Object state determination method and apparatus, electronic device, and storage medium

Abstract

The present disclosure provides an object state determination method and device, equipment and medium, relates to the technical field of computers, in particular to the fields of automatic driving, autonomous parking, intelligent transportation, intelligent cockpit, cloud service and Internet of Vehicles. The specific implementation scheme is as follows: a plurality of target perception data of a mobile object are determined, each target perception data includes a time value and a speed value, the time value represents the collection time of the target perception data, and the speed value represents the speed of the mobile object at the time; a linear relationship between the time and the speed of the plurality of target perception data is determined according to the time value and the speed value of the plurality of target perception data; and the acceleration of the mobile object is determined according to the linear relationship; wherein the plurality of target perception data are determined by: acquiring a time sequence perception data sequence in a predetermined period of time including a plurality of perception data; and performing variable step sampling on the plurality of perception data, so that sampling points close to the current time are denser, and sampling points far away are sparser.

Description

[0001] This application is a divisional application of Chinese patent application CN202111017760.X (“Object State Determination Method, Apparatus, Electronic Device and Storage Medium”) filed on August 31, 2021. Technical Field

[0002] This disclosure relates to the field of computer technology, and in particular to the fields of autonomous driving, autonomous parking, intelligent transportation, intelligent cockpit, cloud services, and vehicle networking. Background Technology

[0003] Autonomous vehicles are a type of intelligent vehicle, also known as wheeled mobile robots. They use onboard sensor systems to perceive the road environment, automatically plan routes, and control the vehicle to reach predetermined destinations.

[0004] Advanced driver assistance systems (ADAS) utilize various sensors installed on a vehicle, such as millimeter-wave radar, lidar, cameras, and ultrasonic radar, to perceive the surrounding environment and collect data. They then perform static and dynamic object identification, detection, and tracking, as well as system calculations and analysis, enabling drivers to anticipate potential dangers and effectively increasing driving comfort and safety. Summary of the Invention

[0005] This disclosure provides a method, apparatus, electronic device, and storage medium for determining the state of an object.

[0006] According to one aspect of this disclosure, a method for determining the state of an object is provided, comprising: determining multiple target perception data for a moving object, wherein each target perception data includes a time value and a velocity value, the time value representing the acquisition time of the target perception data, and the velocity value representing the velocity of the moving object at the time; determining a linear relationship between the time and velocity of the multiple target perception data based on the time value and velocity value of the multiple target perception data; and determining the acceleration of the moving object based on the linear relationship; wherein determining multiple target perception data for a moving object includes: acquiring a time-series perception data sequence of the moving object within a predetermined time period, wherein the time-series perception data sequence includes multiple perception data; and performing variable step-size sampling on the multiple perception data to make the sampling points closer to the current time more dense and the sampling points farther from the current time more sparse, thereby obtaining multiple target perception data.

[0007] According to another aspect of this disclosure, an object state determination apparatus is provided, comprising: a first determination module, configured to determine multiple target perception data for a moving object, wherein each target perception data includes a time value and a velocity value, the time value representing the acquisition time of the target perception data, and the velocity value representing the velocity of the moving object at the time; a second determination module, configured to determine a linear relationship representing the time and velocity of the multiple target perception data based on the time value and velocity value of the multiple target perception data; and a third determination module, configured to determine the acceleration of the moving object based on the linear relationship; wherein the first determination module includes: an acquisition submodule, configured to acquire a time-series perception data sequence of the moving object within a predetermined time period, wherein the time-series perception data sequence includes multiple perception data; and a sampling submodule, configured to perform variable step-size sampling on the multiple perception data to make the sampling points closer to the current time denser and the sampling points farther from the current time sparser, thereby obtaining multiple target perception data.

[0008] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the object state determination method as described above.

[0009] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the object state determination method as described above.

[0010] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the object state determination method as described above.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0013] Figure 1 This illustration schematically shows an exemplary system architecture of an object state determination method and apparatus according to embodiments of the present disclosure;

[0014] Figure 2 A flowchart illustrating an object state determination method according to an embodiment of the present disclosure is shown schematically.

[0015] Figure 3 A flowchart illustrating the recording of sensed data into a historical data list according to an embodiment of the present disclosure is shown schematically.

[0016] Figure 4 A flowchart illustrating the determination of multiple target sampling times according to embodiments of the present disclosure is shown schematically;

[0017] Figure 5 A block diagram schematically illustrates an object state determination apparatus according to embodiments of the present disclosure; and

[0018] Figure 6 A schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0019] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0020] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information comply with the provisions of relevant laws and regulations, necessary confidentiality measures have been taken, and there is no violation of public order and good morals.

[0021] Vehicle driver assistance functions have gradually expanded from limited assistance to more advanced features. Some driver assistance functions not only require accurate awareness of the vehicle's own status but also a certain level of awareness of the traffic environment and the status of other road users to employ more advanced strategies. For autonomous vehicles equipped with LiDAR sensors, relatively accurate speed and acceleration can be obtained by tracking other objects and then using differentiation and filtering. However, most vehicles equipped with advanced driver assistance functions do not have LiDAR; their main sensors are cameras and millimeter-wave radar. When estimating the acceleration of other road users, the position of the object relative to the vehicle is usually obtained directly through sensors. Then, by continuously tracking the object, the velocity value of the object is obtained through differentiation and filtering. Subsequently, the velocity value is differentiated and filtered again to obtain the object's acceleration.

[0022] In realizing the concept disclosed herein, the inventors discovered that methods for estimating the acceleration of other objects using differentiation and filtering require high sensor accuracy. Because two differentiations are required, even minor noise can cause significant fluctuations in the final result, leading to substantial data distortion. Furthermore, while filtering can eliminate some noise, it introduces system delays. These delays affect the vehicle's decision-making and reaction speed, failing to meet the real-time requirements of driving.

[0023] Figure 1 An exemplary system architecture of an object state determination method and apparatus according to embodiments of the present disclosure is illustrated.

[0024] It is important to note that Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this disclosure, to help those skilled in the art understand the technical content of this disclosure, but do not mean that the embodiments of this disclosure cannot be used in other devices, systems, environments, or scenarios. For example, in another embodiment, an exemplary system architecture for applying the object state determination method and apparatus may include a terminal device, but the terminal device can implement the object state determination method and apparatus provided by the embodiments of this disclosure without interacting with the server.

[0025] like Figure 1 As shown, the system architecture according to this embodiment may include terminal devices 111, 112, and 113, a network 114, and a server 115. The network 114 serves as a medium for providing a communication link between the terminal devices 111, 112, and 113 and the server 115. The network 114 may include various connection types, such as wired and / or wireless communication links, etc.

[0026] Users can use terminal devices 111, 112, and 113 to interact with server 115 via network 114 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 111, 112, and 113, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, sensor applications, email clients, and / or social platform software, etc. (for example only).

[0027] Terminal devices 111, 112, and 113 can be devices carried by users in vehicle 110 or built into vehicle 110. These devices can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0028] Server 115 can be a server built into vehicle 110, providing various services, such as a backend management server (for example only) supporting the content browsed by users using terminal devices 111, 112, and 113. The backend management server can analyze and process received user requests and other data, and feed back the processing results (such as web pages, information, or data obtained or generated based on user requests) to the terminal devices. Server 115 can also be a cloud server communicating with the vehicle's infotainment system, also known as a cloud computing server or cloud host. It is a host product in the cloud computing service system, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") in terms of management difficulty and weak business scalability. The server can also be a server for a distributed system or a server integrated with blockchain technology.

[0029] It should be noted that the object state determination method provided in this embodiment can generally be executed by terminal devices 111, 112, or 113. Correspondingly, the object state determination device provided in this embodiment can also be disposed in terminal devices 111, 112, or 113.

[0030] Alternatively, the object state determination method provided in this embodiment of the disclosure can generally be executed by server 115. Correspondingly, the object state determination device provided in this embodiment of the disclosure can generally be located in server 115. The object state determination method provided in this embodiment of the disclosure can also be executed by a server or server cluster that is different from server 115 and capable of communicating with terminal devices 111, 112, 113 and / or server 115. Correspondingly, the object state determination device provided in this embodiment of the disclosure can also be located in a server or server cluster that is different from server 115 and capable of communicating with terminal devices 111, 112, 113 and / or server 115.

[0031] For example, when it is necessary to determine the moving object (such as...) Figure 1When a vehicle (e.g., vehicle 120, 130, etc.) is in motion, terminal devices 111, 112, 113, and server 115 can first determine multiple target perception data points of the moving object. Each target perception data point includes a time value and a speed value; the time value represents the time at which the target perception data was acquired, and the speed value represents the speed of the moving object at that time. Then, a linear relationship between the time and speed of the multiple target perception data points is determined based on the time and speed values. Subsequently, the acceleration of the moving object is determined based on this linear relationship. Alternatively, a server or server cluster capable of communicating with terminal devices 111, 112, 113, and / or server 115 can analyze the multiple target perception data points of the moving object and determine the acceleration of the moving object using the linear relationship.

[0032] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0033] Figure 2 A flowchart illustrating an object state determination method according to an embodiment of the present disclosure is shown schematically.

[0034] like Figure 2 As shown, the method includes operations S210 to S230.

[0035] In operation S210, multiple target perception data for the moving object are determined, wherein each target perception data includes a time value and a velocity value, the time value representing the time when the target perception data is collected, and the velocity value representing the velocity of the moving object at that time.

[0036] In operation S220, based on the time and velocity values ​​of multiple target sensing data, a linear relationship representing the time and velocity between the multiple target sensing data is determined.

[0037] In operation S230, the acceleration of the moving object is determined based on a linear relationship.

[0038] According to embodiments of this disclosure, the moving object may include at least one of moving vehicles, pedestrians, and other movable objects. Since the estimation of acceleration requires reference to the historical velocity information of the moving object, it is necessary to first collect the velocity information of the moving object, i.e., the velocity value. Furthermore, since acceleration is the derivative of velocity over time, it is also necessary to collect the time information corresponding to the velocity, i.e., the time value. Therefore, the perception data may include the acquisition time information of the corresponding perception data and the velocity information of the moving object at that acquisition time. Target perception data may include perception data of the moving object collected at one or more times. Both time information and velocity information can be obtained through sensors, which may include at least one of cameras, millimeter-wave radar, lidar, and other detection devices capable of acquiring time and velocity information.

[0039] According to embodiments of this disclosure, a linear relationship can be expressed as a linear equation. For example, the time values ​​of multiple target sensing data can be used as the abscissa, and the velocity values ​​of the corresponding target sensing data can be used as the ordinate. By determining multiple coordinate points of the multiple target sensing data in the coordinate system, the linear equation can be derived based on these multiple coordinate points. For example, the linear equation can also be determined based on least squares calculations, combining the time values ​​and velocity values ​​of the target sensing data. The determined linear equation can be expressed, for example, as V(t) = k × t + b, and the acceleration of the moving object can be determined based on the slope k of the linear equation, where k and b are parameters.

[0040] According to embodiments of this disclosure, for example, in a scenario where multiple vehicles are in a moving or stationary state, one vehicle is designated as the master vehicle, and the other vehicles can be considered as moving objects relative to the master vehicle. The master vehicle can acquire target perception data of each of the other moving objects and determine linear equations corresponding to each moving object based on the acquired target perception data, thereby further determining the acceleration of each moving object.

[0041] It should be noted that the main vehicle can be in a moving state or a stationary state. The speed value of the moving object can be its absolute speed relative to the ground.

[0042] Through the embodiments of this disclosure, acceleration is determined based on the linear relationship between time and velocity of multiple target sensing data. Since no differentiation or filtering processing of the data is required, the problem of large data distortion when determining acceleration based on differentiation and filtering methods can be effectively solved, reducing system latency and improving the accuracy of acceleration calculation results.

[0043] The following describes specific embodiments. Figure 2 The method shown will be further explained.

[0044] According to embodiments of this disclosure, the method for determining the aforementioned sensing data may include: determining the target velocity value of a moving object acquired at a target time; and determining the sensing data of the moving object at the target time based on the identifier of the moving object, the time value corresponding to the target time, and the target velocity value.

[0045] According to embodiments of this disclosure, since mobile objects can typically include multiple objects, in order to distinguish the sensing data corresponding to each mobile object, the sensing data may also include the identification information of the corresponding mobile object.

[0046] According to embodiments of this disclosure, the target time can be any time within the time range during which the main vehicle can detect a moving object. The actual value of the time can be determined based on the sampling frequency of the sensor when collecting data. For example, if the sensing data is collected at a sampling frequency of 100Hz, the sampling period of the sensing data can be determined to be 0.01s. Then, for the same moving object that the main vehicle can detect, one sensing data point for that moving object can be collected every 0.01s.

[0047] According to embodiments of this disclosure, the obtained perception data may include identification information of the moving object, time information corresponding to the target time, and speed information of the moving object at that time.

[0048] The above embodiments of this disclosure provide a method for acquiring sensing data. Based on this method, the sensing data of all moving objects that need to be detected can be detected, providing a reliable data foundation for acceleration calculation.

[0049] According to embodiments of this disclosure, the sensing data may further include location coordinates, which represent the geographical location of the moving object at a given time.

[0050] According to embodiments of this disclosure, since moving objects can typically include multiple objects—for example, a traffic system is composed of numerous traffic participants—the sampling process also requires collecting the location information of the moving objects as a basis for target tracking. Therefore, the sensing data acquired by the sensor may also include the location coordinates of the moving objects at corresponding times.

[0051] By adding the position coordinates of the moving object to the collected sensing data through the above embodiments of this disclosure, the accuracy of the sensing data collected for each moving object can be improved.

[0052] According to embodiments of this disclosure, determining multiple target sensing data for a moving object may include: acquiring a temporal sensing data sequence of the moving object within a predetermined time period. The temporal sensing data sequence includes multiple sensing data. Variable-step sampling is performed on the multiple sensing data to obtain multiple target sensing data.

[0053] According to embodiments of this disclosure, the predetermined time period can also be any time period within the time range during which the main vehicle can detect the moving object. The time range during which the main vehicle can detect the moving object can be determined based on the distance between the moving object and the main vehicle. For example, if all moving objects within a 50-meter radius of the main vehicle can be detected by the main vehicle, then the predetermined time period can be any time period from the moment the moving object enters a position 50 meters from the main vehicle until it leaves a position 50 meters away from the main vehicle. The set of sensing data collected within this arbitrary time period can constitute a temporal sensing data sequence. The target sensing data can be at least two sensing data selected from the set of sensing data corresponding to this temporal sensing data sequence.

[0054] According to embodiments of this disclosure, variable-step-size sampling of multiple sensing data can be represented by sampling multiple sensing data with different sampling step sizes. Each sensing data can correspond to a position in a time-series sensing data sequence. For example, if 20 sensing data are collected within a predetermined time period of 0.2 seconds, these 20 sensing data are located at positions 1 to 20 in the time-series sensing data they constitute. Variable-step-size sampling can be represented by sampling the sensing data at positions 1, 3, 7, 9, 13, 16, and 18, and the sampling results can be used as target sensing data. Each sensing data can correspond to a collection time, and variable-step-size sampling can also be represented by sampling the sensing data at different times within a predetermined time period to obtain the target sensing data. The sampling time can be randomly determined within the predetermined time period.

[0055] The above embodiments of this disclosure provide a method for determining target perception data. Based on this method, multiple pieces of collected perception data are sampled, which can provide a simple and effective data foundation for acceleration calculation.

[0056] According to embodiments of this disclosure, the method for determining the time-series sensing data sequence may include: determining multiple sensing data points for a moving object acquired within a predetermined time period; and determining a time-series sensing data sequence based on the multiple sensing data points. According to embodiments of this disclosure, the predetermined time period can also be any time period within the time range during which the main vehicle can detect the moving object. When the end time of the predetermined time period is the current time, the acceleration obtained from the target sensing data in the time-series sensing data sequence determined based on the predetermined time period is the current acceleration of the moving object. When the end time of the predetermined time period is not equal to the current time, the corresponding acceleration obtained is the acceleration of the moving object within the corresponding predetermined time period.

[0057] According to embodiments of this disclosure, each time the sensors of the main vehicle detect a moving object, the time t, speed v, and position s from the sensing data collected for the moving object can be merged into a single data point (t, v, s). This single data point can then be stored in a historical data list, which can be identified by the moving object's identification information id. For each piece of sensing data collected within the time range during which the main vehicle can detect a moving object, the operation of storing it in the historical data list identified by the moving object's identification information id can be performed. This facilitates identifying which moving object a particular piece of sensing data in the list was collected for when multiple moving objects are detected simultaneously. A time-series sensing data sequence can be determined from the corresponding historical data list based on a predetermined time period.

[0058] Through the embodiments described above, determining the temporal sensing data sequence based on sensing data within a preset time period can effectively improve the accuracy of the acceleration value determined from the target sensing data in the temporal sensing data sequence. Furthermore, the shorter the preset time period, the higher the accuracy of the calculated acceleration.

[0059] According to embodiments of this disclosure, the operation on the sensing data in the historical data list may further include: determining the first position coordinates of the moving object acquired at a first time moment; determining the second position coordinates of the moving object acquired at a second time moment; the time difference between the first time moment and the second time moment being equal to one time period for acquiring the sensing data, with the second time moment occurring after the first time moment; and discarding the sensing data for the moving target acquired at and before the first time moment if the distance difference between the first and second position coordinates is determined to be greater than a preset threshold.

[0060] According to embodiments of this disclosure, the first moment can be any moment within the time range during which the main vehicle can detect a moving object, and the position coordinates of the moving object collected at this moment can be the first position coordinates. The second moment can be the moment of the next acquisition of sensing data relative to the first moment, and the position coordinates of the moving object collected at this moment can be the second position coordinates. A time period can be determined based on the acquisition frequency; for example, if the acquisition frequency is 100Hz, then a time period can be determined to be 0.01s. A preset threshold can be a distance value that the moving object cannot reach within a time period, and this value can be determined based on the maximum speed at which the moving object can move within a time period. For example, the preset threshold can be a value greater than this maximum speed.

[0061] It should be noted that the first and second moments can differ by one or more time periods; this is not limited here. Regardless of the number of time periods, the preset threshold must be a distance that the moving object cannot reach within the time range from the first moment to the second moment.

[0062] According to embodiments of this disclosure, when collecting sensing data within the timeframe during which the main vehicle can detect a moving object, for each sensing data point not collected for the first time, the location coordinates of the currently collected sensing data can be compared with the location coordinates of the previously collected sensing data based on records in the historical data list. If the distance difference between the two is within a preset threshold range, the currently collected sensing data can be directly recorded into the corresponding historical data list. If the distance difference exceeds the preset threshold, it can be considered that the tracking of the moving object is incorrect. In this case, the records in the historical data list can be cleared, and then the currently collected sensing data can be used as the first record to re-record in the historical data list, thereby achieving re-tracking of the moving object.

[0063] According to embodiments of this disclosure, the historical data list can save only the sensing data within the time period closest to the current moment. For example, only the latest tracked data in the last 0.5 seconds can be retained, and the data before 0.5 seconds can be cleared.

[0064] Figure 3 A flowchart illustrating the recording of perceived data into a historical data list according to an embodiment of the present disclosure is shown.

[0065] like Figure 3 As shown, the process includes operations S310 to S350.

[0066] In operation S310, sensing data of the moving object is acquired. This sensing data may include the acquisition time, the moving object's identification information, speed information, and position coordinates.

[0067] In operation S320, it is determined whether the moving object is being detected for the first time. If yes, operation S330 is executed; otherwise, operation S340 is executed.

[0068] In operation S330, the sensed data is recorded into a historical data list identified by the identification information of the moving object.

[0069] In operation S340, it is determined whether the position coordinates in the sensing data differ excessively from the position coordinates in the historical data list. If yes, operation S350 is executed; otherwise, operation S330 is executed. Whether the difference is excessive can be determined by judging whether the distance difference between the position coordinates in the sensing data and the latest position coordinates in the historical data list is greater than a preset threshold.

[0070] In operation S350, clear the historical data in the historical data list and re-record the sensing data as the first data item in the historical data list.

[0071] Through the above embodiments of this disclosure, by setting a preset threshold to delete potentially erroneous sensing data, the retained sensing data can be made more accurate, which can further improve the accuracy of acceleration calculation results.

[0072] According to embodiments of this disclosure, the above-described variable-step-size sampling of multiple sensing data to obtain multiple target sensing data may include: determining multiple target sampling times. Among the multiple target sampling times, the time difference between at least one pair of adjacent target sampling times is different from the time difference between other adjacent target sampling times. At each target sampling time, the time-series sensing data sequence is sampled to obtain the target sensing data.

[0073] According to embodiments of this disclosure, the target sampling time can be any time within a predetermined time period. For example, if the current time is 10:00:00.00 and the preset time period is 0.2s, then the target sampling time can be any time between 09:59:59.80 and 10:00:00.00, such as 09:59:59.81, 09:59:59.85, 09:59:59.87, 09:59:59.90, 09:59:59.93, 09:59:59.97, and 10:00:00.00.

[0074] The above embodiments of this disclosure provide a method for determining variable step size and target perception data. Based on this method, multiple pieces of perception data are sampled, which can provide a simple and effective data foundation for acceleration calculation.

[0075] According to embodiments of this disclosure, determining multiple target sampling times may include: determining the end time of a predetermined time period as the first sampling time; determining the i-th step size, where i = 1, 2, ..., I-1, I, where the i-th step size is less than the (i+1)-th step size, and I is an integer greater than 1; if the j-th sampling time is before the start time of the predetermined time period, determining the j-th sampling time, j = i+1, based on the (j-1)-th sampling time and the i-th step size; and using the first sampling time and the (j-1)-th sampling time as multiple target sampling times.

[0076] Figure 4 A flowchart illustrating the determination of multiple target sampling times according to an embodiment of the present disclosure is shown schematically.

[0077] like Figure 4 As shown, the process includes operations S410 to S460.

[0078] In operation S410, the current time t is determined to be the first sampling time.

[0079] In operation S420, the step size step is determined, and the initial value of i is 1.

[0080] In operation S430, the time corresponding to t-step is determined to be the j-th sampling time, j = i + 1.

[0081] In operation S440, the (j-1)th sampling time is taken as the target sampling time.

[0082] In operation S450, t = t - step, step = step × scale, i = i + 1. Where scale > 1.0.

[0083] In operation S460, determine whether t is before the start time of the predetermined time period. If yes, end the process; otherwise, iteratively execute operations S420 to S450.

[0084] According to an embodiment of this disclosure, if the current time is, for example, 10:00:00.00, then the initial value of time t can be 10:00:00.00. Assuming an initial step size, i.e., the first step size when i=1, step=0.02s, then two target sampling times can be determined: 10:00:00.00 and 09:59:59.98. Then, assuming scale=1.1, the second step size can be determined to be 0.022, and the third sampling time can be further determined to be 09:59:59.958. And so on, assuming a predetermined time of 0.2s, then the sampling times within the time period from 09:59:59.80 to 10:00:00.00 can be determined as target sampling times.

[0085] Through the above embodiments of this disclosure, the sampling method with variable step size can make the sampling points closer to the current time more dense and the sampling points farther from the current time more sparse. On the basis of enhancing the weight of new data, the influence of historical data can be reduced to a certain extent, and the farther away from the current time, the smaller the influence.

[0086] Through the embodiments described above, the accuracy of acceleration estimation for other road users by vehicles using vision and millimeter-wave radar can be improved without the need for lidar, while maintaining a certain level of real-time performance. Compared to direct differentiation and filtering, this method not only ensures the accuracy of acceleration estimates but also reduces data signal latency.

[0087] Figure 5 A block diagram of an object state determination apparatus according to an embodiment of the present disclosure is shown schematically.

[0088] like Figure 5 As shown, the object state determination device 500 includes a first determination module 510, a second determination module 520, and a third determination module 530.

[0089] The first determining module 510 is used to determine multiple target perception data for a moving object, wherein each target perception data includes a time value and a velocity value, the time value representing the acquisition time of the target perception data, and the velocity value representing the velocity of the moving object at that time.

[0090] The second determining module 520 is used to determine, based on the time and velocity values ​​of multiple target sensing data, the linear relationship between time and velocity representing the multiple target sensing data.

[0091] The third determining module 530 is used to determine the acceleration of the moving object based on a linear relationship.

[0092] According to embodiments of this disclosure, the first determining module includes an acquisition submodule and a sampling submodule.

[0093] The acquisition submodule is used to acquire the time-series sensing data sequence of the moving object within a predetermined time period, wherein the time-series sensing data sequence includes multiple sensing data.

[0094] The sampling submodule is used to perform variable step-size sampling on multiple sensing data to obtain multiple target sensing data.

[0095] According to embodiments of this disclosure, the sampling submodule includes a determining unit and a sampling unit.

[0096] A determining unit is used to determine multiple target sampling times, wherein, among the multiple target sampling times, the time difference between at least one pair of adjacent target sampling times is different from the time difference between other adjacent target sampling times.

[0097] The sampling unit is used to sample the time-series sensing data sequence at each target sampling time to obtain target sensing data.

[0098] According to embodiments of this disclosure, the determining unit includes a first determining subunit, a second determining subunit, a third determining subunit, and a fourth determining subunit.

[0099] The first determining subunit is used to determine the end time of the predetermined time period as the first sampling time.

[0100] The second determining subunit is used to determine the i-th step size, where i = 1, 2, ..., I-1, I, the i-th step size is less than the (i+1)-th step size, and I is an integer greater than 1.

[0101] The third determining subunit is used to determine the j-th sampling time, j = i + 1, based on the (j-1)-th sampling time and the i-th step size, when the j-th sampling time is before the start time of the predetermined time period.

[0102] The fourth determining sub-unit is used to take the first sampling time and the (j-1)th sampling time as multiple target sampling times.

[0103] According to embodiments of this disclosure, the object state determination device further includes a fourth determination module and a fifth determination module.

[0104] The fourth determining module is used to determine the target speed value of the moving object obtained at the target time.

[0105] The fifth determining module is used to determine the perception data of the moving object at the target time based on the identifier of the moving object, the time value corresponding to the target time, and the target speed value.

[0106] According to embodiments of this disclosure, the object state determination device further includes a sixth determination module and a seventh determination module.

[0107] The sixth determining module is used to determine multiple sensing data of the moving object acquired within a predetermined time period.

[0108] The seventh determination module is used to determine the time-series sensing data sequence based on multiple sensing data.

[0109] According to embodiments of this disclosure, the sensing data also includes location coordinates, which represent the geographical location of the moving object at a given time.

[0110] According to embodiments of this disclosure, the object state determination device further includes an eighth determination module, a ninth determination module, and a discard module.

[0111] The eighth determination module is used to determine the first position coordinates of the moving object obtained at the first moment.

[0112] The ninth determining module is used to determine the second position coordinates of the moving object acquired at the second time point, wherein the time difference between the first time point and the second time point is equal to one time period of acquiring the sensing data, and the second time point is after the first time point.

[0113] The discard module is used to discard the perception data of the moving target acquired at the first moment and before the first moment when the distance difference between the first position coordinates and the second position coordinates is greater than a preset threshold.

[0114] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0115] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method described above.

[0116] According to embodiments of the present disclosure, a non-transitory computer-readable storage medium stores computer instructions, wherein the computer instructions are used to cause a computer to perform the method described above.

[0117] According to an embodiment of this disclosure, a computer program product includes a computer program that, when executed by a processor, implements the method described above.

[0118] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0119] like Figure 6 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded from storage unit 608 into random access memory (RAM) 603. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0120] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0121] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the object state determination method. For example, in some embodiments, the object state determination method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the object state determination method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the object state determination method by any other suitable means (e.g., by means of firmware).

[0122] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0123] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0124] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0125] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0126] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0127] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, distributed system servers, or servers incorporating blockchain technology.

[0128] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0129] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for determining the state of an object, comprising: Multiple target perception data for a moving object are determined, wherein each target perception data includes a time value and a velocity value, the time value representing the acquisition time of the target perception data, and the velocity value representing the velocity of the moving object at that time; Based on the time and velocity values ​​of the multiple target perception data, determine a linear relationship characterizing the time and velocity of the multiple target perception data; and The acceleration of the moving object is determined based on the linear relationship, without the need for differentiation and filtering of the target perception data; The determination of multiple target perception data for a moving object includes: Acquire a time-series sensing data sequence of the moving object within a predetermined time period, wherein the time-series sensing data sequence includes multiple sensing data; and The multiple sensing data are sampled with a variable step size so that the sampling points closer to the current time are more dense and the sampling points farther from the current time are more sparse, thus obtaining the multiple target sensing data. The method further includes: Determine the first position coordinates of the moving object obtained at the first moment; Determine the second position coordinates of the moving object obtained at the second time point, wherein the time difference between the first time point and the second time point is equal to one time period for acquiring the sensing data, and the second time point is after the first time point; If the distance difference between the first position coordinates and the second position coordinates is determined to be greater than a preset threshold, the perception data of the moving object acquired at or before the first time point is discarded.

2. The method according to claim 1, wherein, The variable-step-size sampling of the plurality of sensing data includes: Determine a plurality of target sampling times, wherein the time difference between at least one pair of adjacent target sampling times is different from the time difference between other adjacent target sampling times; and At each target sampling time, the time-series sensing data sequence is sampled to obtain the target sensing data.

3. The method according to claim 2, wherein, The determination of multiple target sampling times includes: The end time of the predetermined time period is determined as the first sampling time; Determine the first Step length, where, , No. Step size less than the first Step size, where I is an integer greater than 1; In the If the sampling time is before the start time of the predetermined time period, according to the first... Sampling time and the Step size, determine the first Sampling time, ;as well as The first sampling time and the first sampling time The sampling time is referred to as the multiple target sampling times.

4. The method according to any one of claims 1 to 3, further comprising: Determine the target velocity value of the moving object obtained at the target time; as well as Based on the identifier of the moving object, the time value corresponding to the target time, and the target speed value, the perception data of the moving object at the target time is determined.

5. The method according to any one of claims 1 to 3, further comprising: Determine multiple sensing data points for the moving object acquired within the predetermined time period; The time-series sensing data sequence is determined based on the plurality of sensing data.

6. The method according to any one of claims 1 to 3, wherein, The sensing data also includes location coordinates, which represent the geographical location of the moving object at that time.

7. An object state determination device, comprising: The first determining module is used to determine multiple target perception data for a moving object, wherein each target perception data includes a time value and a velocity value, the time value representing the acquisition time of the target perception data, and the velocity value representing the velocity of the moving object at that time; The second determining module is used to determine, based on the time and velocity values ​​of the plurality of target sensing data, a linear relationship characterizing the time and velocity of the plurality of target sensing data; and The third determining module determines the acceleration of the moving object based on the linear relationship, without needing to perform differentiation and filtering on the target perception data; The first determining module includes: The acquisition submodule is used to acquire a time-series sensing data sequence of the moving object within a predetermined time period, wherein the time-series sensing data sequence includes multiple sensing data; and The sampling submodule is used to perform variable step-size sampling on the multiple sensing data, so that the sampling points closer to the current time are more dense and the sampling points farther from the current time are more sparse, so as to obtain the multiple target sensing data. The device further includes: The eighth determining module is used to determine the first position coordinates of the moving object obtained at the first moment; The ninth determining module is used to determine the second position coordinates of the moving object obtained at the second time point, wherein the time difference between the first time point and the second time point is equal to one time period of obtaining the sensing data, and the second time point is after the first time point; The discard module is used to discard the perception data of the moving object acquired at or before the first time point if the distance difference between the first position coordinates and the second position coordinates is greater than a preset threshold.

8. The apparatus according to claim 7, wherein, The sampling submodule includes: A determining unit is configured to determine a plurality of target sampling times, wherein, among the plurality of target sampling times, the time difference between at least one pair of adjacent target sampling times is different from the time difference between other adjacent target sampling times; and A sampling unit is used to sample the time-series sensing data sequence at each target sampling time to obtain the target sensing data.

9. The apparatus according to claim 8, wherein, The determining unit includes: The first determining subunit is used to determine the end time of the predetermined time period as the first sampling time. The second determining subunit is used to determine the first... Step length, where, , No. Step size less than the first Step size, where 1 is an integer greater than 1; The third determining subunit is used in the... If the sampling time is before the start time of the predetermined time period, according to the first... Sampling time and the Step size, determine the first Sampling time, ;as well as The fourth determining subunit is used to determine the first sampling time and the second sampling time. The sampling time is referred to as the multiple target sampling times.

10. The apparatus according to any one of claims 7 to 9, further comprising: The fourth determining module is used to determine the target speed value of the moving object obtained at the target time. as well as The fifth determining module is used to determine the perception data of the moving object at the target time based on the identifier of the moving object, the time value corresponding to the target time, and the target speed value.

11. The apparatus according to any one of claims 7 to 9, further comprising: The sixth determining module is used to determine multiple sensing data of the moving object acquired within the predetermined time period; The seventh determining module is used to determine the time-series sensing data sequence based on the plurality of sensing data.

12. The apparatus according to any one of claims 7 to 9, wherein, The sensing data also includes location coordinates, which represent the geographical location of the moving object at that time.

13. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

15. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images