阅读说明：本技术 一种障碍物的速度估计方法、装置和电子设备 (Obstacle speed estimation method and device and electronic equipment ) 是由 高涵 于 2020-05-15 设计创作，主要内容包括：本申请公开了一种障碍物的速度估计方法、装置和电子设备,涉及数据处理领域中的自动驾驶数据处理领域。具体实现方案为：一种障碍物的速度估计方法,应用于车辆,包括：获取目标障碍物的第一速度估计值以及至少一个第二速度估计值,其中,所述第一速度估计值为基于所述目标障碍物在当前时刻的速度检测信息估计得到的速度值；所述第二速度估计值为所述目标障碍物在当前时刻之前的历史时刻的速度估计值；基于所述第一速度估计值以及至少一个第二速度估计值,确定目标速度值,其中,所述目标速度值用于控制所述车辆行驶。本申请提供一种障碍物的速度估计方法、装置和电子设备,可以解决现有技术中存在的对障碍物的速度估计不准确的问题。(The application discloses a method and a device for estimating speed of an obstacle and electronic equipment, and relates to the field of automatic driving data processing in the field of data processing. The specific implementation scheme is as follows: a method for estimating the speed of an obstacle, applied to a vehicle, includes: acquiring a first speed estimation value and at least one second speed estimation value of a target obstacle, wherein the first speed estimation value is a speed value estimated based on speed detection information of the target obstacle at the current moment; the second speed estimate is a speed estimate of the target obstacle at a historical time prior to the current time; determining a target speed value based on the first speed estimate and at least one second speed estimate, wherein the target speed value is used to control the vehicle to travel. The application provides a method and a device for estimating the speed of an obstacle and electronic equipment, which can solve the problem that the speed of the obstacle is estimated inaccurately in the prior art.)

1. A method for estimating a speed of an obstacle, applied to a vehicle, includes:

acquiring a first speed estimation value and at least one second speed estimation value of a target obstacle, wherein the first speed estimation value is a speed value estimated based on speed detection information of the target obstacle at the current moment; the second speed estimate is a speed estimate of the target obstacle at a historical time prior to the current time;

determining a target speed value based on the first speed estimate and at least one second speed estimate, wherein the target speed value is used to control the vehicle to travel.

2. The method of claim 1, wherein determining a target speed value based on the first speed estimate and at least one second speed estimate comprises:

determining the first speed estimate as the target speed value if the first speed estimate and the at least one second speed estimate both converge to a first speed value.

3. The method of claim 1, wherein determining a target speed value based on the first speed estimate and at least one second speed estimate comprises:

determining the target speed value from the at least one second speed estimate if the at least one second speed estimate converges to a second speed value and the first speed estimate does not converge to the second speed value.

4. The method of claim 1, wherein the acceleration estimates for each historical time corresponding to the at least one second velocity estimate converge to a first acceleration value, and wherein determining the target velocity value based on the first velocity estimate and the at least one second velocity estimate comprises:

calculating a first acceleration estimation value of the target obstacle under the condition that the at least one second velocity estimation value does not converge, wherein the first acceleration estimation value is an acceleration value calculated based on the velocity detection information of the target obstacle at the current moment and the at least one second velocity estimation value;

determining a target speed value based on the first speed estimate and at least one second speed estimate, comprising:

determining the first velocity estimate as the target velocity value if the first acceleration estimate converges to the first acceleration value.

5. The method of claim 4, wherein determining a target speed value based on the first velocity estimate and at least one second velocity estimate further comprises:

determining the target velocity value from the at least one second velocity estimate value if the first acceleration estimate value does not converge to the first acceleration value.

6. The method of claim 1, wherein determining a target speed value based on the first speed estimate and at least one second speed estimate comprises:

acquiring the speed direction of the target obstacle, wherein the speed direction is estimated based on the speed detection information of the target obstacle at the current moment;

calculating a first included angle value and a second included angle value, wherein the first included angle value is an included angle value between the speed direction and the orientation of the vehicle, and the second included angle value is an included angle value between the speed direction and the direction of a road where the obstacle is located;

and under the condition that the difference value between the first included angle value and the second included angle value is larger than a preset value, determining the target speed value according to the at least one second speed estimation value.

7. A method according to any of claims 3 to 6 wherein said determining said target speed value from said at least one second speed estimate comprises:

determining a second speed estimation value at a first historical moment as the target speed value, wherein the first historical moment is a historical moment which is closest to the current moment in all historical moments corresponding to the at least one second speed estimation value;

alternatively, an average of the at least one second velocity estimate is determined as the target velocity value.

8. An obstacle speed estimation device applied to a vehicle, characterized by comprising:

the system comprises an acquisition module, a first speed estimation value and at least one second speed estimation value, wherein the first speed estimation value is a speed value estimated based on speed detection information of a target obstacle at the current moment; the second speed estimate is a speed estimate of the target obstacle at a historical time prior to the current time;

a determination module configured to determine a target speed value based on the first speed estimate and at least one second speed estimate, wherein the target speed value is used to control the vehicle to travel.

9. The apparatus of claim 8, wherein the means for determining determines the first speed estimate as the target speed value if the first speed estimate and the at least one second speed estimate both converge to the first speed value.

10. The apparatus of claim 8, wherein the means for determining determines the target speed value based on the at least one second speed estimate if the at least one second speed estimate converges to a second speed value and the first speed estimate does not converge to the second speed value.

11. The apparatus of claim 8, wherein the acceleration estimates for each historical time corresponding to the at least one second velocity estimate converge to a first acceleration value, the apparatus further comprising:

a calculation module, configured to calculate a first acceleration estimation value of the target obstacle when the at least one second velocity estimation value does not converge, where the first acceleration estimation value is an acceleration value calculated based on the velocity detection information of the target obstacle at the current time and the at least one second velocity estimation value;

the determining module is configured to determine the first velocity estimate as the target velocity value if the first acceleration estimate converges to the first acceleration value.

12. The apparatus of claim 11, wherein the means for determining is further configured to determine the target speed value based on the at least one second velocity estimate if the first acceleration estimate does not converge on the first acceleration value.

13. The apparatus of claim 8, wherein the determining module comprises:

the obtaining submodule is used for obtaining the speed direction of the target obstacle, wherein the speed direction is estimated based on the speed detection information of the target obstacle at the current moment;

the calculation submodule is used for calculating a first included angle value and a second included angle value, wherein the first included angle value is an included angle value between the speed direction and the orientation of the vehicle, and the second included angle value is an included angle value between the speed direction and the direction of a road where the obstacle is located;

and the determining submodule is used for determining the target speed value according to the at least one second speed estimation value under the condition that the difference value between the first included angle value and the second included angle value is larger than a preset value.

14. The apparatus according to any one of claims 10 to 13, wherein the determining module is configured to determine a second speed estimation value at a first historical time as the target speed value, where the first historical time is a historical time closest to a current time among historical times corresponding to the at least one second speed estimation value;

or, the determining module is configured to determine an average value of the at least one second speed estimation value as the target speed value.

15. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

16. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-7.

Technical Field

The invention relates to the field of automatic driving data processing in the field of data processing, in particular to a method and a device for estimating the speed of an obstacle and electronic equipment.

Background

With the development of automatic driving technology, various unmanned automobiles appear on the market. When the existing unmanned automobile is in the automatic driving mode, a detection element of the unmanned automobile is generally required to detect an obstacle in the driving direction, and the speed of the obstacle is estimated based on the detection result, so as to avoid the problem that the unmanned automobile collides with the obstacle. However, when the road environment is complex, the detection result of the obstacle by the detection element may have a large error, and in this case, the speed estimation of the obstacle may be inaccurate.

Disclosure of Invention

The application provides a method and a device for estimating the speed of an obstacle and electronic equipment, which aim to solve the problem that the speed of the obstacle is estimated inaccurately in the prior art.

In a first aspect, the present application provides a method for estimating a speed of an obstacle, applied to a vehicle, including:

acquiring a first speed estimation value and at least one second speed estimation value of a target obstacle, wherein the first speed estimation value is a speed value estimated based on speed detection information of the target obstacle at the current moment; the second speed estimate is a speed estimate of the target obstacle at a historical time prior to the current time;

determining a target speed value based on the first speed estimate and at least one second speed estimate, wherein the target speed value is used to control the vehicle to travel.

In this way, the target velocity value of the target obstacle at the current time is determined based on the first velocity estimation value obtained by estimating the velocity detection information of the target obstacle, and further based on the velocity estimation value obtained by estimating the velocity of the target obstacle at the past time. The accuracy of speed estimation of the target obstacle is improved.

Optionally, the determining a target speed value based on the first speed estimate and at least one second speed estimate comprises:

determining the first speed estimate as the target speed value if the first speed estimate and the at least one second speed estimate both converge to a first speed value;

in the embodiment, the problem of large speed estimation error of the obstacle in a constant-speed motion state in the prior art is solved by judging the convergence of the first speed estimation value and the at least one second speed estimation value.

Optionally, the determining a target speed value based on the first speed estimate and at least one second speed estimate comprises:

determining the target speed value from the at least one second speed estimate if the at least one second speed estimate all converges to the second speed value and the first speed estimate does not converge to the second speed value.

In the embodiment, the problem of large speed estimation error of the obstacle in a constant-speed motion state in the prior art is solved by judging the convergence of the first speed estimation value and the at least one second speed estimation value.

Optionally, the determining the target speed value based on the first speed estimation value and the at least one second speed estimation value includes:

calculating a first acceleration estimation value of the target obstacle under the condition that the at least one second velocity estimation value does not converge, wherein the first acceleration estimation value is an acceleration value calculated based on the velocity detection information of the target obstacle at the current moment and the at least one second velocity estimation value;

determining the first velocity estimate as the target velocity value if the first acceleration estimate converges to the first acceleration value.

In the embodiment, the problem of large speed estimation error when the obstacle is in a uniform acceleration or uniform deceleration motion state in the prior art is solved by calculating and judging the convergence of the first acceleration estimation value.

Optionally, the determining a target speed value based on the first speed estimate and at least one second speed estimate further includes:

determining the target velocity value from the at least one second velocity estimate value if the first acceleration estimate value does not converge to the first acceleration value.

In the embodiment, the problem of large speed estimation error when the obstacle is in a uniform acceleration or uniform deceleration motion state in the prior art is solved by calculating and judging the convergence of the first acceleration estimation value.

Optionally, the determining a target speed value based on the first speed estimate and at least one second speed estimate comprises:

acquiring the speed direction of the target obstacle, wherein the speed direction is estimated based on the speed detection information of the target obstacle at the current moment;

calculating a first included angle value and a second included angle value, wherein the first included angle value is an included angle value between the speed direction and the orientation of the vehicle, and the second included angle value is an included angle value between the speed direction and the direction of a road where the obstacle is located;

and under the condition that the difference value between the first included angle value and the second included angle value is larger than a preset value, determining the target speed value according to the at least one second speed estimation value.

In the embodiment, the problem that the estimation of the speed direction of the target obstacle is inaccurate in the prior art is solved by judging the relative size between the first included angle value and the second included angle value.

Optionally, said determining said target speed value from said at least one second speed estimate comprises:

determining a second speed estimation value at a first historical moment as the target speed value, wherein the first historical moment is a historical moment which is closest to the current moment in all historical moments corresponding to the at least one second speed estimation value;

alternatively, an average of the at least one second velocity estimate is determined as the target velocity value.

In this embodiment, the second speed estimation value at the first history time is determined as the target speed value, or the average value of the at least one second speed estimation value is determined as the target speed value, so that the problem of how to estimate the current speed of the target obstacle when the first speed estimation value may have a large error is solved.

In a second aspect, the present application provides an obstacle speed estimation device for a vehicle, comprising:

the system comprises an acquisition module, a first speed estimation value and at least one second speed estimation value, wherein the first speed estimation value is a speed value estimated based on speed detection information of a target obstacle at the current moment; the second speed estimate is a speed estimate of the target obstacle at a historical time prior to the current time;

a determination module configured to determine a target speed value based on the first speed estimate and at least one second speed estimate, wherein the target speed value is used to control the vehicle to travel.

Optionally, the determining module is configured to determine the first speed estimate as the target speed value if the first speed estimate and the at least one second speed estimate both converge to a first speed value.

Optionally, the determining module is configured to determine the target speed value according to the at least one second speed estimate when the at least one second speed estimate converges to the first speed value and the first speed estimate does not converge to the first speed value.

Optionally, the acceleration estimated values at the historical times corresponding to the at least one second velocity estimated value each converge to the first acceleration value, and the apparatus further includes:

a calculation module, configured to calculate a first acceleration estimation value of the target obstacle when the at least one second velocity estimation value does not converge, where the first acceleration estimation value is an acceleration value calculated based on the velocity detection information of the target obstacle at the current time and the at least one second velocity estimation value;

the determining module is configured to determine the first velocity estimate as the target velocity value if the first acceleration estimate converges to the first acceleration value.

Optionally, the determining module is further configured to determine the target speed value according to the at least one second speed estimation value in a case where the first acceleration estimation value does not converge to the first acceleration value.

Optionally, the determining module includes:

the obtaining submodule is used for obtaining the speed direction of the target obstacle, wherein the speed direction is estimated based on the speed detection information of the target obstacle at the current moment;

the calculation submodule is used for calculating a first included angle value and a second included angle value, wherein the first included angle value is an included angle value between the speed direction and the orientation of the vehicle, and the second included angle value is an included angle value between the speed direction and the direction of a road where the obstacle is located;

and the determining submodule is used for determining the target speed value according to the at least one second speed estimation value under the condition that the difference value between the first included angle value and the second included angle value is larger than a preset value.

Optionally, the determining module is configured to determine a second speed estimation value at a first historical time as the target speed value, where the first historical time is a closest historical time to a current time among historical times corresponding to the at least one second speed estimation value;

or, the determining module is configured to determine an average value of the at least one second speed estimation value as the target speed value.

In a third aspect, the present application provides an electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of velocity estimation of an obstacle as provided herein.

In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having stored thereon computer instructions for causing the computer to execute the method of velocity estimation of an obstacle provided herein.

One embodiment in the above application has the following advantages or benefits: on the basis of obtaining a first speed estimation value by estimating speed detection information of the target obstacle, a target speed value of the target obstacle at the current time is determined by further combining the speed estimation value obtained by estimating the speed of the target obstacle at the historical time. The accuracy of speed estimation of the target obstacle is improved.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:

fig. 1 is a flow chart of a method of velocity estimation of an obstacle provided in an embodiment of the present application;

fig. 2 is a schematic structural diagram of a speed estimation device of an obstacle provided in an embodiment of the present application;

fig. 3 is a block diagram of an electronic device for implementing a method for estimating a velocity of an obstacle according to an embodiment of the present application.

Detailed Description

The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Referring to fig. 1, fig. 1 is a method for estimating a speed of an obstacle according to an embodiment of the present invention, applied to a vehicle, including:

step 101, obtaining a first speed estimation value and at least one second speed estimation value of a target obstacle, wherein the first speed estimation value is a speed value estimated based on speed detection information of the target obstacle at the current moment; the second velocity estimate is an estimate of the velocity of the target obstacle at a historical time prior to the current time.

The vehicle may be an unmanned automobile, or may be a vehicle having an unmanned mode. The target obstacle may be another vehicle in the traveling direction of the vehicle, or may be a fixed obstacle on the road on which the vehicle travels. It should be noted that the number of the above-mentioned obstacles may be one or more, when there are multiple obstacles, the unmanned vehicle may estimate the speed of multiple obstacles at the same time, and in order to avoid confusion, the following takes speed estimation for a certain target obstacle during the driving of the unmanned vehicle as an example, and the method provided by the present application is further explained.

The speed detection information can be image information collected by a vision sensor arranged on the unmanned automobile, the vision sensor can be a passive vision sensor such as a monocular camera, and the passive vision sensor can continuously shoot the driving direction of the unmanned automobile so as to shoot the obstacle information in the driving direction of the unmanned automobile. Then, a velocity estimation can be performed on each frame of image captured by the passive vision sensor based on a kalman filtering velocity estimation method to determine velocity information of the target obstacle. The speed detection information may be motion state information of the obstacle acquired by the vehicle-mounted radar.

Specifically, the first speed estimation value can be obtained by performing speed estimation on a picture currently taken by the passive vision sensor. Since the vehicle control unit of the unmanned vehicle needs to grasp the speed information of the target obstacle on the road surface in real time so as to control the unmanned vehicle, the unmanned vehicle estimates the speed of the target obstacle at each moment, and thus, when the speed at the current moment needs to be estimated, the at least one second speed estimation value can be obtained through the historical estimation speed maintained by the vehicle control unit. The target speed value is a final speed estimation value obtained by estimating the speed at the current moment by combining the first speed estimation value and at least one second speed estimation value.

The at least one second speed estimation value may be a speed estimation value corresponding to all pictures taken from the first time point to the current time point. As can be seen, the at least one second speed estimation value and the target speed value are actually speed estimation values corresponding to a plurality of adjacent moments, that is, speed estimation values obtained by estimating a plurality of frames of pictures continuously taken by the passive vision sensor. Preferably, the first time point may be a time point relatively close to the current time, for example, n seconds may be pushed forward as the first time point with reference to the current time point, where n may be 1, 3, 5, 7, and so on.

And 102, determining a target speed value based on the first speed estimation value and at least one second speed estimation value, wherein the target speed value is used for controlling the vehicle to run.

Since the first speed estimation value is based on the speed estimation value obtained by photographing the target obstacle and estimating the speed, the accuracy of the first speed estimation value is greatly affected by the photographing environment, for example, when there are interference factors such as rain and fog during photographing, the photographed picture may be unclear, and the first speed estimation value obtained by speed estimation based on the picture may be greatly different from the actual speed value. To this end, the present embodiment estimates the velocity of the obstacle by further combining at least one second velocity estimate value to verify the accuracy of the first velocity estimate value.

Specifically, as can be seen from the above discussion, the at least one second speed estimation value and the target speed value may be speed estimation values corresponding to a plurality of adjacent time instants, and therefore, after the at least one second speed estimation value is obtained, the current operation state of the target obstacle may be analyzed and the speed at the current time instant may be predicted by analyzing the second speed estimation values before the current time instant. Since the speed of the target obstacle in a smaller time period (e.g., 1 second, 3 seconds, 5 seconds, etc.) may be equivalent to one of a constant speed, a uniform acceleration, or a uniform deceleration, by obtaining at least one second speed estimation value in a smaller time period adjacent to the current time before the current time, and estimating the speed of the current time based on the at least one second speed estimation value, a speed estimation value close to the actual speed estimation value of the target obstacle may be obtained. In this way, it is possible to verify whether the first speed estimate is accurate by comparing a current-time speed estimate estimated based on at least one second speed estimate with the first speed estimate. Therefore, the problem of large estimation error generated when the speed of the obstacle is estimated can be avoided.

In the embodiment of the application, on the basis of obtaining the first speed estimation value by estimating the speed detection information of the target obstacle, the target speed value of the target obstacle at the current time is determined by further combining the speed estimation value obtained by estimating the speed of the target obstacle at the historical time. The accuracy of speed estimation of the target obstacle is improved.

Optionally, the determining a target speed value based on the first speed estimate and at least one second speed estimate comprises:

determining the first speed estimate as the target speed value if the first speed estimate and the at least one second speed estimate both converge to a first speed value.

Wherein the convergence of the first velocity estimate and the at least one second velocity estimate to the first velocity value may be: the first velocity estimation value and the at least one second velocity estimation value both fluctuate in the vicinity of the first velocity value and have a relatively small fluctuation range, and for example, the first velocity value may be regarded as the center, and velocity estimation values whose fluctuation size is 5% of the first velocity value may be regarded as velocity estimation values converging on the first velocity value. For another example, when the first speed value is 50km/h, the corresponding convergence section is [47.5, 52.5], and if the first speed estimate and the at least one second speed estimate are both within [47.5, 52.5], it is determined that both the first speed estimate and the at least one second speed estimate converge to the first speed value.

Since the at least one second velocity estimation value converges to the first velocity value, it may be inferred that the target obstacle may be currently in a uniform motion state, and when the first velocity estimation value also converges to the first velocity value, as in the conclusion inferred based on the at least one second velocity estimation value, it may be determined that the estimated first velocity estimation value is a relatively accurate velocity estimation value, and in this case, the first velocity estimation value is determined as the target velocity value.

In the embodiment, the problem of large speed estimation error of the obstacle in a constant-speed motion state in the prior art is solved by judging the convergence of the first speed estimation value and the at least one second speed estimation value.

Optionally, the determining a target speed value based on the first speed estimate and at least one second speed estimate comprises:

determining the target speed value from the at least one second speed estimate if the at least one second speed estimate all converges to the second speed value and the first speed estimate does not converge to the second speed value.

Wherein the convergence of the first velocity estimate and the at least one second velocity estimate to a second velocity value may refer to: the first velocity estimate and the at least one second velocity estimate both fluctuate in the vicinity of the second velocity value with a relatively small fluctuation range. The second speed value may be the same as the first speed value in the above embodiment, or may be different from the first speed value.

Since the at least one second velocity estimate each converges to a second velocity value, it may be inferred that the target obstacle may currently be in a uniform motion state. When the first speed estimate does not converge to the second speed value, this estimate is not the same as the conclusion inferred based on the at least one second speed estimate, and therefore, this estimate may be an estimate with a larger error, and in order to avoid an excessive error in the speed estimation, the current target speed value is estimated by the at least one second speed estimate, and the error in the speed estimation is seen to decrease.

In the embodiment, the problem of large speed estimation error of the obstacle in a constant-speed motion state in the prior art is solved by judging the convergence of the first speed estimation value and the at least one second speed estimation value.

Optionally, the determining the target speed value based on the first speed estimation value and the at least one second speed estimation value includes:

calculating a first acceleration estimation value of the target obstacle under the condition that the at least one second velocity estimation value does not converge, wherein the first acceleration estimation value is an acceleration value calculated based on the velocity detection information of the target obstacle at the current moment and the at least one second velocity estimation value;

determining the first velocity estimate as the target velocity value if the first acceleration estimate converges to the first acceleration value.

Since the at least one second speed estimation value is selected from a speed estimation value within a smaller time period (e.g., 1 second, 3 seconds, 5 seconds, etc.), the speed of the target obstacle can be equivalent to one of a uniform speed, a uniform acceleration, or a uniform deceleration within the time period, and at this time, the acceleration of the target obstacle is a relatively fixed value no matter what motion state the target obstacle is in, and therefore, it can be determined that the acceleration estimation values of the history times corresponding to the at least one second speed estimation value are converged to the first acceleration value. Furthermore, the fact that the acceleration estimation values of the at least one second speed estimation value at the respective historical times converge to the first acceleration value may be that: the acceleration estimated values of the at least one second acceleration estimated value at each historical time fluctuate near the first acceleration value in a relatively small fluctuation range, for example, the first acceleration value may be regarded as the center, and the acceleration estimated value with fluctuation amount of 5% of the first acceleration value may be regarded as the acceleration estimated value converging on the first acceleration value.

In this case, since the acceleration estimation values at the respective historical times corresponding to the at least one second velocity estimation value are all converged to the first acceleration value, it is possible to determine whether the first velocity estimation value is abnormal by determining whether the acceleration value at the current time is converged to the first acceleration value.

The current first acceleration estimation value can be calculated by subtracting the second speed estimation value at the previous moment from the first speed estimation value at the current moment and dividing the difference by the time difference between the first speed estimation value and the second speed estimation value, and whether the first speed estimation value is abnormal or not can be judged by judging whether the first acceleration estimation value converges to the first acceleration value or not.

Specifically, in the case where the at least one second velocity estimation value does not converge, then it may be inferred that the target obstacle is currently in a uniformly-accelerated or uniformly-decelerated motion state, and based on the above discussion, it may be inferred that the current acceleration value is the first acceleration value, and therefore, it may be determined whether there is an abnormality in the first velocity estimation value by determining whether the current first acceleration estimation value converges to the first acceleration. When the first acceleration estimate converges to the first acceleration, since the first acceleration estimate is calculated based on the first velocity estimate, the calculation result based on the first velocity estimate being the same as the above-mentioned inference result, it can be determined that the estimated first velocity estimate is a relatively accurate velocity estimate, and in this case, the first velocity estimate is determined as the target velocity value.

In the embodiment, the problem of large speed estimation error when the obstacle is in a uniform acceleration or uniform deceleration motion state in the prior art is solved by calculating and judging the convergence of the first acceleration estimation value.

Optionally, the determining a target speed value based on the first speed estimate and at least one second speed estimate further includes:

determining the target velocity value from the at least one second velocity estimate value if the first acceleration estimate value does not converge to the first acceleration value.

Specifically, when the first acceleration estimation value does not converge to the first acceleration, it does not match the above-mentioned inference result, and therefore, the estimation value may be an estimation value with a large error, and in order to avoid an excessive error in the speed estimation, the current target speed value is estimated by at least one second speed estimation value, so that the error in the speed estimation is reduced.

In the embodiment, the problem of large speed estimation error when the obstacle is in a uniform acceleration or uniform deceleration motion state in the prior art is solved by calculating and judging the convergence of the first acceleration estimation value.

Optionally, the determining a target speed value based on the first speed estimate and at least one second speed estimate comprises:

acquiring the speed direction of the target obstacle, wherein the speed direction is estimated based on the speed detection information of the target obstacle at the current moment;

calculating a first included angle value and a second included angle value, wherein the first included angle value is an included angle value between the speed direction and the orientation of the vehicle, and the second included angle value is an included angle value between the speed direction and the direction of a road where the obstacle is located;

and under the condition that the difference value between the first included angle value and the second included angle value is larger than a preset value, determining the target speed value according to the at least one second speed estimation value.

Since the estimation of the current speed may have an error in the estimation of the direction of the speed in addition to an error in the magnitude of the speed, the currently estimated direction of the speed may be further determined to determine whether the result of the speed estimated based on the speed detection information of the target obstacle is accurate.

Specifically, the direction of the road on which the target obstacle is located may be a direction of a lane line on the road on which the target obstacle is located, and since the picture taken by the passive vision sensor generally includes the target obstacle and the lane line beside the target obstacle, the second included angle value may be directly determined from the picture taken by the passive vision sensor. The second angle value is a relatively accurate value because it is measured directly from the same picture. The body orientation of the unmanned automobile is generally consistent with the direction of the road where the target obstacle is located, and belongs to the information of the unmanned automobile, so that the body orientation of the unmanned automobile can be relatively accurately acquired. Based on this, the estimated velocity direction of the target obstacle may be checked based on the second pinch angle value and the body orientation of the unmanned vehicle, if a first pinch angle value between the estimated velocity direction and the body orientation of the unmanned vehicle is the same as or close to the second pinch angle value, it may be inferred that the estimated velocity direction of the target obstacle is a relatively accurate value, and if the difference between the first pinch angle value between the estimated velocity direction and the body orientation of the unmanned vehicle is large and the second pinch angle value is large, it may be inferred that there is a large error in the estimated velocity direction, and since there is an error in the estimation of the current velocity direction of the target obstacle, it may cause an erroneous operation of the unmanned vehicle even if there is no error in the estimation of the current velocity direction of the target obstacle, and therefore, in this case, the target speed value is determined from the at least one second speed estimate value such that the error in the speed estimate is seen to be reduced.

In the embodiment, the problem that the estimation of the speed direction of the target obstacle is inaccurate in the prior art is solved by judging the relative size between the first included angle value and the second included angle value.

Optionally, said determining said target speed value from said at least one second speed estimate comprises:

determining a second speed estimation value at a first historical moment as the target speed value, wherein the first historical moment is a historical moment which is closest to the current moment in all historical moments corresponding to the at least one second speed estimation value;

alternatively, an average of the at least one second velocity estimate is determined as the target velocity value.

Wherein the target speed value may be determined based on the at least one second speed estimate value, in a case where it is determined that there may be a large error in a first speed estimate value estimated based on the speed detection information. Specifically, because the time interval between two adjacent frames of pictures continuously shot by the passive vision sensor when the passive vision sensor is used for the target obstacle is very small, the speeds of the times corresponding to the two adjacent frames of pictures are also relatively close, when a first speed estimation value obtained based on a current frame of picture possibly has a large error, a second speed estimation value of the time corresponding to a previous frame of picture can be used as a target speed value of the current time, and therefore the error of the speed estimation of the target obstacle can be effectively reduced.

In addition, in addition to taking the second velocity estimation value at the time corresponding to the previous frame of picture as the target velocity value at the current time, the average value of the at least one second velocity estimation value may be determined as the target velocity value, and as is clear from the above discussion, the at least one second velocity estimation value is the entire velocity estimation value for the target obstacle in the time period adjacent to the current time point and having a small range, and therefore, the velocity change of the target obstacle in the time period is usually not particularly large, and the error of the velocity estimation of the target obstacle can be effectively reduced by calculating the average value of the velocity estimation values in the time period and taking the average value as the target velocity value.

In this embodiment, the second speed estimation value at the first history time is determined as the target speed value, or the average value of the at least one second speed estimation value is determined as the target speed value, so that the problem of how to estimate the current speed of the target obstacle when the first speed estimation value may have a large error is solved.

Referring to fig. 2, fig. 2 is a diagram illustrating an obstacle speed estimation device 200 according to an embodiment of the present application, applied to a vehicle, including:

an obtaining module 201, configured to obtain a first speed estimation value and at least one second speed estimation value of a target obstacle, where the first speed estimation value is a speed value estimated based on speed detection information of the target obstacle at a current time; the second speed estimate is a speed estimate of the target obstacle at a historical time prior to the current time;

a determining module 202 configured to determine a target speed value based on the first speed estimate and at least one second speed estimate, wherein the target speed value is used for controlling the vehicle to run.

Optionally, the determining module 202 is configured to determine the first speed estimation value as the target speed value if the first speed estimation value and the at least one second speed estimation value both converge to the first speed value.

Optionally, the determining module 202 is configured to determine the target speed value according to the at least one second speed estimation value when the at least one second speed estimation value converges to the second speed value and the first speed estimation value does not converge to the second speed value.

Optionally, the acceleration estimated values at the historical times corresponding to the at least one second velocity estimated value each converge to the first acceleration value, and the apparatus further includes:

a calculation module, configured to calculate a first acceleration estimation value of the target obstacle when the at least one second velocity estimation value does not converge, where the first acceleration estimation value is an acceleration value calculated based on the velocity detection information of the target obstacle at the current time and the at least one second velocity estimation value;

the determining module 202 is configured to determine the first speed estimation value as the target speed value when the first acceleration estimation value converges to the first acceleration value.

Optionally, the determining module 202 is further configured to determine the target speed value according to the at least one second speed estimation value in a case that the first acceleration estimation value does not converge to the first acceleration value.

Optionally, the determining module 202 includes:

the obtaining submodule is used for obtaining the speed direction of the target obstacle, wherein the speed direction is estimated based on the speed detection information of the target obstacle at the current moment;

the calculation submodule is used for calculating a first included angle value and a second included angle value, wherein the first included angle value is an included angle value between the speed direction and the orientation of the vehicle, and the second included angle value is an included angle value between the speed direction and the direction of a road where the obstacle is located;

and the determining submodule is used for determining the target speed value according to the at least one second speed estimation value under the condition that the difference value between the first included angle value and the second included angle value is larger than a preset value.

Optionally, the determining module 202 is configured to determine a second speed estimation value at a first historical time as the target speed value, where the first historical time is a closest historical time to a current time in the historical times corresponding to the at least one second speed estimation value;

alternatively, the determining module 202 is configured to determine an average value of the at least one second speed estimation value as the target speed value.

The apparatus provided in this embodiment can implement each process implemented in the method embodiment shown in fig. 1, and can achieve the same beneficial effects, and is not described here again to avoid repetition.

According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.

As shown in fig. 3, the present disclosure is a block diagram of an electronic device according to an obstacle speed estimation method according to an embodiment of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.

As shown in fig. 3, the electronic apparatus includes: one or more processors 301, memory 302, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 3, one processor 301 is taken as an example.

Memory 302 is a non-transitory computer readable storage medium as provided herein. Wherein the memory stores instructions executable by at least one processor to cause the at least one processor to perform the method of velocity estimation of an obstacle provided herein. The non-transitory computer-readable storage medium of the present application stores computer instructions for causing a computer to perform the method of velocity estimation of an obstacle provided herein.

The memory 302, which is a non-transitory computer-readable storage medium, may be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules (e.g., the obtaining module 201 and the determining module 202 shown in fig. 2) corresponding to the speed estimation method of an obstacle in the embodiment of the present application. The processor 301 executes various functional applications of the server and data processing, i.e., implements the speed estimation method of the obstacle in the above-described method embodiment, by running non-transitory software programs, instructions, and modules stored in the memory 302.

The memory 302 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the electronic device of the speed estimation method of the obstacle, and the like. Further, the memory 302 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 302 optionally includes memory located remotely from the processor 301, and these remote memories may be connected over a network to the electronics of the method of velocity estimation of an obstacle. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The electronic device of the method of estimating a velocity of an obstacle may further include: an input device 303 and an output device 304. The processor 301, the memory 302, the input device 303 and the output device 304 may be connected by a bus or other means, and fig. 3 illustrates the connection by a bus as an example.

The input device 303 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic apparatus of the speed estimation method of the obstacle, such as an input device of a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointing stick, one or more mouse buttons, a track ball, a joystick, or the like. The output devices 304 may include a display device, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.

Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

According to the technical scheme of the embodiment of the application, on the basis of obtaining the first speed estimation value by estimating the speed detection information of the target obstacle, the target speed value of the target obstacle at the current time is determined by further combining the speed estimation value obtained by estimating the speed of the target obstacle at the historical time. The accuracy of speed estimation of the target obstacle is improved.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.

The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.