JP2019211830A - Lane change estimation device and lane change estimation method, and vehicle control device and vehicle control method - Google Patents

Abstract

To provide a lane change estimation device and a lane change estimation method capable of highly accurately estimating a lane change of an object vehicle at an early stage, and to provide a vehicle control device and a vehicle control method using an estimation result.SOLUTION: A control unit of a vehicle VCestimates whether or not a vehicle VCtraveling on an adjacent lane Ln2 is to change a lane with respect to an inter-vehicle area Ar on a front side of an own lane Ln1 on the basis of relative distances and relative speeds of vehicles VC, VC, VC, VCtraveling in the periphery. A potential feature quantity is calculated based on an inter-lane potential value ratio that is the ratio of risk potential of the own lane Ln1 to be calculated by risk potential Uof the own vehicle VCand risk potential Uof the vehicle VCto risk potential of the adjacent lane Ln2 to be calculated by risk potential Uof the vehicle VCand risk potential Uof the vehicle VC. Estimation of a lane change of the vehicle VCis performed based on the potential feature quantity.SELECTED DRAWING: Figure 7

Description

  The present invention relates to a lane change estimation device, a lane change estimation method, a vehicle control device, and a vehicle control method.

  Some vehicles, such as automobiles, are provided with a device for controlling the vehicle without depending on the actual operation of the driver, such as auto cruise control. In such a control device, a vehicle traveling around the host vehicle and a traveling environment including a traveling lane are detected, and the vehicle is controlled based on the detection result.

  Patent Document 1 discloses a method for estimating whether or not a vehicle traveling in a lane adjacent to a lane in which the host vehicle travels changes lanes. In Patent Document 1, a vehicle having a relatively low speed is traveling ahead of an estimation target vehicle traveling in an adjacent lane, and whether or not the estimation target vehicle changes lanes in order to pass the preceding vehicle. A technique for estimating the above is disclosed.

JP 2003-228800 A

  However, in the technique disclosed in Patent Document 1, since it is estimated whether or not the lane change is performed only by the relative speed between the estimation target vehicle that estimates the lane change and the vehicle that travels in front of the estimation target vehicle. It is difficult to estimate whether the estimation target vehicle changes lanes with high accuracy.

  If the vehicle is controlled using the result obtained by the method disclosed in Patent Document 1, the vehicle is controlled based on the estimation result with low accuracy, which is large for the driver. It is thought to cause stress.

  The present invention has been made to solve the above-described problems, and is a lane change estimation device and a lane change estimation method capable of estimating a lane change of a target vehicle at an early stage and with high accuracy, and the estimation An object is to provide a vehicle control device and a vehicle control method using the result.

  A lane change estimation apparatus according to an aspect of the present invention is a lane change estimation apparatus that estimates a lane change of a vehicle that travels around a host vehicle, the host vehicle traveling by the host vehicle, and the host vehicle lane. A lane detector that detects adjacent lanes; a vehicle in front of the host vehicle that travels in front of the host vehicle in the host lane; a target vehicle that travels in the adjacent lane and is the target of estimation of the lane change; A speed / distance detection unit that detects a speed and a distance between each of the adjacent lane front vehicle traveling in front of the target vehicle and the adjacent lane rear vehicle traveling behind the target vehicle; and the speed A lane change estimator that receives the detection result from the distance detector and estimates a lane change of the target vehicle, the lane change estimator relative to the vehicle and the vehicle ahead of the lane Speed and relative distance Based on the relative speed and relative distance between the target vehicle and the vehicle ahead of the adjacent lane, and the relative speed and relative distance between the target vehicle and the vehicle behind the adjacent lane, the lane change of the target vehicle is estimated. .

  In the lane change estimation device according to the above aspect, the lane change of the target vehicle is estimated based on the relative speed and the relative distance between the vehicles before the target vehicle starts the lane change. Lane change estimation (estimation of whether or not the target vehicle changes lanes) can be performed at an earlier time point before the change is started, and driving support with smooth control can be performed.

  In the lane change estimation apparatus according to the above aspect, the relative speed and relative distance between the host vehicle and the vehicle ahead of the host lane, the relative speed and relative distance between the target vehicle and the vehicle ahead of the adjacent lane, and the rear of the target vehicle and the adjacent lane. Since the estimation of the lane change of the target vehicle is executed based on the relative speed and the relative distance with the vehicle, the technique of Patent Document 1 for estimating the lane change based on the relative speed between the target vehicle and the vehicle ahead thereof. Compared to, it is possible to estimate the lane change of the target vehicle with high accuracy.

  In the lane change estimation apparatus according to the above aspect, the lane change estimation unit is configured to determine a risk potential of the host vehicle based on the relative speed and the relative distance between the host vehicle and the host vehicle ahead of the host vehicle, and the front of the host vehicle lane. A risk potential of the vehicle, and a risk potential in the own lane is set based on the risk potential, and the adjacent lane is determined based on the relative speed and the relative distance between the target vehicle and the vehicle ahead of the adjacent lane. Set the risk potential of the vehicle ahead and set the risk potential of the vehicle behind the adjacent lane based on the relative speed and the relative distance between the target vehicle and the vehicle behind the adjacent lane, and based on the risk potential Set the risk potential in the adjacent lane, the risk potential value in the own lane and the adjacent vehicle In addition, the ratio of the risk potential to the value of the vehicle may be calculated, the potential feature quantity based on the ratio may be calculated, and the lane change of the target vehicle may be estimated based on the potential feature quantity value. .

  In the case of adopting the above configuration, each risk potential between the vehicles existing before and after is set, the risk potential of the own lane and the risk potential of the adjacent lane are calculated from each risk potential, and the risk potential of those lanes is calculated. The lane change is estimated based on the potential feature amount calculated from the ratio (the potential value ratio between lanes). Therefore, the lane change estimation apparatus according to the above aspect can estimate the lane change at an early stage and with high accuracy.

  In addition, as for the risk potential in the above, the height of the top increases as the speed of the vehicle increases.

  In the lane change estimation apparatus according to the aspect described above, the lane change estimation unit weights between the risk potential of the host vehicle and the risk potential of the vehicle ahead of the host lane when setting the risk potential in the host lane. In setting the risk potential in the adjacent lane, weighting may be performed between the risk potential of the vehicle ahead of the adjacent lane and the risk potential of the vehicle behind the adjacent lane.

  In the case of adopting the above configuration, the risk potential of each vehicle is weighted when calculating the risk potential of the own lane and the adjacent lane. Thereby, in the lane change estimation apparatus according to the above aspect, the risk potential in each lane can be calculated more accurately.

  For weighting, weights obtained experimentally or empirically can be used.

  In the lane change estimation device according to the above aspect, the risk potential of the host vehicle is biased toward the vehicle ahead of the host lane when the relative speed of the host vehicle with respect to the vehicle ahead of the host lane is positive. The risk potential of the vehicle ahead of the own lane is set in a state of being biased toward the front side opposite to the own vehicle when the relative speed of the vehicle ahead of the own lane with respect to the own vehicle is positive. The risk potential of the vehicle ahead of the adjacent lane is set in a state biased toward the front side opposite to the target vehicle when the relative speed of the vehicle ahead of the adjacent lane with respect to the target vehicle is positive, The risk potential of the vehicle behind the adjacent lane is set in a state of being biased toward the target vehicle when the relative speed of the vehicle behind the adjacent lane with respect to the target vehicle is positive. It can also be.

  In the case of adopting the above configuration, when the relative speed is positive with respect to the vehicle traveling forward (the state approaching the vehicle traveling forward), the front vehicle side is more than the rear side. However, since the risk potential is set in a state biased to the front side because the risk is high, the risk potential can be set more accurately.

  In the lane change estimation apparatus according to the aspect described above, the risk potential of the host vehicle is such that the relative speed of the host vehicle with respect to the host vehicle ahead of the host vehicle is biased toward the rear side opposite to the host vehicle ahead of the host lane. The risk potential of the vehicle ahead of the own lane is set in a state of being biased toward the own vehicle when the relative speed of the vehicle ahead of the own lane with respect to the own vehicle is negative, The risk potential of the vehicle is set in a state of being biased toward the target vehicle when the relative speed of the vehicle ahead of the adjacent lane with respect to the target vehicle is negative, and the risk potential of the vehicle behind the adjacent lane is When the relative speed of the vehicle behind the adjacent lane with respect to the target vehicle is negative, it may be set in a state of being biased toward the rear side opposite to the target vehicle.

  In the case of adopting the above configuration, when the relative speed is negative with respect to the vehicle traveling in the front (a state separated from the vehicle traveling in the front), the front vehicle side is more than the rear side. However, assuming that the risk is low, the risk potential is set in a state biased to the rear side, so the risk potential can be set more accurately.

  A vehicle control device according to an aspect of the present invention is a vehicle control device that controls a vehicle, and the target vehicle estimated by the lane change estimation device according to any one of the above aspects and the lane change estimation device And a vehicle control unit that controls at least one of the vehicle speed and the inter-vehicle distance based on the estimation result of the lane change.

  The vehicle control device according to the above aspect controls at least one of the speed of the vehicle (own vehicle) and the inter-vehicle distance based on the result (lane change estimation result) estimated by the lane change estimation device according to each of the above aspects. Therefore, smooth driving is possible while ensuring high safety.

  A lane change estimation method according to an aspect of the present invention is a lane change estimation method for estimating a lane change of a vehicle traveling around a host vehicle, the host vehicle traveling on the host vehicle, and the host vehicle A lane detection step for detecting adjacent lanes; a vehicle in front of the own lane in front of the host vehicle in the lane; a target vehicle that travels in the adjacent lane and is subject to estimation of the lane change; A speed / distance detection step for detecting a speed and a distance between the adjacent lane front vehicle traveling in front of the target vehicle and the adjacent lane rear vehicle traveling behind the target vehicle; and the speed A lane change estimation step for receiving a result of the detection from the distance detection unit and estimating a lane change of the target vehicle, wherein in the lane change estimation step, the host vehicle and the host vehicle ahead Based on the relative speed and relative distance, the relative speed and relative distance between the target vehicle and the vehicle ahead of the adjacent lane, and the relative speed and relative distance between the target vehicle and the vehicle behind the adjacent lane, Perform lane change estimation.

  In the lane change estimation method according to the above aspect, the lane change estimation step estimates the lane change of the target vehicle based on the relative speed and the relative distance between the vehicles before the target vehicle starts the lane change. The lane change can be estimated at an earlier time point before the target vehicle actually starts the lane change, and driving support with smooth control can be performed.

  Further, in the lane change estimation method according to the above aspect, in the lane change estimation step, a relative speed and a relative distance between the host vehicle and the own lane front vehicle, a relative speed and a relative distance between the target vehicle and the adjacent lane front vehicle, Since the lane change of the target vehicle is estimated based on the relative speed and the relative distance between the target vehicle and the vehicle behind the adjacent lane, the lane change is estimated based on the relative speed between the target vehicle and the vehicle ahead of the target vehicle. Compared with the technique of the above-mentioned patent document 1, it is possible to estimate the lane change of the target vehicle with high accuracy.

  In the lane change estimation method according to the above aspect, the lane change estimation step includes the risk potential of the host vehicle and the front of the host lane based on the relative speed and the relative distance between the host vehicle and the host vehicle ahead. Vehicle risk potential, and a self-lane risk potential setting substep for setting a risk potential in the own lane based on the risk potential, the relative speed between the target vehicle and the vehicle ahead of the adjacent lane, and the Based on the relative distance, the risk potential of the vehicle ahead of the adjacent lane is set, and the risk potential of the vehicle behind the adjacent lane is set based on the relative speed and the relative distance between the target vehicle and the vehicle behind the adjacent lane. Based on these risk potentials, the risk potential in the adjacent lane is set. The adjacent lane risk potential setting sub-step, the risk potential value ratio calculation sub-step for calculating the ratio of the risk potential value in the own lane and the risk potential value in the adjacent lane, and the risk potential value ratio A potential feature quantity calculation sub-step for calculating a potential feature quantity based on the lane change estimation sub-step for estimating a lane change of the target vehicle based on the value of the potential feature quantity.

  When the above method is adopted, the potential feature amount is calculated through the own lane risk potential setting sub-step, the adjacent lane risk potential setting sub-step, the risk potential value ratio calculation sub-step, and the potential feature amount calculation sub-step. In the change estimation sub-step, the estimation of the lane change is executed based on the potential feature quantity. Therefore, in the lane change estimation method according to the above aspect, it is possible to estimate the lane change at an early stage and with high accuracy.

  In the lane change estimation method according to the above aspect, in the own lane risk potential setting sub-step, weighting is performed between the risk potential of the own vehicle and the risk potential of the vehicle ahead of the own lane, and the adjacent lane risk potential setting is performed. In the sub-step, weighting is performed between the risk potential of the vehicle ahead of the adjacent lane and the risk potential of the vehicle behind the adjacent lane.

  In the case of adopting the above method, in the own lane risk potential setting sub-step and the adjacent lane risk potential setting sub-step, the risk potential of each vehicle is weighted when calculating the risk potential of the own lane and the adjacent lane. To do. Thereby, in the lane change estimation method according to the above aspect, the risk potential in each lane can be calculated more accurately.

  In the lane change estimation method according to the above aspect, in the own lane risk potential setting sub-step, when the relative speed of the own vehicle with respect to the own lane front vehicle is positive, the lane change estimation method is biased toward the lane front vehicle side. In the state, the risk potential of the host vehicle is set, and when the relative speed of the host vehicle ahead of the host vehicle with respect to the host vehicle is positive, in a state biased toward the front side opposite to the host vehicle, The risk potential of the vehicle in front of the own lane is set, and in the substep for setting the potential potential of the adjacent lane, when the relative speed of the vehicle in front of the adjacent lane with respect to the target vehicle is positive, the front on the side opposite to the target vehicle The risk potential of the vehicle ahead of the adjacent lane is set in a state biased to the side, and the relative speed of the vehicle behind the adjacent lane with respect to the target vehicle is set. There when is positive, a state biased to the side of the subject vehicle, sets the risk potential of the adjacent lane following vehicle, and can be.

  When the above method is adopted, if the relative speed is positive with respect to the vehicle traveling in the front lane risk potential setting sub-step and the adjacent lane risk potential setting sub-step (approaching to the vehicle traveling in front). In this state, the risk potential is set in a state biased to the front side, assuming that the risk is higher on the front vehicle side than on the rear side, so that the risk potential can be set more accurately.

  In the lane change estimation method according to the above aspect, in the own lane risk potential setting substep, when the relative speed of the own vehicle with respect to the own lane front vehicle is negative, the rear side opposite to the own lane front vehicle When the risk potential of the host vehicle is set in a state biased to the side, and when the relative speed of the vehicle ahead of the host lane with respect to the host vehicle is negative, in a state biased to the side of the host vehicle, The risk potential of the vehicle ahead of the own lane is set, and in the adjacent lane risk potential setting sub-step, when the relative speed of the vehicle ahead of the adjacent lane with respect to the target vehicle is negative, the vehicle is biased toward the target vehicle When the risk potential of the vehicle ahead of the adjacent lane is set in the state and the relative speed of the vehicle behind the adjacent lane with respect to the target vehicle is negative In, said subject vehicle in a state biased to the opposite rear side, to set the risk potential of the adjacent lane following vehicle, and can be.

  When the above method is adopted, if the relative speed is negative with respect to the vehicle traveling in the front lane risk potential setting sub-step and the adjacent lane risk potential setting sub-step (separate from the vehicle traveling in the front) In this state, the risk potential is set in a state of being biased to the rear side assuming that the risk of the vehicle ahead is lower than that of the rear side, so that the risk potential can be set more accurately.

  A vehicle control method according to an aspect of the present invention is a vehicle control method for controlling a vehicle, wherein the lane change estimation method according to any one of claims 7 to 11 is executed, and the lane change estimation method is executed. Based on the estimated estimation result of the lane change of the target vehicle, at least one of the speed of the vehicle and the inter-vehicle distance is controlled.

  The vehicle control method according to the aspect described above is based on the result (lane change estimation result) estimated by the execution of the lane change estimation step of the lane change estimation method according to each aspect described above, and the speed of the vehicle (own vehicle) and the inter-vehicle distance. Since at least one of the distances is controlled, smooth running is possible while ensuring high safety.

  In each of the above aspects, it is possible to estimate the lane change of the target vehicle at an early stage and with high accuracy.

It is a mimetic diagram showing a schematic structure of a vehicle concerning an embodiment. It is a block diagram which shows the control structure of a vehicle. It is a schematic diagram which shows the detection range by a radar, a laser sensor, and a vehicle exterior camera. It is a schematic diagram which shows the driving | running | working state in the predetermined time of the own vehicle and a surrounding vehicle. It is a schematic diagram for demonstrating a risk potential. (A) is a schematic diagram showing the risk potential when there is almost no speed difference between the front and rear vehicles, (b) is a case where there is a speed difference between the front vehicle and the rear vehicle. It is a schematic diagram which shows a risk potential. It is a schematic diagram which shows the dynamic relationship between the own vehicle and surrounding vehicles, applying a risk potential. It is a characteristic view which shows the relationship between the potential value ratio between lanes, and a potential feature-value. It is a flowchart which shows the lane change estimation method which a control unit performs. (A) is a schematic diagram explaining the determination method of step S6 in the flowchart of FIG. 9, (b) is a characteristic diagram used for the determination method which an estimator performs. It is a flowchart which shows the vehicle control method which a control unit performs using a lane change estimation result.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In addition, the form demonstrated below is an example of this invention, Comprising: This invention is not limited to the following forms at all except the essential structure.

[Embodiment]
1. Schematic Configuration of Vehicle 1 A schematic configuration of the vehicle 1 according to the present embodiment will be described with reference to FIGS. 1 and 2.

  As shown in FIG. 1, the vehicle 1 includes an engine 10 as a power source. In the vehicle 1 according to the present embodiment, a multi-cylinder gasoline engine is employed as an example of the engine 10.

  A transmission 13 is connected to the engine 10, and a drive shaft 11 is provided so as to extend from the transmission 13 in the left-right direction. Left and right front wheels 12 l and 12 r are attached to the end of the drive shaft 13.

  A differential gear (not shown) is interposed between the transmission 13 and the drive shaft 11.

  On the rear side of the vehicle 1, left and right rear wheels 14 l and 14 r are arranged. Each of the left and right rear wheels 14l and 14r is attached to a rear arm (not shown).

  As shown in FIG. 1, an accelerator pedal 15 and a brake pedal 16 are provided at the foot portion of the driver's seat in the passenger compartment of the vehicle 1. The accelerator pedal 15 increases or decreases the rotational speed of the engine 10 according to the amount of depression by the driver, and the brake pedal 16 operates brakes attached to the front wheels 12l and 12r and the rear wheels 14l and 14r by depression by the driver. Let

  The vehicle 1 is provided with three radars 17, 18, 19, a vehicle exterior camera 20, and a laser sensor 21. Of the three radars 17, 18, and 19, the radar 17 is disposed in the front portion of the vehicle 1, and the remaining two radars 18 and 19 are disposed on the side portion of the vehicle 1. These radars 17, 18, and 19 have functions of detecting a vehicle around the host vehicle (vehicle 1) and detecting a relative speed and a relative distance between the vehicle 1 and the surrounding vehicle.

  The exterior camera 20 and the laser sensor 21 are also provided for detecting surrounding vehicles and detecting the relative speed and the relative distance, like the radars 17, 18, and 19.

  Further, the vehicle 1 is provided with a map information storage unit 22 and a vehicle-vehicle communication unit 23. The map information storage unit 22 stores information related to the road on which the vehicle 1 travels. The map information stored in the map information storage unit 22 includes lane information on the road.

  The vehicle-to-vehicle communication unit 23 is a unit that sequentially communicates between the host vehicle (vehicle 1) and surrounding vehicles, and can acquire speed information, position information, and the like of surrounding vehicles, for example. .

  Further, the vehicle 1 is also provided with a control unit 24. As shown in FIGS. 1 and 2, the control unit 24 is connected to the radars 17, 18, 19, the vehicle exterior camera 20, the laser sensor 21, the map information storage unit 22, the vehicle-vehicle communication unit 23, and the like. It is configured to accept various information.

  The control unit 24 includes a microprocessor including a CPU, a ROM, a RAM, and the like, and is connected to the engine 10, the accelerator pedal 15, the brake pedal 16, and the like. Based on the above various information. Control of the engine 10 is executed. That is, in the vehicle 1 according to the present embodiment, the control unit 24 has a function as a vehicle control device.

  Note that the control unit 24 can output a command related to a reaction force to the driver to the accelerator pedal 15. Similarly, the control unit 24 can output a command for driving the brake pedal 16 as needed even when there is no stepping operation by the driver.

2. Detection Range by Radars 17, 18, 19, Outside Camera 20 and Laser Sensor 21 The detection range by radars 17, 18, 19, outside camera 20, and laser sensor 21 will be described with reference to FIG. FIG. 3 is a schematic diagram showing detection ranges by the radars 17, 18, 19, the vehicle exterior camera 20, and the laser sensor 21 in a state where the vehicle 1 is viewed from above.

As shown in FIG. 3, the radar 17 provided at the front portion of the vehicle 1 can detect a vehicle or the like in a range θ ₁₇ on the front side of the vehicle 1. The radar 18 provided on the left part of the vehicle 1 can detect vehicles in the range θ ₁₈ on the left side of the vehicle 1. The radar 19 provided on the right side of the vehicle 1 can detect vehicles in the range θ ₁₉ on the right side of the vehicle 1.

The vehicle exterior camera 20 is provided on the vehicle interior side of the front windshield of the vehicle 1, and can detect a vehicle or the like in the range θ ₂₀ on the front side of the vehicle 1. Further, the outside-vehicle camera 20 can detect a lane in which the vehicle 1 travels and an adjacent lane.

The laser sensor 21 is, for example, an infrared laser sensor, and can detect a vehicle or the like in an omnidirectional range θ ₂₁ around the vehicle 1.

  In the vehicle 1, the results detected by the radars 17, 18, 19, the outside camera 20, and the laser sensor 21 are input to the control unit 24. The relative speed and relative distance between the vehicle traveling around and the vehicle 1 can be calculated.

3. Lane Change Estimation Method A lane change estimation method executed by the control unit 24 in the vehicle 1 will be described with reference to FIGS.

(1) vehicle VC _R and around the vehicle _{VC T, VC P, VC F} , the running condition of VC _L First, the vehicle VC _R is the vehicle, the vehicle _VC T _{therearound, VC P, VC F, VC} L The traveling situation will be described with reference to FIG.

As shown in FIG. 4, vehicle VC _R is toward the traveling direction (toward the right in FIG. 4) is traveling in the right lane Ln1. Hereinafter, the vehicle VC _R described as "vehicle VC _R", the lane Ln1 may be referred to as "own vehicle lane Ln1". The own lane Ln1 the vehicle VC _L ahead of the vehicle VC _R is traveling. The vehicle VC _L corresponds to “own vehicle ahead vehicle”.

In the present embodiment, between the vehicle VC _R and the vehicle VC _L, it is empty vehicle region Ar. The inter-vehicle area Ar is assumed to be an area large enough for the vehicle to interrupt.

A lane Ln2 adjacent to the own lane Ln1 is provided on the left side (upper side in FIG. 4) with respect to the own lane Ln1. Hereinafter, the lane Ln2 is referred to as “adjacent lane Ln2”. The next lane Ln2, a vehicle traveling around the vehicle VC _R, and the vehicle VC _T, and the vehicle VC _P, and the vehicle VC _P exists.

Vehicle VC _T, then control unit 24 of the vehicle VC _R is a vehicle for the estimation target lane change corresponds to the "target vehicle". Vehicle VC _P, in the adjacent lane Ln2, a vehicle traveling ahead of the subject vehicle VCT, corresponds to the "next lane ahead the vehicle." The vehicle VC _F is a vehicle that travels behind the target vehicle VC _T in the adjacent lane Ln2, and corresponds to the “adjacent lane rear vehicle”.

Vehicle VC _R is traveling at a speed _{v R,} the vehicle VC _L is traveling at a speed _v higher than _R velocity _{v L.} Headway between the vehicle VC _R and the vehicle VC _L is the distance _{r RL.}

Target vehicle VC _T is traveling at a speed _{v T,} the vehicle VC _P is traveling at a low speed _{v P} than the speed _{v T,} the vehicle VC _F is at a high velocity _{v F} than the speed _{v T} It is running.

Vehicle to the target vehicle VC _T and the vehicle VC _P is a distance _{r TP,} headway between the vehicle VC _F and the target vehicle VC _T is the distance _{r FT.}

(2) Setting risk potential Ui Next, the vehicle VC _R and around the vehicle _{VC T, VC P, VC F} , how to set the risk potential Ui to VC _L, will be described with reference to FIGS. 5 to 7 .

(I) Definition of Risk Potential As shown in FIG. 5, when an own object (corresponding to the own vehicle) and an obstacle (corresponding to the surrounding vehicle) are arranged apart by a distance r, the risk potential is It is defined as:

  In (Equation 1), “σ” represents the variation of the distance r.

  Next, when setting a risk potential for a running vehicle as shown in FIG. 4, a risk potential (artificial risk potential) for expressing a dynamic relationship between vehicles is defined as follows: The

Note that in equation (2), "θi" in a plan view from above, the vehicle VC with respect to the reference line oriented in the traveling direction of the _R, the vehicle VC the center and the periphery of the _R vehicle _VC T, VC _P , VC _F , VC _L are angles formed by imaginary lines connecting the centers.

  As defined in (Equation 2), the risk potential has a higher peak as the vehicle speed of the vehicle for which the risk potential is set is higher.

  Moreover, it is set in a state biased forward or backward depending on whether the relative speed between the front and rear vehicles is positive or negative. That is, as shown in FIG. 6A, when two vehicles are traveling at the same speed v1, the risk potential U1 is set in a state in which there is no bias in the front-rear direction.

  On the other hand, as shown in FIG. 6B, when the vehicle traveling in the front travels at the speed v1 and the vehicle traveling in the rear travels at the speed v2 higher than the speed v1, the risk potential U2 is increased to the front side. Set in a biased state. Further, since the speed v2 is higher than the speed v1, the risk potential U2 is set to have a higher peak than the risk potential U1.

  In addition, although illustration is abbreviate | omitted about the case where the speed of the vehicle which drive | works back is lower than the speed of the vehicle which drive | works ahead, it is to the back side opposite to what is shown in FIG.6 (b). Risk potential is set in a biased state.

(Ii) Setting of Risk Potential Ui in Embodiment Setting of risk potential in the situation shown in FIG. 4 will be described with reference to FIG. The vehicle speeds of the vehicles VC _R , VC _T , VC _P , VC _F , VC _L , the inter-vehicle distance between them, and the like are as described above.

As shown in FIG. 7, for the vehicle VC _R, risk potential U _R state biased to the rear side is set, the vehicle VC for the _L, the risk potential U _L state biased to the front side Is set. Such risk potential U _R, bias U _L, as described above, is due to the relative velocity.

For vehicle VC _P running ahead of the target vehicle VC _T, risk potential U _P state biased to the rear side is set, for the vehicle VC _F for traveling behind the target vehicle VC _T, forward risk potential U _F state biased to the side is set. The bias is due to the same reason as described above.

(3) Lane risk potential _U C, the _{U N} Configuration Next, set the risk potential _U P as described _above, U _F, U C, from _{U N,} risk potential _U C performed for each lane, the _{U N} The setting will be described.

Risk potential _{U C} of the adjacent lane Ln2 is defined by the following equation.

In the above equation (3), "omega _C" and "1-omega _C 'are coefficients for performing weighting to each risk potential U _P and risk potential U _F.

Incidentally, in setting the risk potential U _C of the adjacent lane Ln2 can employ the weights determined experimentally or empirically.

Risk potential _{U N} of the own lane Ln1 is defined by the following equation.

In the equation (4), "omega _N" and "1-omega _N" is a coefficient for performing weighting to each risk potential U _L and the risk potential U _R, defined experimentally or empirically The

(4) Calculation of inter-lane potential value ratio and calculation of potential feature quantity The inter-lane potential value ratio z is calculated using the risk potentials U _C and U _N for each lane set as described above. The lane potential value ratio z is defined as follows.

  Next, the potential feature amount P is calculated using the inter-lane potential value ratio z obtained above. The potential feature amount P is defined by the following equation.

  Note that the function “φ” in (Expression 6) is a cumulative distribution function assigned experimentally and empirically (by learning), and is defined by the traveling environment of the vehicle.

(5) using the potential characteristic amount P of the estimated calculated in the lane change, whether or not the estimated change lanes to the target vehicle VC _T inter-vehicle region Ar. Specifically, as shown in FIG. 8, when the potential characteristic quantity P is greater than the determination threshold value P1 is presumed target vehicle VC _T comes to change lanes against vehicle region Ar of the own lane Ln1 .

Conversely, the potential characteristic amount P is in the following cases determination threshold P1, the target vehicle VC _T is presumed not come to change lanes against vehicle region Ar of the own lane Ln1.

(6) Summary of Lane Change Estimation Method Summary and supplement of the above lane change estimation method will be described with reference to FIGS.

As shown in FIG. 9, the control unit 24 having a function as a lane change estimating unit includes radars 17, 18, 19, a camera 20 outside the vehicle, a laser sensor 21, a map information storage unit 22, and a vehicle-vehicle communication unit 23. Various data are acquired from the above (step S1). The data (information) to be acquired includes information related to surrounding vehicles VC _T , VC _P , VC _F , VC _L and information related to lanes Ln 1, Ln 2.

Next, the control unit 24 determines the target vehicle related to the estimation of the lane change (step S2). In the present embodiment, the vehicle VC _T which is traveling in the adjacent lane Ln2 is the target vehicle. Then, the control unit 24 is calculated based on the equation (2), each vehicle _{VC R, VC P, VC F} , sets the risk potential Ui of VC _L, lane with their potential _U C, a _{U N} (Step S3). As described above, weighting is performed when calculating the lane potentials U _C and U _N.

  Next, the control unit 24 calculates the lane potential value ratio z based on the above (Equation 5) (Step S4), and calculates the potential feature amount P based on the above (Equation 6) (Step S5).

Next, as described with reference to FIG. 8, the control unit 24 determines whether or not the potential feature amount P is larger than the determination threshold value P1 (step S6). : Yes), the target vehicle VC _T is estimated to change lanes (step S7). On the other hand, the control unit 24, is determined in step S6, if it is determined that "No" is the target vehicle VC _T is estimated not to change lanes (step S8).

Here, as shown in FIG. 10 (a), the target vehicle VC _T is the estimation of whether or not to change the lane, the estimator is used. The estimator, potential feature amount, receives an input, such as horizontal position and horizontal speed of the target vehicle VC _T, and outputs the determination result by the machine learning.

Examples of machine learning in the estimator, as shown in FIG. 10 (b), takes a lateral position of the target vehicle VC _T on the horizontal axis, the characteristic view taken potential characteristic quantity on the vertical axis, the threshold when the potential feature quantity input above the straight line is located, when the target vehicle VC _T is estimated to change lanes, the potential feature quantity input below the straight line becomes threshold is located, target vehicle VC _T is estimated not to change lanes.

4). Control Method of Vehicle 1 A control method of the vehicle 1 using the lane change estimation result as described above will be described with reference to FIG. FIG. 11 is a flowchart showing a control method of the vehicle 1 performed by the control unit 24 having a function as a vehicle control unit using the lane change estimation result.

  As shown in FIG. 11, the control unit 24 acquires the result estimated above (step S11), and predicts the positions of surrounding vehicles (step S12). Since the control unit 24 also has a function as a lane change estimating unit, the execution of step S11 is an internal data exchange.

Next, the control unit 24, a prediction result of the estimation result and around the vehicle position, to assess the risk of surroundings of the vehicle VC _R (step S13). For example, when the target vehicle VC _T is predicted to come interrupting the vehicle region Ar is, in consideration of such inter-vehicle distance and the relative velocity after the interruption, the risk assessment is made.

Next, the control unit 24, for inter-vehicle distance between the speed and the vehicle ahead of the host vehicle VC _R (target vehicle VC T that is estimated to interrupt forward by lane _change), and sets the candidate condition (step S14). Then, the control unit 24 evaluates the risk of the condition set in step S14 (step S15), corrects the speed and the inter-vehicle distance based on the evaluation result (step S16), and then the corrected condition. Is determined to be optimal (step S17).

  The control unit 24 repeats the execution of step S15 and step S16 until it is determined to be optimal in the determination of step S17 (step S17: No). Then, if the control unit 24 determines that it is optimal in the determination in step S17 (step S17: Yes), it instructs the engine 10 or the like to realize the final speed and the inter-vehicle distance.

[Modification]
In the vehicle 1 according to the above-described embodiment, in order to detect the position, speed, lane, and the like of surrounding vehicles, three radars 17, 18, 19, an outside camera 20, a laser sensor 21, a map information storage unit 22, and Although the vehicle-to-vehicle communication unit 23 is provided, the present invention is not limited to this. For example, at least one of the three radars 17, 18, 19, the outside camera 20, the laser sensor 21, the map information storage unit 22, and the vehicle-vehicle communication unit 23 may be provided.

In the above embodiment, the vehicle moving lane Ln1 which the vehicle VC _R is traveling, the adjacent lane Ln2 adjacent to the own lane Ln1, the it is assumed that performing lane change estimation of the traveling vehicle in two lanes, the present invention is, This is not a limitation. For example, even in a situation where there is a lane on the opposite side of the adjacent lane Ln2 across the own lane Ln1, the lane change estimation can be performed as in the above embodiment. In this case, the risk potential is also set for the vehicle traveling in the opposite lane, and the risk potential of the opposite lane is also calculated.

In the above embodiment, the vehicle VC _L ahead of the host vehicle VC _R is employed as an example the situation is traveling, the present invention is not intended to be limited thereto. For example, if the front of the vehicle VCR as the vehicle is not traveling, be only risk potential U _L in the above equation (4) becomes "0", similarly to the above calculation of the potential characteristic quantity P Is possible.

  In the above-described embodiment, the engine 10 is employed as an example of the power source of the vehicle 1, but the present invention is not limited to this. For example, an electric motor may be used as a power source, or an engine and an electric motor may be used in combination. Moreover, it can also be set as a range extender type electric vehicle.

  In the above embodiment, the front engine / front drive vehicle 1 is used as an example, but the present invention is not limited to this. For example, a front engine / rear drive vehicle, a four-wheel drive vehicle, a rear engine / rear drive vehicle, or the like may be employed.

  In the above embodiment, the control unit 24 has the function as the lane change estimation unit and the function as the vehicle control unit. However, in the present invention, the lane change estimation unit and the vehicle control unit are provided as separate units. It can also be configured.

Risk potential _U R shown in FIG. 7 in the above _{embodiment, U L, U P, U} F is based on each vehicle _{VC R, VC L, VC T} , VC P, VC F velocity and mutual distance between vehicles, etc. However, the present invention is not limited to this. That is, the risk potential Ui is set according to the above (Equation 2) based on the respective speeds of the host vehicle and the vehicles traveling in the vicinity, the distance between the vehicles, and the like.

1 vehicle 10 engine (drive source)
17 to 19 Radar 20 Camera outside the vehicle 21 Laser sensor 22 Map information storage unit 23 Inter-vehicle communication unit 24 Control unit (lane change estimation unit, vehicle control unit)
VC _R vehicle (the vehicle)
VC _L vehicle (vehicle in front of own lane)
VC _T vehicle (target vehicle)
VC _P vehicle (other lane preceding vehicle)
VC _F vehicles (vehicles behind other lanes)
Ln1 own lane Ln2 other lane

Claims (12)

A lane change estimation device for estimating a lane change of a vehicle traveling around the host vehicle,
A lane detector for detecting the own lane in which the host vehicle is traveling and the adjacent lane adjacent to the own lane;
A host vehicle in front of the host vehicle in the host vehicle lane, a target vehicle that travels in the neighboring lane and is subject to estimation of the lane change, and a vehicle in front of the target lane that runs in front of the target vehicle; A speed / distance detector that detects the speed and distance between the vehicles behind the adjacent lanes that run behind the target vehicle;
A lane change estimation unit that accepts a result of the detection from the speed / distance detection unit and estimates a lane change of the target vehicle;
With
The lane change estimation unit includes a relative speed and a relative distance between the host vehicle and the vehicle ahead of the host lane, a relative speed and a relative distance between the target vehicle and the vehicle ahead of the adjacent lane, the target vehicle and the adjacent lane. Based on the relative speed and the relative distance with the rear vehicle, the lane change of the target vehicle is estimated.
Lane change estimation device. In the lane change estimating apparatus according to claim 1,
The lane change estimation unit is
Based on the relative speed and the relative distance between the host vehicle and the vehicle ahead of the lane, a risk potential of the host vehicle and a risk potential of the vehicle ahead of the lane are set. Set the risk potential in the lane,
Based on the relative speed and the relative distance between the target vehicle and the vehicle ahead of the adjacent lane, a risk potential of the vehicle ahead of the adjacent lane is set, and the relative speed between the target vehicle and the vehicle behind the adjacent lane and Based on the relative distance, set the risk potential of the vehicle behind the adjacent lane, set the risk potential in the adjacent lane based on these risk potentials,
While calculating the ratio of the value of the risk potential in the own lane and the value of the risk potential in the adjacent lane, calculate the potential feature amount based on the ratio,
Based on the value of the potential feature value, the lane change of the target vehicle is estimated.
Lane change estimation device. In the lane change estimation apparatus according to claim 2,
The lane change estimation unit is
In setting the risk potential in the own lane, weighting is performed between the risk potential of the own vehicle and the risk potential of the vehicle ahead of the own lane,
In setting the risk potential in the adjacent lane, weighting is performed between the risk potential of the vehicle ahead of the adjacent lane and the risk potential of the vehicle behind the adjacent lane.
Lane change estimation device. In the lane change estimation apparatus according to claim 2 or claim 3,
The risk potential of the host vehicle is set in a state of being biased toward the host vehicle ahead when the relative speed of the host vehicle with respect to the host vehicle ahead is positive.
The risk potential of the vehicle ahead of the own lane is set in a state of being biased toward the front side opposite to the own vehicle when the relative speed of the vehicle ahead of the own lane with respect to the vehicle is positive.
The risk potential of the vehicle ahead of the adjacent lane is set in a state of being biased toward the front side opposite to the target vehicle when the relative speed of the vehicle ahead of the adjacent lane with respect to the target vehicle is positive,
The risk potential of the vehicle behind the adjacent lane is set in a state biased toward the target vehicle when the relative speed of the vehicle behind the adjacent lane with respect to the target vehicle is positive.
Lane change estimation device. In the lane change estimation apparatus according to any one of claims 2 to 4,
The risk potential of the host vehicle is set in a state of being biased toward a rear side opposite to the host vehicle ahead when the relative speed of the host vehicle with respect to the host vehicle ahead is negative,
The risk potential of the vehicle ahead of the own lane is set in a state of being biased toward the vehicle when the relative speed of the vehicle ahead of the own lane with respect to the vehicle is negative,
The risk potential of the vehicle ahead of the adjacent lane is set in a state of being biased toward the target vehicle when the relative speed of the vehicle ahead of the adjacent lane with respect to the target vehicle is negative,
The risk potential of the vehicle behind the adjacent lane is set in a state biased to the rear side opposite to the target vehicle when the relative speed of the vehicle behind the adjacent lane with respect to the target vehicle is negative.
Lane change estimation device. A vehicle control device for controlling a vehicle,
A lane change estimation device according to any one of claims 1 to 5,
A vehicle control unit that controls at least one of the speed and the inter-vehicle distance of the vehicle based on the estimation result of the lane change of the target vehicle estimated by the lane change estimation device;
Comprising
Vehicle control device. A lane change estimation method for estimating a lane change of a vehicle traveling around the host vehicle,
A lane detection step for detecting the own lane in which the host vehicle is traveling and the adjacent lane adjacent to the own lane;
A host vehicle in front of the host vehicle in the host vehicle lane, a target vehicle that travels in the neighboring lane and is subject to estimation of the lane change, and a vehicle in front of the target lane that runs in front of the target vehicle; A speed / distance detection step for detecting respective speeds and distances between the vehicles behind the adjacent lanes traveling behind the target vehicle;
A lane change estimation step for accepting a result of the detection from the speed / distance detection unit and estimating a lane change of the target vehicle;
With
In the lane change estimation step, a relative speed and a relative distance between the host vehicle and the vehicle ahead of the host lane, a relative speed and a relative distance between the target vehicle and the vehicle ahead of the adjacent lane, the target vehicle and the adjacent lane Based on the relative speed and the relative distance with the rear vehicle, the lane change of the target vehicle is estimated.
Lane change estimation method. The lane change estimation method according to claim 7,
The lane change estimation step includes
Based on the relative speed and the relative distance between the host vehicle and the vehicle ahead of the lane, a risk potential of the host vehicle and a risk potential of the vehicle ahead of the lane are set. A sub-step for setting the own lane risk potential to set the risk potential in the lane;
Based on the relative speed and the relative distance between the target vehicle and the vehicle ahead of the adjacent lane, the risk potential of the vehicle ahead of the adjacent lane is set, and the relative speed between the target vehicle and the vehicle behind the adjacent lane and Based on the relative distance, the risk potential of the vehicle behind the adjacent lane is set, and the adjacent lane risk potential setting substep for setting the risk potential in the adjacent lane based on these risk potentials;
A risk potential value ratio calculating sub-step for calculating a ratio between a value of the risk potential in the own lane and a value of the risk potential in the adjacent lane;
A potential feature amount calculation substep for calculating a potential feature amount based on the risk potential value ratio;
A lane change estimation substep for estimating a lane change of the target vehicle based on the value of the potential feature amount;
Having
Lane change estimation method. The lane change estimation method according to claim 8,
In the own lane risk potential setting sub-step, weighting is performed between the risk potential of the host vehicle and the risk potential of the vehicle ahead of the host lane,
In the adjacent lane risk potential setting sub-step, weighting is performed between the risk potential of the vehicle ahead of the adjacent lane and the risk potential of the vehicle behind the adjacent lane.
Lane change estimation method. In the lane change estimation method according to claim 8 or 9,
In the own lane risk potential setting sub-step, when the relative speed of the own vehicle with respect to the vehicle ahead of the own lane is positive, the risk potential of the own vehicle is biased toward the vehicle ahead of the own lane. In addition, when the relative speed of the vehicle ahead of the host vehicle with respect to the host vehicle is positive, the risk potential of the vehicle ahead of the host vehicle is set in a state of being biased toward the front side opposite to the host vehicle. And
In the adjacent lane risk potential setting sub-step, when the relative speed of the vehicle ahead of the adjacent lane with respect to the target vehicle is positive, the front side of the adjacent lane is biased toward the front side opposite to the target vehicle. Setting the risk potential of the vehicle, and setting the risk potential of the vehicle behind the adjacent lane in a state of being biased toward the target vehicle when the relative speed of the vehicle behind the adjacent lane with respect to the target vehicle is positive To
Lane change estimation method. In the lane change estimation method according to any one of claims 8 to 10,
In the own lane risk potential setting substep, when the relative speed of the own vehicle with respect to the vehicle ahead of the own lane is negative, the self-lane risk potential setting sub-step is biased toward the rear side opposite to the vehicle ahead of the own lane. Setting the risk potential of the vehicle and setting the risk potential of the vehicle ahead of the own lane in a state of being biased toward the own vehicle when the relative speed of the vehicle ahead of the own lane with respect to the vehicle is negative And
In the adjacent lane risk potential setting sub-step, when the relative speed of the vehicle ahead of the adjacent lane with respect to the target vehicle is negative, the risk potential of the vehicle ahead of the adjacent lane is biased toward the target vehicle. And when the relative speed of the vehicle behind the adjacent lane with respect to the target vehicle is negative, the risk potential of the vehicle behind the adjacent lane is set in a state biased toward the rear side opposite to the target vehicle. To
Lane change estimation method. A vehicle control method for controlling a vehicle, comprising:
A lane change estimation method according to any one of claims 7 to 11 is executed,
Controlling at least one of the speed and the inter-vehicle distance of the vehicle based on the estimation result of the lane change of the target vehicle, which is estimated by executing the lane change estimation method;
Vehicle control method.

Images