CN114550442B - Automatic driving vehicle state evaluation and early warning method based on vehicle-road cooperation - Google Patents
Automatic driving vehicle state evaluation and early warning method based on vehicle-road cooperation Download PDFInfo
- Publication number
- CN114550442B CN114550442B CN202111675077.5A CN202111675077A CN114550442B CN 114550442 B CN114550442 B CN 114550442B CN 202111675077 A CN202111675077 A CN 202111675077A CN 114550442 B CN114550442 B CN 114550442B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- road
- automatic driving
- data
- uncomfortable
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 71
- 238000011156 evaluation Methods 0.000 title claims abstract description 59
- 206010000117 Abnormal behaviour Diseases 0.000 claims abstract description 12
- 230000008569 process Effects 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims abstract description 5
- 230000001133 acceleration Effects 0.000 claims description 59
- 238000001914 filtration Methods 0.000 claims description 18
- 230000036461 convulsion Effects 0.000 claims description 16
- 230000003238 somatosensory effect Effects 0.000 claims description 16
- 230000002159 abnormal effect Effects 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims 2
- 238000007619 statistical method Methods 0.000 claims 1
- 238000000605 extraction Methods 0.000 abstract description 3
- 230000008901 benefit Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an automatic driving vehicle state evaluation and early warning method based on vehicle-road cooperation, which relates to the technical field of road traffic, wherein the evaluation comprises two parts: the method comprises the steps of evaluating the comfort level of the passenger body feeling in the whole running process of the automatic driving vehicle, evaluating the safety states of passengers and vehicles in the whole running process of the automatic driving vehicle, collecting the running data of the automatic driving vehicle and the non-automatic driving vehicle through a road end, fusing the running data collected by the automatic driving vehicle end, carrying out data processing and feature extraction, and establishing an objective standard for evaluating the comfort level of the passenger body feeling of the automatic driving vehicle, wherein the objective standard can be used as a state constraint of path planning; through learning and training the large amount of data, the abnormal behavior of the automatic driving vehicle can be predicted on line, and when the unsafe state of the vehicle is predicted, the abnormal behavior can be early warned to a vehicle safety officer or a remote monitoring center, the vehicle is taken over in time, and the unsafe state is separated.
Description
Technical Field
The invention relates to the technical field of road traffic, in particular to an automatic driving vehicle state evaluation and early warning method based on vehicle-road cooperation.
Background
The automated driving vehicle state assessment includes: 1. the method comprises the following steps of evaluating the comfort level state of the body feeling of an occupant in the whole running process of an automatic driving vehicle; 2. and (5) evaluating the safety state of the passengers and the vehicle in the whole process of automatic driving. At present, only a vehicle end is used for collecting driving data, and compared with data collected by a road end, the collected data is single, has no universality, and has a small data volume, so that the data characteristic extraction is not facilitated; the comfort level evaluation depends on the built vehicle comfort level prediction model, the prediction accuracy can not be ensured, and the influence of factors such as road surface quality, gradient and the like is larger; the comfort evaluation standard is subjective evaluation, and an objective and referenceable evaluation system is absent; emergency safeguards only occur when abnormal conditions occur in the vehicle, and such a take over generally lacks environmental suitability.
Disclosure of Invention
Aiming at the technical problems and overcoming the defects of the prior art, the invention provides an automatic driving vehicle state evaluation and early warning method based on vehicle-road cooperation, which comprises the following steps:
s1, data acquisition based on vehicle-road cooperative technology
S1.1, for a road end side, acquiring driving data of an automatic driving vehicle and a non-automatic driving vehicle passing through a road section through a sensing system of a road side unit, and uploading the driving data to a cloud platform through a road side unit network layer;
s1.2, for a vehicle end side, an automatic driving vehicle is driven by a driver, vehicle driving data are collected by means of a vehicle-mounted sensing layer, and the driving data are transmitted to a cloud platform through a vehicle-mounted network terminal;
s2, evaluation of comfort level state of body feeling
S2.1, body feeling comfort degree evaluation index: accx: longitudinal acceleration, m/s 2 The method comprises the steps of carrying out a first treatment on the surface of the decx: longitudinal deceleration, m/s 2 The method comprises the steps of carrying out a first treatment on the surface of the accy: lateral acceleration, m/s 2 The method comprises the steps of carrying out a first treatment on the surface of the jerkx: longitudinal jerk, m/s 3 The method comprises the steps of carrying out a first treatment on the surface of the jerky: lateral jerk, m/s 3 ；
S2.2, calculating body feeling comfort data;
s2.3, a comfort level evaluation standard is obtained, and comfort level index standard reference values under different speeds and curvatures are obtained according to different rules;
s2.4, on-line evaluation of somatosensory comfort: designing hysteresis logic and hysteresis curved surfaces, comparing the hysteresis section values according to the somatosensory data values and the standard somatosensory data in an online mode, and outputting the specific type of the uncomfortable state, the times of the uncomfortable state in one automatic driving process and the proportion of the uncomfortable time to the total driving time;
s3, safety state assessment and early warning
The method comprises the steps of acquiring a large amount of data covered by multiple scenes through a vehicle-road cooperation technology as a data set for offline training of a neural network model, outputting the model to be used for online prediction of vehicles which are automatically driven and social vehicles within a certain range in future time or not.
The technical scheme of the invention is as follows:
in the foregoing method for evaluating and early warning the state of an automatically driven vehicle based on vehicle-road coordination, in S1.1, the driving data includes a plurality of pieces of information including a position of a coordinate point of the vehicle in a global coordinate system, a longitudinal speed and acceleration, a lateral speed and acceleration, a heading angle of the vehicle, a curvature of a road, and a steering radius.
In the foregoing automatic driving vehicle state evaluation and early warning method based on vehicle-road coordination, in S1.1, the sensing system includes a laser radar, a camera, and a millimeter wave radar, and in S1.2, the vehicle-mounted sensing layer includes an IMU, a laser radar, and a millimeter wave radar.
The foregoing method for evaluating and early warning the state of the automatic driving vehicle based on the vehicle-road cooperation comprises the following steps of S2.2 body feeling comfort data calculation:
accx: vehicle end: according to the position coordinate information differential calculation, longitudinal acceleration is obtained, second-order low-pass filtering is carried out to obtain est_accx, second-order low-pass filtering is carried out to the acceleration information obtained based on the IMU to obtain imu_accx, confidence proportions are added to the two acceleration values to obtain ax_filtered=ka_est_accx+kb_imu_accx, and a final longitudinal acceleration value accx is obtained through zero-crossing detection; road end: according to the position coordinate information, longitudinal acceleration is obtained through differential calculation, second-order low-pass filtering is carried out to obtain est_accx, and a final longitudinal acceleration value accx is obtained through zero-crossing detection;
decx: consistent with the accx calculation method, obtaining a final longitudinal acceleration value decx through zero crossing detection;
accy: calculating current running road curvature information kappa=dyaw/ds according to the position information, wherein dyaw is course angle change in unit time, and ds is vehicle position change in unit time; vehicle end: performing first-order low-pass filtering on the basis of the lateral acceleration data of the IMU to obtain imu_accy; road end: calculating est_accy by a position difference method;
jerkx: differentiating based on the longitudinal acceleration to obtain a longitudinal acceleration change rate jerk, and performing mean value filtering to obtain est_jerkx;
jerky: and differentiating based on the lateral acceleration to obtain a lateral acceleration change rate jerk, and performing robust mean filtering to obtain est_jerky.
The foregoing method for evaluating and early warning the state of the automatic driving vehicle based on the vehicle-road cooperation, S2.3 body feeling comfort evaluation criteria:
(1) Processing vehicle driving data obtained by vehicle-road cooperation, calculating the curvature of the vehicle driving route at each moment and the current speed of the vehicle, and obtaining each driving comfort index value at the curvature-speed, so that a huge data lattice set is formed, and five curvature-speed-comfort index scattered point distributions can be obtained by separating the data lattice set;
(2) Defining a speed anchor point and a curvature anchor point, wherein the minimum turning diameter of the passenger car is 9.0-12.0m, and the curvature interval is 0-0.2m -1 Interval size 0.02, i.e. [0:0.02:0.2 ]]The vehicle speed interval is designed to be 0-22m/s, and the interval size is 1.0, namely [ 0:1:22:]；
(3) Screening out bad data, traversing a speed anchor point and a curvature anchor point, calculating extreme values, average values, mean square deviations, 25%, 50% and 75% data value distribution points of various comfort indexes in the range of the anchor point interval, and fitting the data by using a moving least square method;
(4) Comparing and analyzing three data of vehicle end data, road end data and vehicle-road cooperation;
(5) And obtaining the standard reference values of the comfort index under different speeds and curvatures according to different rules.
In the foregoing automatic driving vehicle state evaluation and early warning method based on vehicle-road coordination, S2.3 (5), the evaluation function is designed, or the penalty coefficient is modified to obtain a suitable reference standard value, or the gaussian function is used as the membership function and then subjected to the sharpness processing to obtain the reference standard value.
According to the automatic driving vehicle state evaluation and early warning method based on the vehicle-road cooperation, S2.3, 75% numerical distribution points are selected as comfort level reference standard values.
According to the automatic driving vehicle state evaluation and early warning method based on the vehicle-road cooperation, S2.4, the upper limit and the lower limit of the hysteresis of the standard somatosensory data under the current kappa and speed are obtained through interpolation calculation by adopting a curved surface interpolation method, and the somatosensory comfort degree is evaluated on line according to the obtained standard interval and logic.
The foregoing method for evaluating and early warning the state of an automatic driving vehicle based on vehicle-road coordination, S2, obtains the overall comfort level evaluation and comparison level corresponding to the uncomfortable times and uncomfortable time proportion according to the fuzzy statistics method, and specifically includes the following steps:
(1) The automatic driving time is less than or equal to 10mins
The uncomfortable times are less than or equal to 6 times, the uncomfortable time proportion is less than or equal to 10 percent, and the comfort level is high;
the uncomfortable times are less than or equal to 18 times, the uncomfortable time proportion is less than or equal to 25%, and the comfort level is medium;
the uncomfortable times are less than or equal to 30 times, the uncomfortable time proportion is less than or equal to 40%, and the comfort level is low;
(2) The automatic driving time is less than or equal to 20mins
The uncomfortable times are less than or equal to 15 times, the uncomfortable time proportion is less than or equal to 15 percent, and the comfort level is high;
the uncomfortable times are less than or equal to 45 times, the uncomfortable time proportion is less than or equal to 30 percent, and the comfort level is medium;
the uncomfortable times are less than or equal to 80 times, the uncomfortable time proportion is less than or equal to 45%, and the comfort level is low;
(3) The automatic driving time is less than or equal to 40mins
The uncomfortable times are less than or equal to 45 times, the uncomfortable time proportion is less than or equal to 20 percent, and the comfort level is high;
the uncomfortable times are less than or equal to 150 times, the uncomfortable time proportion is less than or equal to 35%, and the comfort level is medium;
the uncomfortable times are less than or equal to 300 times, the uncomfortable time proportion is less than or equal to 50 percent, and the comfort level is low.
The third step, the abnormal behavior comprises abnormal stopping, abnormal acceleration, abnormal deceleration, abnormal steering wheel large-amplitude rotation and collision risk.
The beneficial effects of the invention are as follows:
(1) According to the invention, the road end is used for collecting the running data of the automatic driving vehicle and the non-automatic driving vehicle, the running data collected by the automatic driving vehicle end is fused, the data processing and the feature extraction are carried out, and the objective evaluation standard of the body feeling comfort of the passengers of the automatic driving vehicle is established, so that the system can be used as the state constraint of path planning; through learning and training the large amount of data, the abnormal behavior of the automatic driving vehicle can be predicted on line, and when the unsafe state of the vehicle is predicted, the abnormal behavior is early-warned to a vehicle safety officer or a remote monitoring center, vehicle taking over is performed in time, and the unsafe state is separated;
(2) The invention fully utilizes the quantity, stability and full-time working advantages of road end equipment, acquires the vehicle running information under a specific road section through the road end side, can acquire the driving data of a plurality of social vehicles, and has the advantages of wide sampling coverage, large data volume and high efficiency; the vehicle end side is used for collecting data, so that the method has the advantages of complex driving scene and accurate data collection; therefore, the data can be mutually supplemented by the data acquisition method of the vehicle-road cooperative technology, a large amount of driving data can be rapidly acquired, and the data can be compared and analyzed;
(3) According to the invention, by means of massive vehicle driving data, the data are fully analyzed and statistically processed, and an objective evaluation system of longitudinal acceleration, longitudinal deceleration, transverse acceleration, longitudinal jerk and transverse jerk of the automatic driving vehicle under different speeds and different curvatures is established, so that comfort evaluation is digitized;
(4) According to the invention, the data are learned and trained to obtain a vehicle behavior prediction model, the dynamics of the output vehicle is predicted, when the vehicle predicts abnormal parking, sudden acceleration, steering wheel slamming and other abnormal behaviors deviating from the planned track or the surrounding vehicles possibly generate collision risks to the vehicle, the early warning information is early-warned to the vehicle safety personnel or uploaded to a remote monitoring center, and real-time panoramic intervention is performed, so that the safety of the vehicle and passengers is ensured.
Drawings
FIG. 1 is a data acquisition method based on a vehicle-road cooperative technology;
FIG. 2 is a method for establishing a body comfort level evaluation criterion;
FIG. 3 is a comfort evaluation criteria;
FIG. 4 is a method for on-line assessment of somatosensory comfort;
fig. 5 shows the result of the decx interpolation hysteresis interval.
Detailed Description
The method for evaluating and early warning the state of the automatic driving vehicle based on the vehicle-road cooperation provided by the embodiment specifically comprises the following steps:
1. data acquisition based on vehicle-road cooperation technology
As in the case of figure 1,
for the road end side, driving data (including multiple information such as vehicle coordinate point position, longitudinal speed and acceleration, transverse speed and acceleration, vehicle course angle, road curvature, steering radius and the like under a global coordinate system) of an automatic driving vehicle and a non-automatic driving vehicle passing through a road section are collected through a sensing system (laser radar, a camera, millimeter wave radar and the like) of a road side unit, and the driving data are uploaded to a cloud platform through a road side unit network layer.
And secondly, for the vehicle end side, the automatic driving vehicle is driven by a driver, vehicle driving data are collected by means of an on-board sensing layer (IMU, laser radar, millimeter wave radar and the like), and the driving data are transmitted to a cloud platform through an on-board network terminal.
2. Somatosensory comfort state assessment
For an automatic driving vehicle, the automatic driving is realized in each scene, the indexes for evaluating the quality of the automatic driving comprise comfort feeling of riding passengers, and the driving comfort has different evaluation standards for different people, so that the automatic driving vehicle is subjective and personal feeling.
Body feeling comfort degree evaluation index
accx: longitudinal acceleration, m/s 2 ；
decx: longitudinal deceleration, m/s 2 ；
accy: lateral acceleration, m/s 2 ；
jerkx: longitudinal jerk, m/s 3 ；
jerky: lateral jerk, m/s 3 ；
In the transverse direction, the left and right body feeling of the passengers is not bad due to bilateral symmetry, so that the left and right are not distinguished; in the longitudinal direction, the member has a large difference in body feeling for the forward direction and the backward direction, and thus the acceleration in the longitudinal direction is subdivided into the acceleration in the forward direction and the acceleration in the backward direction.
(II) somatosensory comfort data calculation
accx: vehicle end: according to the position coordinate information differential calculation, longitudinal acceleration is obtained, second-order low-pass filtering is carried out to obtain est_accx, second-order low-pass filtering is carried out to the acceleration information obtained based on the IMU to obtain imu_accx, confidence proportions are added to the two acceleration values to obtain ax_filtered=ka_est_accx+kb_imu_accx, and a final longitudinal acceleration value accx is obtained through zero-crossing detection; road end: according to the position coordinate information, longitudinal acceleration is obtained through differential calculation, second-order low-pass filtering is carried out to obtain est_accx, and a final longitudinal acceleration value accx is obtained through zero-crossing detection;
decx: consistent with the accx calculation method, obtaining a final longitudinal acceleration value decx through zero crossing detection;
accy: calculating current running road curvature information kappa=dyaw/ds according to the position information, wherein dyaw is course angle change in unit time, and ds is vehicle position change in unit time; vehicle end: performing first-order low-pass filtering on the basis of the lateral acceleration data of the IMU to obtain imu_accy; road end: calculating est_accy by a position difference method;
jerkx: differentiating based on the longitudinal acceleration to obtain a longitudinal acceleration change rate jerk, and performing mean value filtering to obtain est_jerkx;
jerky: and differentiating based on the lateral acceleration to obtain a lateral acceleration change rate jerk, and performing robust mean filtering to obtain est_jerky.
Third, body feeling comfort evaluation criterion
As shown in figure 2 of the drawings,
(1) Processing vehicle driving data obtained by vehicle-road cooperation, calculating the curvature of the vehicle driving route at each moment and the current speed of the vehicle, and obtaining each driving comfort index value at the curvature-speed, so that a huge data lattice set is formed, and five curvature-speed-comfort index scattered point distributions can be obtained by separating the data lattice set;
(2) Defining a speed anchor point and a curvature anchor point, wherein the minimum turning diameter of the passenger car is 9.0-12.0m, and the curvature interval is 0-0.2m -1 Interval size 0.02, i.e. [0:0.02:0.2 ]]The vehicle speed interval is designed to be 0-22m/s, and the interval size is 1.0, namely [ 0:1:22:]；
(3) Screening out bad data, traversing a speed anchor point and a curvature anchor point, calculating extreme values, average values, mean square deviations, 25%, 50% and 75% data value distribution points of various comfort indexes in the range of the anchor point interval, and fitting the data by using a moving least square method;
(4) Comparing and analyzing three data of vehicle end data, road end data and vehicle-road cooperation;
(5) The comfort index standard reference values under different speeds and curvatures are obtained according to different rules, for example, a proper reference standard value can be obtained by modifying a punishment coefficient in a mode of designing an evaluation function, or a Gaussian function can be used as a membership function and then subjected to a sharpening process to obtain the reference standard value.
The present invention selects 75% of the numerical distribution points as the comfort level reference standard values, and the obtained result is shown in fig. 3.
(IV) on-line assessment of somatosensory comfort
The objective evaluation standard of the driving comfort is provided, so that whether the driving comfort is in a comfortable driving state at present can be judged according to the standard, but when the calculated driving comfort index fluctuates up and down at the standard value, the judgment result is caused to vibrate, the accurate judgment cannot be performed, and therefore hysteresis logic and a hysteresis curved surface are designed. Referring to fig. 4, in the on-line mode, according to the position, speed and acceleration information, calculating the current kappa and speed and the corresponding comfort index values, comparing the motion sensing data values with the standard motion sensing data hysteresis interval values, and interpolating by using a curved surface interpolation method to obtain the upper and lower limits of the hysteresis of the standard motion sensing data under the current kappa and speed, taking decx as an example, and interpolating the hysteresis interval when evaluating the comfort in real time, as shown in fig. 5. According to the obtained standard interval and logic, the on-line evaluation of the body feeling comfort level can output the specific type of the uncomfortable state, the times of the uncomfortable state in one automatic driving process and the proportion of the uncomfortable time to the total driving time.
Further, the overall comfort evaluation comparison level table corresponding to the uncomfortable times and uncomfortable time proportion can be obtained according to the fuzzy statistics method, for example, the following steps are adopted:
3. safety state assessment and early warning
The method comprises the steps that a large amount of data covered by multiple scenes acquired through a vehicle-road cooperation technology is used as a data set for offline training of a neural network model, and the model is output to judge whether abnormal behaviors of a vehicle occur in a future period of time, wherein the abnormal behaviors comprise abnormal parking, abnormal acceleration, abnormal deceleration and large-amplitude rotation of an abnormal steering wheel and collision risks; the model is used for self-automatic driving vehicles and social vehicles in a certain range on-line prediction, if abnormal behaviors of the self-vehicle or collision threat of surrounding vehicles to the self-vehicle are predicted in a specified step length, the self-vehicle is early-warned to the on-vehicle safety personnel if the on-vehicle safety personnel are on the spot, the safety personnel and the vehicles are ensured by on-site intervention of the safety personnel, and if the on-vehicle safety personnel are not on the spot, early warning signals are uploaded to a remote monitoring center, and the safety personnel and the vehicles are ensured by remote panoramic intervention of the safety personnel or automatic safety pre-proposal.
The scheme has the following effects:
(1) The method has the advantages that the data acquisition advantage of road end-vehicle end coordination is fully exerted, and the driving data with the characteristics of wide coverage samples, various scenes, huge body volume and mutual complementation can be efficiently acquired;
(2) Establishing an automatic driving comfort objective evaluation system of longitudinal acceleration, longitudinal deceleration, transverse acceleration, longitudinal jerk and transverse jerk of the automatic driving vehicle under different speeds and different curvatures, evaluating the driving comfort of the automatic driving vehicle on line according to the system, wherein the obtained reference standard value can be used as a state constraint during development of an automatic driving planning control algorithm to guide more reasonable track development;
(3) The neural network is trained based on massive data, abnormal behaviors of the vehicle and surrounding vehicles within a certain range can be predicted on line, and when the abnormal behaviors occur, early warning is carried out to a vehicle-mounted safety officer or a remote monitoring center in time, and intervention measures are taken in time to ensure the safety of passengers and vehicles.
In addition to the embodiments described above, other embodiments of the invention are possible. All technical schemes formed by equivalent substitution or equivalent transformation fall within the protection scope of the invention.
Claims (9)
1. An automatic driving vehicle state evaluation and early warning method based on vehicle-road cooperation is characterized in that: comprising the following steps:
s1, data acquisition based on vehicle-road cooperation technology
S1.1, for a road end side, acquiring driving data of an automatic driving vehicle and a non-automatic driving vehicle passing through a road section through a sensing system of a road side unit, and uploading the driving data to a cloud platform through a road side unit network layer;
s1.2, for a vehicle end side, an automatic driving vehicle is driven by a driver, vehicle driving data are collected by means of a vehicle-mounted sensing layer, and the driving data are transmitted to a cloud platform through a vehicle-mounted network terminal;
s2, evaluation of somatosensory comfort degree state
S2.1, body feeling comfort degree evaluation index: accx: longitudinal acceleration, m/s 2 The method comprises the steps of carrying out a first treatment on the surface of the decx: longitudinal deceleration, m/s 2 The method comprises the steps of carrying out a first treatment on the surface of the accy: lateral acceleration, m/s 2 The method comprises the steps of carrying out a first treatment on the surface of the jerkx: longitudinal jerk, m/s 3 The method comprises the steps of carrying out a first treatment on the surface of the jerky: lateral jerk, m/s 3 ；
S2.2, calculating body feeling comfort data;
s2.3, a comfort level evaluation standard is obtained according to different rules, and comfort level index standard reference values under different speeds and curvatures are obtained, wherein the method comprises the following steps:
(1) Processing vehicle driving data obtained by vehicle-road cooperation, calculating the curvature of the vehicle driving route at each moment and the current speed of the vehicle, and obtaining each driving comfort index value at the curvature-speed, so that a huge data lattice set is formed, and five curvature-speed-comfort index scattered point distributions can be obtained by separating the data lattice set;
(2) Defining a speed anchor point and a curvature anchor point, wherein the minimum turning diameter of the passenger car is 9.0-12.0m, and the curvature interval is 0-0.2m -1 Interval size 0.02, i.e. [0:0.02:0.2 ]]The vehicle speed interval is designed to be 0-22m/s, and the interval size is 1.0, namely [ 0:1:22:]；
(3) Screening out bad data, traversing a speed anchor point and a curvature anchor point, calculating extreme values, average values, mean square deviations, 25%, 50% and 75% data value distribution points of various comfort indexes in the range of the anchor point interval, and fitting the data by using a moving least square method;
(4) Comparing and analyzing three data of vehicle end data, road end data and vehicle-road cooperation;
s2.4, on-line evaluation of somatosensory comfort: designing hysteresis logic and hysteresis curved surfaces, comparing the hysteresis section values according to the somatosensory data values and the standard somatosensory data in an online mode, and outputting the specific type of the uncomfortable state, the times of the uncomfortable state in one automatic driving process and the proportion of the uncomfortable time to the total driving time;
s3, safety state assessment and early warning
The method comprises the steps of acquiring a large amount of data covered by multiple scenes through a vehicle-road cooperation technology as a data set for offline training of a neural network model, outputting the model to be used for online prediction of vehicles which are automatically driven and social vehicles within a certain range in future time or not.
2. The vehicle-road-coordination-based automatic driving vehicle state evaluation and early warning method according to claim 1, wherein the vehicle-road-coordination-based automatic driving vehicle state evaluation and early warning method is characterized by comprising the following steps of: in S1.1, the driving data includes a plurality of pieces of information including a vehicle coordinate point position, a longitudinal speed and acceleration, a lateral speed and acceleration, a vehicle course angle, a road curvature, and a steering radius in a global coordinate system.
3. The vehicle-road-coordination-based automatic driving vehicle state evaluation and early warning method according to claim 1, wherein the vehicle-road-coordination-based automatic driving vehicle state evaluation and early warning method is characterized by comprising the following steps of: in the S1.1, the perception system comprises a laser radar, a camera and a millimeter wave radar, and in the S1.2, the vehicle-mounted perception layer comprises an IMU, the laser radar and the millimeter wave radar.
4. The vehicle-road-coordination-based automatic driving vehicle state evaluation and early warning method according to claim 1, wherein the vehicle-road-coordination-based automatic driving vehicle state evaluation and early warning method is characterized by comprising the following steps of: the S2.2 body feeling comfort data calculation comprises the following steps of:
accx: vehicle end: according to the position coordinate information differential calculation, longitudinal acceleration is obtained, second-order low-pass filtering is carried out to obtain est_accx, second-order low-pass filtering is carried out to the acceleration information obtained based on the IMU to obtain imu_accx, confidence proportions are added to the two acceleration values to obtain ax_filtered=ka_est_accx+kb_imu_accx, and a final longitudinal acceleration value accx is obtained through zero-crossing detection; road end: according to the position coordinate information, longitudinal acceleration is obtained through differential calculation, second-order low-pass filtering is carried out to obtain est_accx, and a final longitudinal acceleration value accx is obtained through zero-crossing detection;
decx: consistent with the accx calculation method, obtaining a final longitudinal deceleration value decx through zero crossing detection;
accy: calculating current running road curvature information kappa=dyaw/ds according to the position information, wherein dyaw is course angle change in unit time, and ds is vehicle position change in unit time; vehicle end: performing first-order low-pass filtering on the basis of the lateral acceleration data of the IMU to obtain imu_accy; road end: calculating est_accy by a position difference method;
jerkx: differentiating based on the longitudinal acceleration to obtain a longitudinal acceleration change rate jerk, and performing mean value filtering to obtain est_jerkx;
jerky: and differentiating based on the lateral acceleration to obtain a lateral acceleration change rate jerk, and performing robust mean filtering to obtain est_jerky.
5. The vehicle-road-coordination-based automatic driving vehicle state evaluation and early warning method according to claim 1, wherein the vehicle-road-coordination-based automatic driving vehicle state evaluation and early warning method is characterized by comprising the following steps of: and S2.3 (5), designing an evaluation function, or modifying a punishment coefficient to obtain a proper comfort index standard reference value, or taking a Gaussian function as a membership function and then performing a sharpening process to obtain the comfort index standard reference value.
6. The vehicle-road-coordination-based automatic driving vehicle state evaluation and early warning method according to claim 1, wherein the vehicle-road-coordination-based automatic driving vehicle state evaluation and early warning method is characterized by comprising the following steps of: and S2.3, selecting 75% numerical distribution points as comfort index standard reference values.
7. The vehicle-road-coordination-based automatic driving vehicle state evaluation and early warning method according to claim 1, wherein the vehicle-road-coordination-based automatic driving vehicle state evaluation and early warning method is characterized by comprising the following steps of: and S2.4, interpolating and calculating by adopting a curved surface interpolation method to obtain the upper limit and the lower limit of the hysteresis of the standard somatosensory data under the current kappa and speed, and carrying out on-line evaluation on the somatosensory comfort degree according to the obtained upper limit and lower limit of the hysteresis of the standard somatosensory data.
8. The vehicle-road-coordination-based automatic driving vehicle state evaluation and early warning method according to claim 1, wherein the vehicle-road-coordination-based automatic driving vehicle state evaluation and early warning method is characterized by comprising the following steps of: s2, obtaining an overall comfort level evaluation comparison grade corresponding to uncomfortable times and uncomfortable time proportion according to a fuzzy statistical method, wherein the overall comfort level evaluation comparison grade is specifically as follows:
(1) The automatic driving time is less than or equal to 10mins
The uncomfortable times are less than or equal to 6 times, the uncomfortable time proportion is less than or equal to 10 percent, and the comfort level is high;
the uncomfortable times are less than or equal to 18 times, the uncomfortable time proportion is less than or equal to 25%, and the comfort level is medium;
the uncomfortable times are less than or equal to 30 times, the uncomfortable time proportion is less than or equal to 40%, and the comfort level is low;
(2) The automatic driving time is less than or equal to 20mins
The uncomfortable times are less than or equal to 15 times, the uncomfortable time proportion is less than or equal to 15 percent, and the comfort level is high;
the uncomfortable times are less than or equal to 45 times, the uncomfortable time proportion is less than or equal to 30 percent, and the comfort level is medium;
the uncomfortable times are less than or equal to 80 times, the uncomfortable time proportion is less than or equal to 45%, and the comfort level is low;
(3) The automatic driving time is less than or equal to 40mins
The uncomfortable times are less than or equal to 45 times, the uncomfortable time proportion is less than or equal to 20 percent, and the comfort level is high;
the uncomfortable times are less than or equal to 150 times, the uncomfortable time proportion is less than or equal to 35%, and the comfort level is medium;
the uncomfortable times are less than or equal to 300 times, the uncomfortable time proportion is less than or equal to 50 percent, and the comfort level is low.
9. The vehicle-road-coordination-based automatic driving vehicle state evaluation and early warning method according to claim 1, wherein the vehicle-road-coordination-based automatic driving vehicle state evaluation and early warning method is characterized by comprising the following steps of: and S3, abnormal behaviors comprise abnormal parking, abnormal acceleration, abnormal deceleration and abnormal steering wheel large-amplitude rotation and collision risks.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111675077.5A CN114550442B (en) | 2021-12-31 | 2021-12-31 | Automatic driving vehicle state evaluation and early warning method based on vehicle-road cooperation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111675077.5A CN114550442B (en) | 2021-12-31 | 2021-12-31 | Automatic driving vehicle state evaluation and early warning method based on vehicle-road cooperation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114550442A CN114550442A (en) | 2022-05-27 |
| CN114550442B true CN114550442B (en) | 2023-11-03 |
Family
ID=81669147
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111675077.5A Active CN114550442B (en) | 2021-12-31 | 2021-12-31 | Automatic driving vehicle state evaluation and early warning method based on vehicle-road cooperation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114550442B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115862188A (en) * | 2022-12-01 | 2023-03-28 | 西部科学城智能网联汽车创新中心(重庆)有限公司 | Method and device for sensing abnormal driving based on cloud |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503378A (en) * | 2016-10-26 | 2017-03-15 | 哈尔滨工业大学 | A kind of flat vertical line shape Evaluation Method of Mechanical Property of the road based on transverse acceleration and vertical acceleration |
| CN107807625A (en) * | 2017-09-05 | 2018-03-16 | 百度在线网络技术（北京）有限公司 | A kind of appraisal procedure and device based on automated driving system comfort level end to end |
| CN108248608A (en) * | 2017-12-28 | 2018-07-06 | 北京百度网讯科技有限公司 | For assessing the method and apparatus of the comfort level of control loop |
| CN109583776A (en) * | 2018-12-05 | 2019-04-05 | 百度在线网络技术（北京）有限公司 | A kind of vehicle body-sensing evaluating method, device, electronic equipment, medium and vehicle |
| CN111540237A (en) * | 2020-05-19 | 2020-08-14 | 河北德冠隆电子科技有限公司 | Method for automatically generating vehicle safety driving guarantee scheme based on multi-data fusion |
| CN111829793A (en) * | 2020-08-03 | 2020-10-27 | 广州导远电子科技有限公司 | Driving process comfort evaluation method, device and system based on combined positioning |
| JP2020175893A (en) * | 2015-11-04 | 2020-10-29 | トヨタ自動車株式会社 | Automated driving system, automated driving apparatus, and automated driving method |
| CN112418646A (en) * | 2020-11-18 | 2021-02-26 | 广州小鹏自动驾驶科技有限公司 | Vehicle comfort evaluation method and device and readable storage medium |
| CN113370984A (en) * | 2021-06-30 | 2021-09-10 | 中国科学技术大学先进技术研究院 | Multi-index-based comprehensive evaluation method and system for comfort of automatic driving vehicle |
-
2021
- 2021-12-31 CN CN202111675077.5A patent/CN114550442B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2020175893A (en) * | 2015-11-04 | 2020-10-29 | トヨタ自動車株式会社 | Automated driving system, automated driving apparatus, and automated driving method |
| CN106503378A (en) * | 2016-10-26 | 2017-03-15 | 哈尔滨工业大学 | A kind of flat vertical line shape Evaluation Method of Mechanical Property of the road based on transverse acceleration and vertical acceleration |
| CN107807625A (en) * | 2017-09-05 | 2018-03-16 | 百度在线网络技术（北京）有限公司 | A kind of appraisal procedure and device based on automated driving system comfort level end to end |
| CN108248608A (en) * | 2017-12-28 | 2018-07-06 | 北京百度网讯科技有限公司 | For assessing the method and apparatus of the comfort level of control loop |
| CN109583776A (en) * | 2018-12-05 | 2019-04-05 | 百度在线网络技术（北京）有限公司 | A kind of vehicle body-sensing evaluating method, device, electronic equipment, medium and vehicle |
| CN111540237A (en) * | 2020-05-19 | 2020-08-14 | 河北德冠隆电子科技有限公司 | Method for automatically generating vehicle safety driving guarantee scheme based on multi-data fusion |
| CN111829793A (en) * | 2020-08-03 | 2020-10-27 | 广州导远电子科技有限公司 | Driving process comfort evaluation method, device and system based on combined positioning |
| CN112418646A (en) * | 2020-11-18 | 2021-02-26 | 广州小鹏自动驾驶科技有限公司 | Vehicle comfort evaluation method and device and readable storage medium |
| CN113370984A (en) * | 2021-06-30 | 2021-09-10 | 中国科学技术大学先进技术研究院 | Multi-index-based comprehensive evaluation method and system for comfort of automatic driving vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114550442A (en) | 2022-05-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109177982B (en) | Vehicle driving risk degree evaluation method considering driving style | |
| CN104157156B (en) | A kind of highway Dangerous Area speed of a motor vehicle dynamic management method for early warning | |
| DE102009034097A1 (en) | Adaptive vehicle control system with integrated driving style recognition | |
| GB2549376A (en) | Autonomous peril control | |
| GB2549377A (en) | Autonomous occupant attention-based control | |
| DE102009034096A1 (en) | Adaptive vehicle control system with driving style recognition | |
| GB2549184A (en) | Autonomous vehicle control transitioning | |
| GB2549579A (en) | Autonomous confidence control | |
| CN109767651B (en) | Seamless communication method for curve area in V2X environment | |
| Dang et al. | Analysis of Chinese driver's lane change characteristic based on real vehicle tests in highway | |
| CN113895464B (en) | Intelligent vehicle driving map generation method and system fusing personalized driving style | |
| CN106952361B (en) | A kind of efficient vehicle running state identifying system | |
| CN110660194A (en) | Driving monitoring early warning method and system | |
| CN114550442B (en) | Automatic driving vehicle state evaluation and early warning method based on vehicle-road cooperation | |
| CN112950811B (en) | New energy automobile region operation risk assessment and early warning system integrating whole automobile safety | |
| CN110320916A (en) | Consider the autonomous driving vehicle method for planning track and system of occupant's impression | |
| CN113570747A (en) | Driving safety monitoring system and method based on big data analysis | |
| CN112070927A (en) | Highway vehicle microscopic driving behavior analysis system and analysis method | |
| CN116572984A (en) | Dangerous driving management and control method and system based on multi-feature fusion | |
| CN115892063A (en) | Road condition monitoring and coping method for unmanned commercial vehicle | |
| CN113335293B (en) | Highway road surface detection system of drive-by-wire chassis | |
| Inata et al. | Driver behavior modeling based on database of personal mobility driving in urban area | |
| CN105468888A (en) | Method and device for assessing automobile motion control performance | |
| CN116238544B (en) | Running control method and system for automatic driving vehicle | |
| DE102020108508B3 (en) | Procedure for evaluating route sections |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230418 Address after: 1 / F, building 28, 6055 Jinhai highway, Fengxian District, Shanghai 201400 Applicant after: Zhongzhixing (Shanghai) Transportation Technology Co.,Ltd. Applicant after: Tianyi Transportation Technology Co.,Ltd. Address before: 1 / F, building 28, 6055 Jinhai highway, Fengxian District, Shanghai 201400 Applicant before: Zhongzhixing (Shanghai) Transportation Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |