential. Further, the relationship between the risk potential RP and the reaction force increase amount ΔF is not limited to that shown in FIG. 26, and various maps in which the reaction force increase amount ΔF increases as the risk potential RP increases can be used. .

  In the ninth embodiment described above, the reaction force command value FA obtained by adding the reaction force increase amount ΔF corresponding to the risk potential RP to the normal reaction force characteristic is corrected and recorrected. However, the present invention is not limited to this. It is also possible to calculate the recorrection value FAcc of the reaction force command value FA by recorrecting the reaction force increase amount ΔF and adding it to the normal reaction force characteristic.

  In the first to eighth embodiments described above, the driving operation amount detection unit 10 functions as a driving operation amount detection unit, and the vehicle surrounding state detection unit 20 functions as a vehicle surrounding state detection unit and an obstacle detection unit. The virtual driver driving operation amount calculation unit 40 functions as virtual driver driving operation amount calculation means, the driving intention estimation unit 70 functions as driving intention estimation means, and the driving intention estimation reference variable setting unit 60 changes the driving intention estimation reference. The virtual driver driving operation amount correction unit 90 can function as a virtual driver driving operation amount correction unit. Further, the laser radar 110, the front camera 120, and the vehicle speed sensor 140 function as an obstacle detection unit, the risk potential calculation unit 151 functions as a risk potential calculation unit, and the accelerator pedal reaction force command value calculation units 152 and 155 operate. The accelerator pedal reaction force control device 170 can function as an operation reaction force generation unit. The accelerator pedal reaction force command value correction unit 152 and the risk potential correction unit 154 can function as a correction unit, specifically, an operation reaction force correction unit and a risk potential correction unit, respectively, but are not limited thereto. Another type of millimeter wave radar or the like may be used as the obstacle detection means. Further, as an operation reaction force generating means, a reaction force is generated in a vehicle operation device different from an accelerator pedal, for example, a steering reaction force control device that generates a steering reaction force in a steering device, or a joystick lever that outputs a drive command for a vehicle. It is also possible to use a device.

The system figure of the driving intention estimation apparatus by 1st Embodiment. (A)-(c) The figure which shows the example of the driving | running | working locus | trajectory of the own vehicle according to the driving | running | working condition of the preceding vehicle in the case of changing lanes. The flowchart which shows the process sequence of the driving intention estimation process in 1st Embodiment. The figure explaining the calculation method of the driving operation amount of a virtual driver. The figure explaining the calculation method of the driving operation amount series approximation degree of a virtual driver. The figure which shows the horizontal position in the lane of a preceding vehicle. The figure which shows the relationship between the horizontal position in a lane of a preceding vehicle, and a lane change intention estimation threshold value. The figure which shows the distance of the vehicle body edge part and lane edge of a preceding vehicle. The figure which shows the relationship between the distance of the vehicle body edge part and lane edge of a preceding vehicle, and a lane change intention estimation threshold value. The figure which shows the distance which added offset amount to the distance of the vehicle body edge part and lane edge of a preceding vehicle. The figure which shows the relationship between the vehicle width of a preceding vehicle, and offset amount. The figure which shows the relationship between the distance which added offset amount to the distance of the vehicle body edge part and lane edge of a preceding vehicle, and a lane change intention estimation threshold value. The figure which shows the distance between center positions of the own vehicle and a preceding vehicle. The figure which shows the relationship between the distance between center positions of the own vehicle and a preceding vehicle, and a lane change intention estimation threshold value. The figure which shows the outer end part distance of the own vehicle and a preceding vehicle. The figure which shows the relationship between the outer edge part distance of the own vehicle and a preceding vehicle, and a lane change intention estimation threshold value. The system figure of the driving intention estimation apparatus by 6th Embodiment. The flowchart which shows the process sequence of the driving intention estimation process in 6th Embodiment. The figure which shows the relationship between the horizontal position in a lane of a preceding vehicle, and the steering angle correction coefficient of a lane change intention model. The figure which shows the relationship between the distance of the vehicle body edge part and lane edge of a preceding vehicle, and the steering angle correction coefficient of a lane change intention model. The figure which shows the relationship between the distance which added offset amount to the distance of the vehicle body edge part and lane edge of a preceding vehicle, and the steering angle correction coefficient of a lane change intention model. The system figure of the driving operation assistance apparatus for vehicles by 9th Embodiment. The block diagram of the vehicle carrying the driving operation assistance apparatus for vehicles shown in FIG. The figure which shows the structure of an accelerator pedal and its periphery. The flowchart which shows the process sequence of the driving operation assistance control process in 9th Embodiment. The figure which shows the relationship between risk potential and reaction force increase amount. The figure which shows the relationship between the lane change intention estimation threshold value and the correction coefficient of an accelerator pedal reaction force command value. The system figure of the driving operation auxiliary device for vehicles by a 10th embodiment. The flowchart which shows the process sequence of the driving operation assistance control process in 10th Embodiment. The figure which shows the relationship between the lane change intention estimation threshold value and the correction coefficient of risk potential.

Explanation of symbols

1, 2: Driving intention estimation device 10: Driving operation amount detection unit 20: Vehicle ambient state detection unit 30: Vehicle state detection unit 40: Virtual driver driving operation amount calculation unit 50: Virtual driver driving operation amount approximation degree calculation unit 60: Driving intention estimation reference variable setting unit 70: Driving intention estimation unit 90: Virtual driver driving operation amount correction unit 100, 200: Vehicle driving operation assist device 150, 150A: Controller 170: Accelerator pedal reaction force control device

Claims (33)

Vehicle surrounding state detecting means for detecting the vehicle surrounding state of the host vehicle;
Driving operation amount detection means for detecting the driving operation amount by an actual driver;
For a plurality of different virtual drivers given a driving intention, based on the vehicle surrounding state detected by the vehicle surrounding state detecting means, a driving operation amount required for each virtual driver to perform the driving intention is calculated. A virtual driver operation amount calculation means for calculating;
The degree of approximation between the driving operation amount of the plurality of virtual drivers calculated by the virtual driver driving operation amount calculation means and the driving operation amount of the actual driver detected by the driving operation amount detection means (hereinafter, driving Driving amount approximation degree calculating means for calculating the respective operation amount approximation degrees),
Driving intention estimation means for estimating a driving intention of the actual driver based on the plurality of driving operation quantity approximation degrees calculated by the driving operation amount approximation degree calculation means;
Obstacle status detection means for detecting an obstacle status ahead of the host vehicle;
A driving intention estimation apparatus, comprising: a driving intention estimation reference changing unit that changes a driving intention estimation reference in the driving intention estimation unit based on the obstacle status detected by the obstacle status detection unit. In the driving intention estimation device according to claim 1,
The obstacle state detecting means detects the traveling state of a preceding vehicle ahead of the host vehicle as the obstacle state. In the driving intention estimation device according to claim 2,
The driving intention estimation reference changing means sets the driving intention estimation reference according to a lateral position in the lane of the preceding vehicle detected by the obstacle state detecting means. . In the driving intention estimation device according to claim 3,
The driving intention estimation reference changing means is configured to increase the lane change intention so that the estimated sensitivity of the lane change intention toward the lane edge direction increases as the lateral position of the preceding vehicle approaches the left or right lane edge. The driving intention estimation device according to claim 1, wherein the driving intention estimation criterion is reduced. In the driving intention estimation device according to claim 3 or 4,
The driving intention estimation reference changing means is configured to increase the estimation accuracy of a lane change intention in a direction opposite to the lane edge as the lateral position of the preceding vehicle approaches the lane edge on either side. A driving intention estimation device characterized in that the driving intention estimation reference for lane change intention is increased. In the driving intention estimation device according to claim 2,
The driving intention estimation reference changing means sets the driving intention estimation reference according to a distance between a vehicle body end portion and a lane edge in the lateral direction of the preceding vehicle detected by the obstacle state detecting means. Driving intention estimation device. In the driving intention estimation device according to claim 6,
The driving intention estimation reference changing unit is configured to increase the lane change intention so that the estimated sensitivity of the lane change intention toward the lane edge increases as the distance between the vehicle body end of the preceding vehicle and the lane edge decreases. The driving intention estimation device according to claim 1, wherein the driving intention estimation criterion is reduced. In the driving intention estimation device according to claim 6 or 7,
The driving intention estimation reference changing means is configured to increase the estimation accuracy of the lane change intention in the direction opposite to the lane edge as the distance between the vehicle body end of the preceding vehicle and the lane edge decreases. A driving intention estimation device characterized in that the driving intention estimation reference for lane change intention is increased. In the driving intention estimation device according to any one of claims 6 to 8,
The driving intention estimation reference changing means sets the driving intention estimation reference using a value corrected by adding a correction value to the distance between the vehicle body end of the preceding vehicle and the lane edge. Driving intention estimation device. In the driving intention estimation device according to claim 9,
The driving intention estimation device, wherein the correction value is set according to a vehicle width of the preceding vehicle. In the driving intention estimation device according to claim 10,
The driving intention estimation device according to claim 1, wherein the correction value is set so as to increase as the vehicle width of the preceding vehicle increases. In the driving intention estimation device according to claim 1,
The driving intention estimation reference changing means changes the driving intention estimation reference based on a preceding vehicle ahead of the host vehicle detected by the obstacle condition detecting unit and a lateral position in the lane of the host vehicle. A driving intention estimation device characterized by the above. In the driving intention estimation device according to claim 12,
The driving intention estimation reference changing means sets the driving intention estimation reference according to a distance between center positions between the lateral center position of the preceding vehicle and the lateral center position of the host vehicle. A driving intention estimation device characterized by the above. In the driving intention estimation device according to claim 13,
The driving intention estimation reference changing means increases the estimation sensitivity of the lane change intention in the direction in which the center position of the preceding vehicle exists with respect to the center position of the host vehicle as the distance between the center positions increases. As described above, the driving intention estimation device characterized by reducing the driving intention estimation reference regarding the lane change intention. In the driving intention estimation device according to claim 13 or claim 14,
The driving intention estimation reference variable setting means is adapted to change the lane in a direction opposite to the direction in which the center position of the preceding vehicle exists with respect to the center position of the host vehicle as the distance between the center positions increases. The driving intention estimation device characterized by increasing the driving intention estimation reference regarding the lane change intention so that the estimation accuracy becomes high. In the driving intention estimation device according to claim 12,
The driving intention estimation reference changing means is configured to estimate the driving intention according to an outer end distance between the lateral vehicle body outer end of the preceding vehicle and the lateral vehicle body outer end of the host vehicle. A driving intention estimation device characterized by setting a reference. The driving intention estimation device according to claim 16,
The driving intention estimation reference changing means changes the lane so that the greater the outer end distance is, the higher the estimation sensitivity of the intention to change the lane in the direction in which the preceding vehicle is offset with respect to the host vehicle. A driving intention estimation device characterized by reducing the driving intention estimation reference regarding intention. In the driving intention estimation device according to claim 16 or claim 17,
The driving intention estimation reference changing means increases the estimation accuracy of the intention to change the lane in the direction opposite to the direction in which the preceding vehicle is offset with respect to the host vehicle as the outer end distance increases. The driving intention estimation device characterized by increasing the driving intention estimation reference regarding the lane change intention. Vehicle surrounding state detecting means for detecting the vehicle surrounding state of the host vehicle;
Driving operation amount detection means for detecting the driving operation amount by an actual driver;
For a plurality of different virtual drivers given a driving intention, based on the vehicle surrounding state detected by the vehicle surrounding state detecting means, a driving operation amount required for each virtual driver to perform the driving intention is calculated. A virtual driver operation amount calculation means for calculating;
The degree of approximation between the driving operation amount of the plurality of virtual drivers calculated by the virtual driver driving operation amount calculation means and the driving operation amount of the actual driver detected by the driving operation amount detection means (hereinafter, driving Driving amount approximation degree calculating means for calculating the respective operation amount approximation degrees),
Driving intention estimation means for estimating a driving intention of the actual driver based on the plurality of driving operation quantity approximation degrees calculated by the driving operation amount approximation degree calculation means;
Obstacle status detection means for detecting an obstacle status ahead of the host vehicle;
Virtual driver driving operation amount correcting means for correcting the driving operation amount of the virtual driver calculated by the virtual driver driving operation amount calculating means based on the obstacle situation detected by the obstacle situation detecting means; A driving intention estimation device comprising: In the driving intention estimation device according to claim 19,
The obstacle state detecting means detects the traveling state of a preceding vehicle ahead of the host vehicle as the obstacle state. In the driving intention estimation device according to claim 20,
The virtual driver driving operation amount correcting means has detected a target position for calculating the driving operation amount of a virtual driver given a lane change intention among the plurality of virtual drivers detected by the obstacle state detecting means. A driving intention estimation device that corrects a driving operation amount of the virtual driver by changing the position according to a lateral position in a lane of the preceding vehicle. In the driving intention estimation device according to claim 21,
The virtual driver driving operation amount correcting means moves the target position of the lane change intention toward the lane end direction from the target position of the lane keeping intention as the lateral position of the preceding vehicle approaches the left or right lane edge. Driving intention estimation device characterized by being kept away. In the driving intention estimation device according to claim 21 or claim 22,
The virtual driver driving operation amount correcting means sets the target position of the lane change intention in the direction opposite to the lane end as the lane change intention becomes closer to the left or right lane end as the lateral position of the preceding vehicle approaches. A driving intention estimation device characterized by approaching a target position. In the driving intention estimation device according to claim 20,
The virtual driver driving operation amount correcting means has detected a target position for calculating the driving operation amount of a virtual driver given a lane change intention among the plurality of virtual drivers detected by the obstacle state detecting means. A driving intention estimation device that corrects a driving operation amount of the virtual driver by changing the distance according to a distance between a vehicle body end portion and a lane edge in a lateral direction of the preceding vehicle. In the driving intention estimation device according to claim 24,
The virtual driver driving operation amount correction means sets the target position using a value corrected by adding a correction value to the distance between the vehicle body end of the preceding vehicle and the lane edge. Driving intention estimation device. In the driving intention estimation device according to claim 20,
The virtual driver driving operation amount correcting means is intended to change the lane in the lane end direction as the lateral position in the lane of the preceding vehicle detected by the obstacle state detecting means approaches either left or right lane edge. Correction is performed so that the amount of driving operation of the virtual driver having a large value is increased, and correction is performed so that the amount of driving operation of the virtual driver having intention to change lanes in the direction opposite to the lane edge is decreased. A driving intention estimation device characterized by the above. In the driving intention estimation device according to claim 20,
The virtual driver driving operation amount correcting means has a lane change intention toward the lane end direction as the distance between the vehicle body end portion and the lane edge in the lateral direction of the preceding vehicle detected by the obstacle state detecting means decreases. Correction is performed so that the driving operation amount of the virtual driver is increased, and correction is performed so that the driving operation amount of the virtual driver having the intention to change the lane in the direction opposite to the lane edge is decreased. A driving intention estimation device characterized by the above. In the driving intention estimation device according to claim 27,
The virtual driver driving operation amount correction means corrects the driving operation amount of the virtual driver using a value corrected by adding a correction value to the distance between the vehicle body end portion and the lane edge of the preceding vehicle. A driving intention estimation device characterized by the above. The driving intention estimation device according to any one of claims 1 to 18,
Obstacle detection means for detecting obstacle conditions around the vehicle;
Risk potential calculation means for calculating a risk potential around the host vehicle based on a detection result by the obstacle detection means;
Based on the risk potential calculated by the risk potential calculation means, an operation reaction force calculation means for calculating an operation reaction force generated in an accelerator pedal;
An operation reaction force generation means for causing the accelerator pedal to generate the operation reaction force calculated by the operation reaction force calculation means;
Correction for correcting the operation reaction force generated in the accelerator pedal based on the driving intention estimation result by the driving intention estimation means and the driving intention estimation reference set by the driving intention estimation reference variable setting means. A vehicle driving operation assisting device. The vehicular driving operation assistance device according to claim 29,
The correction means is an operation reaction force correction means for correcting a relationship between the risk potential and the operation reaction force,
When the driving intention estimating means estimates that the driving intention is a lane change, the operating reaction force correcting means reduces the operating reaction force compared to a case where the driving intention is estimated to be other than a lane change. In addition, the vehicle driving operation assistance device is characterized in that when the driving intention estimation criterion relating to the lane change is large, the operation reaction force is decreased as compared with a case where the driving intention estimation criterion is small. The vehicular driving operation assistance device according to claim 29,
The correction means is a risk potential correction means for correcting a relationship between the risk potential and the operation reaction force,
When the driving intention estimation unit estimates that the driving intention is a lane change, the risk potential correction unit lowers the risk potential compared to a case where the driving intention is estimated to be other than a lane change. In addition, when the driving intention estimation criterion related to the lane change is large, the risk potential is lowered as compared with the case where the driving intention estimation criterion is small. A driving intention estimation device according to any one of claims 19 to 28;
Obstacle detection means for detecting obstacle conditions around the vehicle;
Risk potential calculation means for calculating a risk potential around the host vehicle based on a detection result by the obstacle detection means;
Based on the risk potential calculated by the risk potential calculation means, an operation reaction force calculation means for calculating an operation reaction force generated in an accelerator pedal;
An operation reaction force generation means for causing the accelerator pedal to generate the operation reaction force calculated by the operation reaction force calculation means;
Correction for correcting the operation reaction force generated in the accelerator pedal based on the driving intention estimation result by the driving intention estimation means and the driving intention estimation reference set by the driving intention estimation reference variable setting means. A vehicle driving operation assisting device.   A vehicle comprising the vehicular driving assist device according to any one of claims 29 to 32.

Images