Unmanned vehicle braking performance detection system and unmanned vehicle

Abstract

The embodiment of the invention provides a system for detecting the braking performance of an unmanned vehicle, and the system comprises a vehicle model matching module which is used for matching a pre-constructed vehicle model for the unmanned vehicle based on the obtained vehicle data; the expected deceleration obtaining module is used for inputting the braking request of the unmanned vehicle and the current vehicle speed into the vehicle model under the condition that the braking demand is generated, and the expected deceleration is obtained; the observer is used for estimating the actual deceleration of the unmanned vehicle based on a first observed quantity obtained by observing the real vehicle data of the unmanned vehicle, and estimating the driving resistance of the unmanned vehicle by using the expected deceleration and the actual deceleration to obtain a road surface rolling resistance estimated value; and the evaluation module is used for judging whether the braking performance of the unmanned vehicle declines or not based on the road surface rolling resistance estimation value obtained in the braking process and the road surface rolling resistance estimation threshold value corresponding to the vehicle model. The method achieves the discrimination of the degradation degree of the braking performance of different unmanned vehicles, and effectively avoids the occurrence of safety accidents.

Description

Technical Field

[0001] The present disclosure relates to the technical field of braking performance detection, and in particular to a braking performance detection system for an unmanned vehicle and an unmanned vehicle. Background Art

[0002] For driverless vehicles, the electric control braking system is one of the most important wire-controlled components, playing an indispensable role in deceleration, obstacle avoidance, and terminal parking. If the braking system of an driverless vehicle fails, it may not be able to decelerate and stop normally, causing serious safety accidents.

[0003] At present, most unmanned vehicles use pneumatic braking. From the braking principle, it is difficult to ensure the consistency of braking performance of different vehicles, and as the vehicle is used for a longer time, the braking performance will also decay to varying degrees. For manned vehicles, the driver's subjective feeling can be used to determine whether the vehicle's braking ability is normal, but for unmanned vehicles, there is currently no clear evaluation method to evaluate the braking consistency of a certain model of vehicle. Even for vehicles of the same model, the braking performance of different vehicles will change differently depending on the usage scenario and usage time. The braking performance detection method for the same model of vehicle cannot make the detection results of each vehicle of the same model accurate. Summary of the invention

[0004] The disclosed embodiments provide a system for detecting the braking performance of an unmanned vehicle and an unmanned vehicle, so as to solve the existing problem that it is impossible to specifically detect whether the braking performance of different unmanned vehicles has declined.

[0005] Based on the above problems, in the first aspect, a detection system for the braking performance of an unmanned vehicle is provided, comprising:

[0006] A vehicle model matching module, used to match a pre-built vehicle model for the unmanned vehicle based on the acquired vehicle data;

[0007] an expected deceleration acquisition module, used for inputting the braking request and current vehicle speed of the unmanned vehicle into the vehicle model when a braking demand is generated, obtaining an expected deceleration of the unmanned vehicle, and inputting the expected deceleration into an observer;

[0008] The observer is used to estimate the actual deceleration of the unmanned vehicle based on a first observation value obtained by observing the actual vehicle data of the unmanned vehicle, and estimate the driving resistance of the unmanned vehicle using the expected deceleration and the actual deceleration to obtain an estimated value of road rolling resistance, and input the estimated value of road rolling resistance into an evaluation module;

[0009] The evaluation module is used to determine whether the braking performance of the unmanned vehicle is degraded based on the estimated value of road rolling resistance obtained during braking and the estimated threshold of road rolling resistance corresponding to the vehicle model.

[0010] In combination with the first aspect, in a possible implementation manner, the observer is further used to observe the dynamic and static data of the unmanned vehicle and the braking scene to obtain a second observation value, and input the second observation value into the evaluation module;

[0011] The evaluation module is also used to determine the weight of the second observation quantity according to the current braking scenario, perform weighted processing on the second observation quantity based on the determined weight, obtain an adjustment coefficient for the road surface rolling resistance estimation threshold, and use the adjustment coefficient to adjust the road surface rolling resistance estimation threshold.

[0012] In combination with the first aspect, in a possible implementation manner, the evaluation module is further configured to determine that the braking performance of the unmanned vehicle has declined when the estimated road rolling resistance value is greater than the estimated road rolling resistance threshold value for a preset number of times; or

[0013] The road rolling resistance estimation threshold includes upper and lower boundary thresholds, and the evaluation module is used to determine that the braking performance of the unmanned vehicle has declined when the road rolling resistance estimation value is greater than the upper boundary threshold of the road rolling resistance estimation threshold for a preset number of times.

[0014] In combination with the first aspect, in a possible implementation, the evaluation module is also used to count the time percentage of the road rolling resistance estimation value being higher than the road rolling resistance estimation threshold or higher than the upper boundary threshold of the road rolling resistance estimation threshold during braking, and determine that the braking performance of the unmanned vehicle has declined when the time percentage is higher than the time percentage threshold for performance decline evaluation.

[0015] In combination with the first aspect, in a possible implementation, the expected deceleration adjustment module is used to feed back the road rolling resistance estimation value to the vehicle model to adjust the expected deceleration output by the vehicle model.

[0016] In combination with the first aspect, in a possible implementation, the vehicle data includes: static parameters of the unmanned vehicle and dynamic parameters obtained by actually measuring the unmanned vehicle; the vehicle model matching module is also used to preliminarily match the corresponding vehicle model based on the static parameters, and optimize the preliminarily matched vehicle model based on the dynamic parameters, wherein the braking capacity of the vehicle model is not lower than a specified braking capacity requirement threshold.

[0017] In combination with the first aspect, in a possible implementation manner, the first observation quantity includes: a motion state parameter measured by an inertial measurement unit IMU;

[0018] The observer is also used to calculate the posture of the unmanned vehicle through the motion state parameters measured by the IMU, and obtain the acceleration and pitch angle of the unmanned vehicle; filter the acceleration to eliminate data noise caused by the unevenness of the road surface during the driving of the unmanned vehicle; and estimate the actual deceleration of the unmanned vehicle during braking based on the filtered acceleration and the pitch angle.

[0019] In combination with the first aspect, in a possible implementation manner, the second observation includes at least one of the following:

[0020] Duration of the braking process, road grade, and initial braking request.

[0021] In combination with the first aspect, in a possible implementation manner, the static parameter includes at least one of a vehicle type, a model, and a vehicle weight; and / or,

[0022] The dynamic parameter includes at least one of speed, deceleration and braking distance.

[0023] In a second aspect, an unmanned vehicle is provided, comprising: a system for detecting the braking performance of the unmanned vehicle as described in any one of the embodiments of the first aspect.

[0024] The beneficial effects of the embodiments of the present disclosure include:

[0025] The disclosed embodiment provides a detection system for the braking performance of an unmanned vehicle and an unmanned vehicle, including: a vehicle model matching module, an expected deceleration acquisition module, an observer and an evaluation module; the output of the vehicle model matched by the unmanned vehicle, that is, the expected acceleration, is continuously adjusted by using the estimated road rolling resistance value estimated by the expected deceleration and the actual deceleration; the estimated road rolling resistance value estimated by the evaluation module and the estimated road rolling resistance threshold value corresponding to the vehicle model are used to judge whether the braking performance of the unmanned vehicle is declining. In the disclosed embodiment, firstly, by matching the corresponding vehicle model for each unmanned vehicle individual, each unmanned vehicle can be targeted to evaluate the decline of braking performance; secondly, the estimated road rolling resistance value can be evaluated according to the expected deceleration output by the vehicle model and the actual deceleration during the braking process of the unmanned vehicle, and further based on the estimated road rolling resistance value, whether the braking performance is declining is judged. It can be seen that the detection system for the braking performance of the unmanned vehicle provided by the disclosed embodiment can not only be applicable to a single unmanned vehicle individual of any vehicle type, but also can adopt an effective detection method to timely detect when the braking performance of the unmanned vehicle declines, effectively avoiding the occurrence of safety accidents caused by the decline of the vehicle braking performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A structural diagram of a braking performance detection system for an unmanned vehicle provided in an embodiment of the present disclosure;

[0027] Figure 2 A flow chart of a system for detecting the braking performance of an unmanned vehicle provided in an embodiment of the present disclosure;

[0028] Figure 3a A schematic diagram of the speed change of the unmanned vehicle when braking to a stop at 20 km / h provided by an embodiment of the present disclosure;

[0029] Figure 3b A schematic diagram of the pitch angle change of the unmanned vehicle when braking to stop at 20 km / h provided by an embodiment of the present disclosure;

[0030] Figure 4 A schematic diagram of the actual deceleration of the unmanned vehicle during braking and the estimated value of the road rolling resistance provided by the embodiment of the present disclosure;

[0031] Figure 5a This is one of the constant deceleration braking decay verification effect diagrams provided by the embodiment of the present disclosure;

[0032] Figure 5b The second constant deceleration braking decay verification effect diagram provided by the embodiment of the present disclosure;

[0033] Figure 6 The third constant deceleration braking decay verification effect diagram provided by the embodiment of the present disclosure;

[0034] Figure 7a One of the vehicle braking effect diagrams with no braking performance degradation provided by the embodiment of the present disclosure;

[0035] Figure 7b The second diagram of the braking effect of a vehicle with no braking performance degradation provided by the embodiment of the present disclosure;

[0036] Figure 8 The third diagram of the braking effect of a vehicle with no braking performance degradation provided by the embodiment of the present disclosure;

[0037] Figure 9a One of the vehicle braking effect diagrams with braking performance degradation provided by the embodiment of the present disclosure;

[0038] Figure 9b The second diagram of the braking effect of a vehicle with degraded braking performance provided by the embodiment of the present disclosure;

[0039] Fig.10 This is the third diagram of the braking effect of a vehicle with degraded braking performance provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0040] The embodiment of the present disclosure provides a detection system for the braking performance of an unmanned vehicle. The preferred embodiments of the present disclosure are described below in conjunction with the drawings of the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present disclosure, and are not used to limit the present disclosure. In addition, the embodiments and features in the embodiments of the present application can be combined with each other if there is no conflict.

[0041] The present disclosure provides a system for detecting the braking performance of an unmanned vehicle. Figure 1 As shown, including:

[0042] The vehicle model matching module 101 is used to match a pre-built vehicle model for the unmanned vehicle based on the acquired vehicle data;

[0043] The expected deceleration acquisition module 102 is used to input the braking request and the current speed of the unmanned vehicle into the vehicle model when a braking demand is generated, obtain the expected deceleration of the unmanned vehicle, and input the expected deceleration into the observer 103;

[0044] The observer 103 is used to estimate the actual deceleration of the unmanned vehicle based on the first observed value obtained by observing the actual vehicle data of the unmanned vehicle, and estimate the driving resistance of the unmanned vehicle using the expected deceleration and the actual deceleration to obtain an estimated value of the road rolling resistance, and input the estimated value of the road rolling resistance into the evaluation module 104;

[0045] The evaluation module 104 is used to determine whether the braking performance of the unmanned vehicle is degraded based on the estimated value of the road rolling resistance obtained during the braking process and the estimated threshold of the road rolling resistance corresponding to the vehicle model.

[0046] In the disclosed embodiment, a detection system for the braking performance of an unmanned vehicle can be set for each individual unmanned vehicle of various vehicle types. During implementation, a corresponding vehicle model can be matched for each individual unmanned vehicle, not only the vehicle model can be matched, but also the dynamic and static data of the vehicle can be matched more accurately (described in detail in the subsequent embodiments). In the case where the unmanned vehicle generates a braking demand, the unmanned vehicle braking system is in the process of responding to the braking request, and the detection system for the braking performance of the unmanned vehicle provided by the disclosed embodiment can also respond to the braking request at the same time. That is, the braking parameters (brake request and current vehicle speed) are input into the vehicle model to obtain the expected deceleration of the unmanned vehicle. At the same time, the observer 103 obtains the first observation value and determines the actual deceleration by observing the actual braking process of the unmanned vehicle, thereby estimating the driving resistance of the unmanned vehicle based on the expected deceleration and the actual deceleration, and obtaining the estimated value of the road rolling resistance. If the braking performance of the unmanned vehicle declines, the estimated road rolling resistance value estimated based on the actual deceleration of the unmanned vehicle will be different from the situation where the braking performance of the unmanned vehicle has not declined. Therefore, the evaluation module 104 uses this principle to determine whether the braking performance of the unmanned vehicle has declined based on the estimated road rolling resistance value and the road rolling resistance estimation threshold corresponding to the vehicle model.

[0047] In the disclosed embodiments, the above-mentioned pre-built vehicle model may adopt an existing virtual vehicle, that is, a virtual vehicle model constructed by using simulation tools based on the parameters of some iconic vehicles, to support virtual testing in different scenarios; it may also be implemented as a set of related data recorded by different real vehicle tests stored in a storage medium, and the unmanned vehicle and different data sets may be matched by comparing the vehicle data and the test data.

[0048] In the disclosed embodiment, the braking performance detection system starts to count the braking time after the braking demand is generated during the driving process of the unmanned vehicle. The braking command issued to the unmanned vehicle and the braking request input to the vehicle model can remain unchanged during the braking time; the above-mentioned braking command and braking request can be implemented as the target speed for the unmanned vehicle to take braking. That is, the braking request of the unmanned vehicle and the current speed are input into the vehicle model (the braking request is the target speed), and the rate of change between the target speed and the current speed can be used to obtain the expected deceleration of the vehicle model under ideal conditions without considering other influencing factors such as road resistance through the deceleration calculation formula.

[0049] Furthermore, after matching the pre-built vehicle model for the unmanned vehicle, during the entire braking process, the expected deceleration acquisition module 102 and the observer 103 can be executed in a loop for multiple times, and the observer 103 can input the road rolling resistance estimation values ​​obtained multiple times into the evaluation module 104. The evaluation module 104 can judge whether the braking performance of the unmanned vehicle is degraded through the road rolling resistance estimation values ​​obtained multiple times (for example: the road rolling resistance estimation values ​​obtained during the entire braking process).

[0050] In another embodiment provided by the present disclosure, the observer 103 is further used to observe the dynamic and static data of the unmanned vehicle and the braking scene to obtain a second observation value, and input the second observation value into the evaluation module 104;

[0051] The evaluation module 104 is further used to determine the weight of the second observation quantity according to the current braking scenario, perform weighted processing on the second observation quantity based on the determined weight, obtain an adjustment coefficient for the road rolling resistance estimation threshold, and use the adjustment coefficient to adjust the road rolling resistance estimation threshold.

[0052] In the disclosed embodiment, after the vehicle model is determined, it may have a corresponding road rolling resistance estimation threshold. If the estimated road rolling resistance value estimated according to the braking process of the actual unmanned vehicle is within the threshold, it can be considered that the braking performance of the unmanned vehicle is normal. If the estimated road rolling resistance value estimated according to the braking process of the actual unmanned vehicle is not within the threshold, for example: exceeds the threshold, it means that the actual unmanned vehicle consumes more energy than expected in the braking process of the current braking scenario, and it can be said that the braking performance of the unmanned vehicle may have declined.

[0053] Therefore, the second observation quantity may include physical quantities that actually affect the road resistance, such as the time of the braking process, the road slope, the road surface material, and the initial braking request, etc. For each item of the second observation quantity, the corresponding weight may be determined in combination with the actual braking scenario. During implementation, the relationship between the actual characteristics of each item of the second observation quantity and the respective weights may be stored in correspondence, so as to be used when weights need to be assigned to each item of the second observation quantity for different vehicles and different braking scenarios.

[0054] In the disclosed embodiment, the weight of the second observation quantity can be determined based on a "penalty-incentive" variable weight model, which comprehensively considers the degree of influence of each second observation quantity that will affect the road resistance on the road resistance, and calculates the dynamic weight by using the penalty-incentive variable weight principle, optimizes the calculation method of the constant weight, and adopts the weight allocation method of the road resistance influencing factors based on the variable weight model method that integrates multiple influencing factors (i.e., the second observation quantity mentioned above).

[0055] In another embodiment provided by the present disclosure, the evaluation module 104 is further configured to determine that the braking performance of the unmanned vehicle has declined when the estimated road rolling resistance value is greater than the estimated road rolling resistance threshold value for a preset number of times; or

[0056] The road rolling resistance estimation threshold includes upper and lower boundary thresholds. The evaluation module is used to determine that the braking performance of the unmanned vehicle has declined when the road rolling resistance estimation value exceeds the upper boundary threshold of the road rolling resistance estimation threshold for a preset number of times.

[0057] In the disclosed embodiment, the above-mentioned road rolling resistance estimation threshold for the unmanned vehicle can be implemented as a preset value. During the braking time, the number of times the above-mentioned road rolling resistance estimation value is greater than the preset road rolling resistance estimation threshold is counted. When the number is greater than the preset number, it can be determined that the braking performance of the unmanned vehicle has declined; wherein the above-mentioned preset number can be adjusted according to the length of the braking time.

[0058] The above-mentioned road rolling resistance estimation threshold for the unmanned vehicle is also a range, that is, it can be implemented as two preset values, namely the upper boundary threshold and the lower boundary threshold. During the braking time, the number of times the above-mentioned road rolling resistance estimation value is greater than the upper boundary threshold of the preset road rolling resistance estimation threshold is counted. When the number is greater than the preset number, it can be determined that the braking performance of the unmanned vehicle has declined; wherein the above-mentioned preset number can be adjusted according to the length of the braking time.

[0059] In another embodiment provided by the present disclosure, the evaluation module 104 is also used to count the time proportion when the road rolling resistance estimation value is higher than the road rolling resistance estimation threshold or higher than the upper boundary threshold of the road rolling resistance estimation threshold during braking, and determine that the braking performance of the unmanned vehicle has declined when the time proportion is higher than the time proportion threshold of the performance decline evaluation.

[0060] In the disclosed embodiment, the time percentage threshold of the performance degradation evaluation can be implemented as a preset value or obtained through a corresponding vehicle model. The time percentage threshold of the performance degradation evaluation can be adjusted accordingly according to the vehicle performance and actual braking conditions.

[0061] In another embodiment provided by the present disclosure, the system further includes: an expected deceleration adjustment module 105, which is used to feed back the estimated value of road rolling resistance to the vehicle model to adjust the expected deceleration output by the vehicle model.

[0062] In the disclosed embodiment, the estimated road rolling resistance value is fed back to the vehicle model, and the expected deceleration output by the vehicle model is adjusted with reference to the closed-loop control principle. The output signal of the system, the estimated road rolling resistance value, returns along the feedback channel to the vehicle model at the input end of the system, and the output expected deceleration of the vehicle model is adjusted to form a closed channel. During implementation, the expected deceleration output by the vehicle model is adjusted accordingly with reference to the estimated road rolling resistance value to make it closer to the actual deceleration of the unmanned vehicle, to verify whether the expected deceleration during the braking process of the unmanned vehicle can fit the actual deceleration, and then to determine whether the braking performance of the unmanned vehicle has declined.

[0063] In another embodiment provided by the present disclosure, the vehicle data includes: static parameters of the unmanned vehicle and dynamic parameters obtained by actually measuring the unmanned vehicle; the vehicle model matching module 101 is also used to preliminarily match the corresponding vehicle model based on the static parameters, and optimize the preliminarily matched vehicle model based on the dynamic parameters, wherein the braking capacity of the vehicle model is not lower than the specified braking capacity requirement threshold.

[0064] In the disclosed embodiments, when matching a vehicle model for an unmanned vehicle based on the acquired vehicle data, it can be implemented by matching the corresponding vehicle model based on the static parameters of the unmanned vehicle and using the vehicle model to implement relevant functions of the system; in order to make the vehicle model and the actual vehicle more compatible, it can also be implemented by preliminarily matching the corresponding vehicle model based on the static parameters of the unmanned vehicle, and optimizing the preliminarily matched vehicle model based on the measured dynamic parameters of the unmanned vehicle.

[0065] Furthermore, the braking capacity corresponding to the matched vehicle model should not violate objective facts and conform to actual physical laws, and the braking capacity of the above vehicle model should not be lower than the specified braking capacity requirement threshold.

[0066] In another embodiment provided by the present disclosure, the first observed quantity includes: a motion state parameter measured by an inertial measurement unit (IMU);

[0067] The observer 103 is also used to calculate the posture of the unmanned vehicle through the motion state parameters measured by the IMU, and obtain the acceleration and pitch angle of the unmanned vehicle; filter the acceleration to eliminate data noise caused by the unevenness of the road surface during the driving of the unmanned vehicle; and estimate the actual deceleration of the unmanned vehicle during braking based on the filtered acceleration and pitch angle.

[0068] In the disclosed embodiments, the IMU is mainly used to detect and measure acceleration, tilt, shock, vibration, rotation and multi-degree-of-freedom motion; it refers to a device that uses an accelerometer and a gyroscope to measure the single-axis, dual-axis or tri-axis attitude angle (or angular rate) and acceleration of an object. The acceleration and pitch angle can be measured by the IMU sensor, and the data can be filtered to eliminate data noise, so that subsequent estimates are closer to the actual deceleration. The actual deceleration of the vehicle during braking is estimated by combining the acceleration and pitch angle measured by the sensor.

[0069] In another embodiment provided by the present disclosure, the second observation amount may include at least one of the following:

[0070] Duration of the braking process, road grade, and initial braking request.

[0071] In another embodiment provided by the present disclosure, the static parameter includes at least one of the vehicle type, model and vehicle weight; and / or,

[0072] The dynamic parameter includes at least one of speed, deceleration and braking distance.

[0073] The specific working process of the unmanned vehicle braking performance detection system provided by the present disclosure can be referred to Figure 2 Implementation.

[0074] In order to understand the effect of the above system, the measured data is plotted, as shown in the figure. Figure 3a , 3b , Figure 4 As shown in the figure, the unmanned vehicle starts braking from 20 km / h. Taking constant braking request braking as an example, the observer obtains an equivalent estimated value of the road rolling resistance based on the expected deceleration of the vehicle model and the actual deceleration estimated by the observer, and feeds it back to the vehicle model to dynamically adjust the expected acceleration output by the vehicle model. Figure 4 Braking process observation variables flag (1: in the braking process, 0: brake exit), observe (estimated road rolling resistance), acceleration-time (blue: vehicle model expected acceleration, yellow: estimated actual acceleration)

[0075] At constant deceleration, the braking fade verification effect is as follows Figure 5a , 5b , Figure 6 As shown; among them, Figure 6 Braking process observation variables flag (1: in the braking process, 0: braking exit), observe (estimated road rolling resistance), acceleration-time (blue: expected acceleration of vehicle model, yellow: estimated actual acceleration).

[0076] This system is used to verify the braking degradation. When the braking performance of the unmanned vehicle is not degraded, the braking effect of the unmanned vehicle is as follows: Figure 7a , 7b , Figure 8 As shown in the figure, the fitting rate between the expected acceleration and the actual acceleration of the unmanned vehicle is high, and the number and time proportion of the estimated road rolling resistance values ​​determined by both of them being greater than the threshold are both lower than the setting, so it can be determined that the braking performance of the unmanned vehicle has not declined. Among them, Figure 8 Braking process observation variables flag (1: in the braking process, 0: braking exit), observe (estimated road rolling resistance), acceleration-time (blue: expected acceleration of vehicle model, yellow: estimated actual acceleration).

[0077] When the braking performance of the unmanned vehicle declines, the braking effect of the unmanned vehicle is Figure 9a , 9b , Fig.10 As shown in the figure, the fitting rate between the expected acceleration and the actual acceleration of the unmanned vehicle is obviously low, and the number and time proportion of the estimated road rolling resistance values ​​determined by both of them being greater than the threshold are both higher than the setting, so it can be determined that the braking performance of the unmanned vehicle has declined. Among them, Fig.10 Braking process observation variables flag (1: in the braking process, 0: braking exit), observe (estimated road rolling resistance), acceleration-time (blue: expected acceleration of vehicle model, yellow: estimated actual acceleration).

[0078] Based on the same disclosed concept, the disclosed embodiment also provides an unmanned vehicle. Since the principle of the problem solved by the unmanned vehicle is similar to that of the aforementioned unmanned vehicle braking performance detection system, the implementation of the unmanned vehicle can refer to the implementation of the aforementioned detection system, and the repeated parts will not be repeated.

[0079] Through the description of the above implementation methods, those skilled in the art can clearly understand that the embodiments of the present disclosure can be implemented by hardware, or by software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the system described in each embodiment of the present disclosure.

[0080] Those skilled in the art will appreciate that the accompanying drawings are merely schematic diagrams of a preferred embodiment, and the modules or processes in the accompanying drawings are not necessarily required for implementing the present disclosure.

[0081] Those skilled in the art can understand that the modules in the system in the embodiment can be distributed in the system of the embodiment according to the description of the embodiment, or can be changed accordingly and located in one or more systems different from the present embodiment. The modules in the above embodiment can be combined into one module, or can be further divided into multiple sub-modules.

[0082] The serial numbers of the above-mentioned embodiments of the present disclosure are only for description and do not represent the advantages or disadvantages of the embodiments.

[0083] Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is also intended to include these modifications and variations.

Claims

1. A detection system for the braking performance of an unmanned vehicle. It is characterized in that include: A vehicle model matching module, used to match a pre-built vehicle model for the unmanned vehicle based on the acquired vehicle data; an expected deceleration acquisition module, used for inputting the braking request and current vehicle speed of the unmanned vehicle into the vehicle model when a braking demand is generated, obtaining an expected deceleration of the unmanned vehicle, and inputting the expected deceleration into an observer; The observer is used to estimate the actual deceleration of the unmanned vehicle based on a first observation value obtained by observing the actual vehicle data of the unmanned vehicle, and estimate the driving resistance of the unmanned vehicle using the expected deceleration and the actual deceleration to obtain an estimated value of road rolling resistance, and input the estimated value of road rolling resistance into an evaluation module; The evaluation module is used to determine whether the braking performance of the unmanned vehicle is degraded based on the estimated value of road rolling resistance obtained during braking and the estimated threshold of road rolling resistance corresponding to the vehicle model.

2. The system according to claim 1, It is characterized in that The observer is further used to observe the dynamic and static data of the unmanned vehicle and the braking scene to obtain a second observation value, and input the second observation value into the evaluation module; The evaluation module is also used to determine the weight of the second observation quantity according to the current braking scenario, perform weighted processing on the second observation quantity based on the determined weight, obtain an adjustment coefficient for the road rolling resistance estimation threshold, and use the adjustment coefficient to adjust the road rolling resistance estimation threshold.

3. The system according to claim 1 or 2, It is characterized in that The evaluation module is further configured to determine that the braking performance of the unmanned vehicle has declined when the estimated road rolling resistance value is greater than the estimated road rolling resistance threshold value for a preset number of times; or The road rolling resistance estimation threshold includes upper and lower boundary thresholds, and the evaluation module is used to determine that the braking performance of the unmanned vehicle has declined when the road rolling resistance estimation value is greater than the upper boundary threshold of the road rolling resistance estimation threshold for a preset number of times.

4. The system according to claim 1 or 2, It is characterized in that The evaluation module is also used to count the time proportion of the estimated road rolling resistance value during braking that is higher than the road rolling resistance estimation threshold or higher than the upper boundary threshold of the road rolling resistance estimation threshold, and determine that the braking performance of the unmanned vehicle has declined when the time proportion is higher than the time proportion threshold for performance decline evaluation.

5. The system according to claim 1, It is characterized in that Also includes: The expected deceleration adjustment module is used to feed back the estimated value of the road rolling resistance to the vehicle model to adjust the expected deceleration output by the vehicle model.

6. The system of claim 1, It is characterized in that The vehicle data includes: static parameters of the unmanned vehicle and dynamic parameters obtained by actual measurement of the unmanned vehicle; the vehicle model matching module is also used to preliminarily match the corresponding vehicle model based on the static parameters, and optimize the preliminarily matched vehicle model based on the dynamic parameters, wherein the braking capacity of the vehicle model is not lower than a specified braking capacity requirement threshold.

7. The system of claim 1, It is characterized in that The first observed quantity includes: motion state parameters measured by an inertial measurement unit IMU; The observer is also used to calculate the posture of the unmanned vehicle through the motion state parameters measured by the IMU, and obtain the acceleration and pitch angle of the unmanned vehicle; filter the acceleration to eliminate data noise caused by the unevenness of the road surface during the driving of the unmanned vehicle; and estimate the actual deceleration of the unmanned vehicle during braking based on the filtered acceleration and the pitch angle.

8. The system of claim 2, It is characterized in that The second observation includes at least one of the following: Duration of the braking process, road grade, and initial braking request.

9. The system according to claim 6, It is characterized in that The static parameters include at least one of vehicle type, model and vehicle weight; and / or, The dynamic parameter includes at least one of speed, deceleration and braking distance.

10. An unmanned vehicle, It is characterized in that A system for detecting the braking performance of an unmanned vehicle comprising any one of claims 1-9.

Images