Self-vehicle control method for trajectory jump and unmanned vehicle

Abstract

The application provides a self-vehicle control method for trajectory jump and an unmanned vehicle, and can be applied to the technical fields of unmanned driving, automatic driving, intelligent auxiliary driving and the like. The self-vehicle control method for trajectory jump comprises the following steps: determining a cumulative jump number of a self-vehicle trajectory in a target time period, wherein the jump number indicates the number of times that a control amount for obtaining the self-vehicle trajectory in an automatic driving mode jumps between two adjacent time points, and the cumulative jump number is obtained by accumulating the jump number; adjusting a current jump threshold based on the cumulative jump number in the target time period to obtain a target jump threshold for the target time period, wherein the current jump threshold comprises a jump threshold for a first time period located before the target time period; and controlling the self-vehicle based on a comparison result between the cumulative jump number in the target time period and the target jump threshold.

Description

Technical Field

[0001] This application relates to the technical fields of unmanned driving, autonomous driving, and intelligent assisted driving, and more specifically, to a vehicle control method for trajectory changes and an unmanned vehicle. Background Technology

[0002] With the rapid development of autonomous driving technology, autonomous vehicles can be applied to a variety of scenarios. The autonomous vehicle's self-control and decision-making rely on the vehicle's perception system, such as information collected by devices like LiDAR, cameras, and millimeter-wave radar.

[0003] However, for autonomous vehicles operating in harsh environments, the vehicle's perception system is severely affected by environmental interference. This environmental influence on perceived information can lead to trajectory changes in vehicle control. Furthermore, trajectory changes can cause overload and wear on the internal control equipment of the autonomous vehicle, resulting in safety risks. Summary of the Invention

[0004] In view of this, this application provides a vehicle control method for trajectory changes and an unmanned vehicle.

[0005] One aspect of this application provides a vehicle control method for trajectory jumps, comprising: determining the cumulative number of jumps in the vehicle trajectory within a target time period, wherein the number of jumps indicates the number of times the control quantity used to obtain the vehicle trajectory in autonomous driving mode jumps between two adjacent moments, and the cumulative number of jumps is obtained by the cumulative number of jumps; adjusting a current jump threshold based on the cumulative number of jumps within the target time period to obtain a target jump threshold for the target time period, wherein the current jump threshold includes a jump threshold for a first time period preceding the target time period; and controlling the vehicle based on a comparison between the cumulative number of jumps within the target time period and the target jump threshold.

[0006] Another aspect of this application provides a vehicle control device for trajectory jumps, comprising: a determining module for determining the cumulative number of jumps in the vehicle trajectory within a target time period, wherein the jump count indicates the number of times the control quantity used to obtain the vehicle trajectory in autonomous driving mode jumps between two adjacent moments, and the cumulative jump count is obtained by the cumulative jump count; an adjusting module for adjusting a current jump threshold based on the cumulative jump count within the target time period to obtain a target jump threshold for the target time period, wherein the current jump threshold includes a jump threshold for a first time period preceding the target time period; and a controlling module for controlling the vehicle based on a comparison between the cumulative jump count within the target time period and the target jump threshold.

[0007] Another aspect of this application provides an autonomous vehicle, comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method described above.

[0008] Another aspect of this application provides a computer-readable storage medium storing computer-executable instructions that, when executed, are used to implement the method described above.

[0009] Another aspect of this application provides a computer program product including computer-executable instructions that, when executed, are used to implement the methods described above. Attached Figure Description

[0010] The above and other objects, features and advantages of this application will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0011] Figure 1 An exemplary system architecture for applying a vehicle control method for trajectory changes, according to embodiments of this application, is illustrated.

[0012] Figure 2 A flowchart illustrating a vehicle control method for trajectory changes according to an embodiment of this application is shown schematically.

[0013] Figure 3 The illustration shows a scenario where a vehicle is controlled based on a comparison between the cumulative number of transitions within a target time period and a target transition threshold, according to an embodiment of this application.

[0014] Figure 4 A schematic diagram illustrating trajectory transition detection according to an embodiment of this application is shown.

[0015] Figure 5 A schematic block diagram of a vehicle control device for trajectory changes according to an embodiment of this application is shown.

[0016] Figure 6 A block diagram of an unmanned vehicle suitable for implementing a vehicle control method for trajectory jumps, according to an embodiment of this application, is illustrated schematically. Detailed Implementation

[0017] The embodiments of this application will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of this application. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of this application for ease of explanation. However, it will be apparent that one or more embodiments may be implemented without these specific details. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of this application.

[0018] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0019] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0020] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0021] In the embodiments of this application, the collection, updating, analysis, processing, use, transmission, provision, disclosure, and storage of data (e.g., including but not limited to user personal information) comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures have been taken to prevent unauthorized access to user personal information data and to maintain user personal information security, network security, and other security. In the embodiments of this application, user authorization or consent has been obtained before acquiring or collecting user personal information.

[0022] In practical applications, under severe weather conditions such as strong winds, rain, snow, dust storms, and sandstorms, the detection stability of the vehicle's perception system changes, making it prone to false detections, missed detections, or positional jumps. This directly affects the quality of the vehicle trajectory obtained from the vehicle's decision-making and planning, causing the vehicle to exhibit start-stop intention jumps that are not driven by driving intent. These jumps in the vehicle trajectory's start-stop intentions lead to the vehicle's control equipment frequently performing ineffective throttle / brake alternations, frequent gear shifts, and frequent release and activation of the parking brake, severely impacting the lifespan of the vehicle's internal control equipment and the smoothness of driving.

[0023] Especially in mining environments, unmanned vehicles are typically heavy and bulky mining vehicles. Mining areas frequently experience severe weather conditions such as strong winds, dust storms, and sandstorms. These conditions are compounded by unstructured obstacles like falling rocks, tumbleweeds, and water-filled pits, causing the vehicles to exhibit sudden changes in start-stop intentions beyond the driver's control. Furthermore, compared to passenger vehicles, mining vehicles (such as wide-body dump trucks and rigid trucks) have significant physical limitations in terms of response and control. Additionally, the drive-by-wire actuators in mining vehicles (such as heavy-duty air brake systems, hydraulic retarders, and transmissions) are designed with a greater emphasis on shock resistance and durability than on the precision of high-frequency responses.

[0024] The design characteristics of unmanned mining vehicles make them extremely sensitive to frequent throttle-brake alternations, gear shifts, and parking brake releases and activations. For example, regarding frequent throttle-brake alternations, the vehicle's enormous inertia means that each braking intervention requires a huge amount of energy. If the vehicle's control causes frequent fluctuations in pedal opening, it can easily lead to brake fade, shortening the lifespan of the friction pads and retarder. Regarding frequent shifts between drive and neutral gears, the gears and clutches inside the vehicle's transmission must withstand enormous torque loads. Unnecessary frequent gear shifting can exacerbate wear on the synchronizers and clutches, and in severe cases, may even cause the transmission control unit (TCU) to overheat or malfunction, forcibly disengaging from the gear and causing a power interruption. Regarding the frequent application and release of the parking brake, unmanned mining vehicles typically use spring-loaded parking brakes to achieve long-term parking on slopes. Frequent application and release of the parking brake can not only cause wear on the air brake valve, but also lead to insufficient air pressure due to frequent pressure build-up and depressurization in the air circuit. This can result in unexpected parking brake activation, causing impact damage to the drive shaft and rear axle.

[0025] Therefore, abnormal fluctuations in the vehicle's trajectory and its intention to start and stop may only manifest as slight jerks in passenger autonomous vehicles, but in mining autonomous vehicles, they can directly evolve into major safety hazards affecting operational safety and equipment lifespan.

[0026] To avoid the impact of trajectory jumps on trajectory control and driving safety, related technologies compare a fixed jump threshold with the number of detected jumps to achieve trajectory jump detection. However, this method struggles to detect periodic, low-frequency trajectory jumps, and even if such jumps exist, they often fail to trigger protection, resulting in the vehicle remaining in an abnormal execution state for extended periods without any alarms. Alternatively, other related technologies may detect trajectory jumps during vehicle start-up and delay activation upon detection. However, this method only mitigates instantaneous trajectory jumps during the start-up phase and cannot address the anomaly of continuous trajectory jumps.

[0027] Therefore, embodiments of this application provide a vehicle control method for trajectory jumps, comprising: determining the cumulative number of jumps in the vehicle trajectory within a target time period, wherein the number of jumps indicates the number of times the control quantity used to obtain the vehicle trajectory in autonomous driving mode jumps between two adjacent moments, and the cumulative number of jumps is obtained by the cumulative number of jumps; adjusting a current jump threshold based on the cumulative number of jumps within the target time period to obtain a target jump threshold for the target time period, wherein the current jump threshold includes a jump threshold for a first time period preceding the target time period; and controlling the vehicle based on a comparison between the cumulative number of jumps within the target time period and the target jump threshold.

[0028] By detecting the cumulative number of trajectory jumps within a target time period and adjusting the current jump threshold based on this cumulative number of jumps, a target jump threshold for the target time period is obtained. This extends the detection of trajectory jumps from a specific moment to the entire target time period, avoiding missed detection of low-frequency, periodic trajectory jumps and improving the accuracy of trajectory jump detection. Furthermore, adjusting the current jump threshold using the cumulative number of jumps allows for dynamic adjustment of the threshold based on current real-world operating conditions, resulting in a target jump threshold that better reflects the actual operating conditions. Subsequently, by comparing the cumulative number of jumps with the target jump threshold, accurate trajectory jump detection can be achieved. This accurate trajectory jump detection enables vehicle control, proactively mitigating wear and tear on vehicle control equipment and safety risks caused by trajectory jumps.

[0029] Figure 1 An exemplary system architecture for applying a vehicle control method for trajectory changes, according to embodiments of this application, is illustrated.

[0030] like Figure 1As shown, the system architecture 100 according to this embodiment may include a vehicle 101, a network 102, and a server 103. The network 102 serves as a medium for providing a communication link between the vehicle 101 and the server 103. The network 102 may include various connection types, such as wired and / or wireless communication links. The vehicle 101 may be various types of autonomous vehicles, such as passenger autonomous vehicles, mining autonomous vehicles, and autonomous vehicles performing other operational tasks. The vehicle 101 can communicate with the server 103 through the network 102 to send sensing information, receive or send instructions, etc. The server 103 may be a server providing various services, such as a cloud server, or simply the cloud.

[0031] It should be noted that the vehicle control method for trajectory changes provided in this application embodiment can generally be executed by the vehicle 101. Correspondingly, the vehicle control device for trajectory changes provided in this application embodiment can generally be installed in the vehicle 101. Alternatively, the vehicle control method for trajectory changes provided in this application embodiment can also be executed by the server 103 or a server cluster. Correspondingly, the vehicle control device for trajectory changes provided in this application embodiment can also be installed on the server 103 or a server cluster.

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

[0033] Figure 2 A flowchart illustrating a vehicle control method for trajectory changes according to an embodiment of this application is shown schematically. Figure 2 As shown, the method includes operations S210~S230.

[0034] In operation S210, determine the cumulative number of jumps in the vehicle trajectory within the target time period.

[0035] In operation S220, the current transition threshold is adjusted based on the cumulative number of transitions within the target time period to obtain the target transition threshold for the target time period.

[0036] In operation S230, the vehicle is controlled based on the comparison between the cumulative number of transitions within the target time period and the target transition threshold.

[0037] The target time period can be any time period with a certain duration. For example, taking the current moment as an example, if trajectory change detection needs to be performed at the current moment, the current moment can be taken as the last moment of the target time period, and together with multiple moments preceding the current moment, the target time period can be formed. The duration can be predetermined or dynamically changing.

[0038] For example, trajectory jump detection within a target time period can be achieved by using a sliding window with a duration of 5 seconds. Each sliding window can be regarded as a target time period, and the duration of the target time period can be 3-10 seconds.

[0039] The jump count indicates the number of times the control quantity used to obtain the vehicle's trajectory changes between two adjacent moments in autonomous driving mode. The cumulative jump count is obtained by accumulating the jump count. In this embodiment, the control quantity can be generated by the decision module in the vehicle based on vehicle perception information, and may include speed, acceleration, desired acceleration, etc.

[0040] A jump in the control quantity between two adjacent moments can be caused by a large difference in the control quantity between the two moments, or by different starting and stopping intentions of the control quantity. Starting and stopping intention refers to the intention of the vehicle to start and / or brake (also known as stop).

[0041] Two adjacent moments can be any two adjacent moments within the target time period. The cumulative number of transitions is obtained by accumulating the transition counts of multiple non-repeating pairs of adjacent moments within the target time period. For example, taking a target time period of t0~t4 with a duration of 5 seconds as an example, two adjacent moments can be any pair of moments: t0 and t1, t1 and t2, t2 and t3, or t3 and t4. The cumulative number of transitions can be obtained by accumulating the transition counts of these four pairs of adjacent moments. It can be understood that the duration of 5 seconds can include 5, 50, 500, or more moments; the specific number can be determined based on the fineness of the time division within the target time period.

[0042] The current transition threshold includes a transition threshold for a first time period preceding the target time period. The first time period can be a time period preceding and adjacent to the target time period. For example, for times t0 to t9, if times t5 to t9 are the target time period, then times t0 to t4 are the first time period. The current transition threshold can be calculated when the first time period is considered the target time period, or it can be predetermined.

[0043] For the current transition threshold, it can be adjusted positively or negatively based on the cumulative number of transitions, such as increasing or decreasing the current transition threshold. In one specific embodiment, the adjustment amount of the current transition threshold can be a fixed value; or, the adjustment amount can also be related to the cumulative number of transitions.

[0044] The target jump threshold refers to the jump threshold adjusted by using the cumulative jump count to adjust the current jump threshold. It can be a threshold used to indicate that there is an anomaly in the trajectory jump. It is understood that the target jump threshold serves as a benchmark to measure whether the cumulative jump count exceeds expectations. Since the target jump threshold is dynamic, the sensitivity of trajectory jump detection using the target jump threshold to the cumulative jump count also changes dynamically to adapt to the actual operating conditions of the vehicle and achieve trajectory jump detection.

[0045] The comparison result indicates the magnitude of the cumulative number of jumps relative to the target jump threshold. Multiple comparison results can correspond to multiple vehicle control strategies, enabling various control methods for the vehicle based on these results. Vehicle control can be based on control variables used to generate the vehicle's trajectory, such as controlling the vehicle to start, stop, accelerate, decelerate, and brake.

[0046] In the embodiments of this application, by detecting the cumulative number of trajectory jumps within a target time period and adjusting the current jump threshold based on the cumulative number of jumps, a target jump threshold for the target time period is obtained. This extends the detection of trajectory jumps from a certain moment to the entire target time period, avoiding missed detection of periodically low-frequency trajectory jumps and improving the accuracy of trajectory jump detection. Furthermore, adjusting the current jump threshold using the cumulative number of jumps allows for dynamic adjustment of the threshold based on the current actual operating conditions, resulting in a target jump threshold that better reflects the current real-world conditions. Subsequently, by comparing the cumulative number of jumps with the target jump threshold, accurate trajectory jump detection can be achieved. This allows for vehicle control based on accurate trajectory jump detection, proactively mitigating wear and tear on vehicle control equipment and safety risks caused by trajectory jumps.

[0047] According to an embodiment of this application, for operation S230, the vehicle is controlled based on the comparison result between the cumulative number of transitions within the target time period and the target transition threshold, including: if the cumulative number of transitions within the target time period is greater than or equal to the target transition threshold, the control of the vehicle using the control quantity at the last moment of the target time period is interrupted; if the cumulative number of transitions within the target time period is less than the target transition threshold, the vehicle is controlled using the control quantity at the last moment of the target time period.

[0048] A cumulative number of jumps less than the target jump threshold indicates that the trajectory jumps within the target time period have not reached an abnormality, and the vehicle can perform normal vehicle control based on the control input. If the last moment in the target time period can be the current moment, the vehicle can be controlled based on the real-time control input at the current moment, such as normal acceleration, deceleration, braking, and gear shifting.

[0049] A cumulative number of trajectory jumps greater than or equal to the target jump threshold indicates an abnormal trajectory jump within the target time period, requiring intervention in the vehicle control system to prevent wear and tear on the control equipment caused by the vehicle controlling based on the control input. In this case, the control system can be interrupted from using the current control input for vehicle control to ensure that the parking or driving states are not disturbed by the abnormal control input.

[0050] Figure 3 The illustration schematically depicts a scenario where autonomous vehicle control is performed based on a comparison between the cumulative number of transitions within a target time period and a target transition threshold, as described in this application embodiment. Figure 3 As shown, after obtaining the cumulative number of transitions of vehicle 101 within the target time period, if the cumulative number of transitions is greater than or equal to the target transition threshold, the vehicle control is interrupted; otherwise, if the cumulative number of transitions is less than the target transition threshold, the vehicle control proceeds normally.

[0051] For example, interrupting the control of the vehicle using the control quantity at the current moment can include: prohibiting the vehicle from switching drive gears, prohibiting the switching of throttle and brake, and prohibiting changes to the parking state.

[0052] In this embodiment, a dynamic target jump threshold can be used to quickly detect whether the trajectory jump is abnormal within a target time period based on sensitivity adapted to the current real working conditions. Then, if an abnormal trajectory jump is detected, the vehicle control can be intervened to avoid wear and tear on the vehicle control equipment and safety risks caused by trajectory jump in advance.

[0053] Considering that when trajectory jumps or abnormal trajectory jumps are detected, only internal action suppression is performed on the control equipment, on-site dispatchers or remote maintenance personnel cannot know that the vehicle is currently in an "abnormal protection" state that intervenes in the vehicle's control. This makes it impossible to distinguish between normal "abnormal protection" states, normal braking caused by obstacles, invalid braking, and other information, affecting the human's true perception and maintenance of whether the vehicle is abnormal.

[0054] In another embodiment, the method further includes: if it is determined that the vehicle has a transition and / or the number of transitions at at least once is greater than an alarm threshold, sending alarm information to the cloud via the vehicle.

[0055] Determining that a trajectory change exists can be understood as the number of trajectory changes at any given time within the target time period being non-zero, or the cumulative number of trajectory changes being non-zero. To avoid occasional or false alarm-triggered trajectory changes affecting manual judgment, an alarm threshold can be set. An alarm will only be triggered if the number of trajectory changes at any given time within the target time period exceeds the alarm threshold. Determining that a trajectory change exists can also be considered a special case where the alarm threshold is 1.

[0056] Alarm thresholds can be fixed or dynamically changing, such as being determined based on dynamically changing target fluctuation thresholds. The specific value of the alarm threshold can be determined according to the actual situation.

[0057] Alarm information is used to indicate the presence of a trajectory change. Alarm information may include at least one of the following: the number of changes at the time the alarm was triggered, the target time period, and the cumulative number of changes within the target time period. Therefore, if the cumulative number of changes exceeds the target change threshold and vehicle control is interrupted, on-site dispatchers or remote maintenance personnel can determine, based on the alarm information, that the vehicle is currently in an "abnormal protection" state, rather than due to other reasons.

[0058] In other embodiments, alarm information can also be sent from the vehicle to the cloud when the vehicle's speed is less than the starting speed threshold and the cumulative number of transitions is greater than the target transition threshold in autonomous driving mode.

[0059] In this embodiment, intuitive alarm information allows on-site dispatchers or remote maintenance personnel to perceive the vehicle's status realistically and intuitively, enabling them to perform timely maintenance on the vehicle.

[0060] According to embodiments of this application, the control quantity includes a desired acceleration for controlling the vehicle to generate its trajectory. The method further includes: determining the number of transitions in the later time step between two adjacent time steps as one if the difference between the desired accelerations at two adjacent time steps is greater than an acceleration threshold; or, the control quantity also includes speed, and the method further includes: determining the number of transitions in the later time step between two adjacent time steps as one if the speed at the later time step is less than a starting speed threshold, the start / stop intentions indicated by the desired accelerations at two adjacent time steps are different, and the difference is greater than an acceleration threshold.

[0061] The control quantity is generated by the vehicle's decision-making module based on vehicle perception information. The desired acceleration refers to the ideal acceleration of the vehicle under conditions unaffected by external factors. However, in reality, external disturbances can cause the actual acceleration achieved by the vehicle to differ from the desired acceleration. As stated above, the trajectory jump detection in this embodiment is performed before vehicle control; therefore, the control quantity used to calculate the number of jumps includes the desired acceleration rather than the actual acceleration.

[0062] Furthermore, if the control quantity includes speed, the number of transitions can be calculated directly using the speed data obtained from sensors installed inside the vehicle.

[0063] In one embodiment, considering that the calculation of the vehicle's expected acceleration during the decision-making process is subject to various constraints such as vehicle dynamics, if the difference between the expected acceleration DsrAccSpd(t) at time t and the expected acceleration at time t-1 within the target time period, DsrAccSpd(t-1), is greater than the acceleration threshold, it indicates, on the one hand, that there is a problem with the vehicle perception information used to determine the expected acceleration, possibly due to a jump in vehicle position, and on the other hand, this control variable can also cause a jump in the vehicle's trajectory. Therefore, when the difference between the expected acceleration at time t and the expected acceleration at time t-1 is greater than the acceleration threshold, the number of jumps at time t is determined to be one, that is, |DsrAccSpd(t) - DsrAccSpd(t-1)| > acceleration threshold. In this embodiment, time t and time t-1 can be any two adjacent times within the target time period, and time t represents the later of the two adjacent times.

[0064] The acceleration threshold can be determined based on the actual situation, such as 0.45 m / s² to cover the vast majority of invalid transitions.

[0065] In one embodiment, the sign of the desired acceleration corresponds to different start-stop intentions. For example, a desired acceleration greater than zero indicates a start-up intention, while a desired acceleration less than zero indicates a stop-stop intention. If the start-up intentions differ between two adjacent moments, the vehicle needs to alternate between throttle and brake. As mentioned above, this operation leads to wear on control equipment (such as the braking system). Therefore, different start-up intentions between two adjacent moments can be considered as the number of jumps plus 1. For example, when DsrAccSpd(t) * DsrAccSpd(t-1) < 0, the start-up intentions are different between two adjacent moments.

[0066] In one embodiment, the number of transitions can also be determined by combining the starting intention and the difference in expected acceleration between two adjacent time points. That is, when |DsrAccSpd(t) - DsrAccSpd(t-1)| > acceleration threshold and DsrAccSpd(t)*DsrAccSpd(t-1) < 0, the number of transitions at time t is 1.

[0067] In one embodiment, a vehicle in a parked state is more concerned with starting and stopping intentions. Therefore, whether the vehicle is in a parked state can also be determined by whether the speed at the later time step is less than the starting speed threshold. If the speed at the later time step is less than the starting speed threshold, it indicates that the vehicle is currently in a parked state. Combined with the judgment condition mentioned above, |DsrAccSpd(t) - DsrAccSpd(t-1)|>acceleration threshold and DsrAccSpd(t)* DsrAccSpd(t-1)<0, the number of transitions at time t is determined to be 1. For example, the starting speed threshold can be 0.3 km / h, or it can be determined according to the actual situation.

[0068] In the embodiments of this application, by combining the various effects of trajectory jumps on the vehicle control device under real working conditions, multiple methods are used to determine the number of jumps at each moment in the target time period, so that the cumulative number of jumps obtained by accumulating the number of jumps at multiple moments in the target time period can be adapted to various real working conditions, which facilitates accurate threshold adjustment and trajectory jump detection in the future.

[0069] According to an embodiment of this application, for operation S220, the current jump threshold is adjusted based on the cumulative number of jumps within the target time period to obtain a target jump threshold for the target time period. This includes: negatively adjusting the current jump threshold based on the cumulative number of jumps within the target time period to obtain a target jump threshold, so that the target jump threshold is negatively correlated with the duration of the target time period and / or the number of jumps at each moment within the target time period.

[0070] Since a non-zero cumulative number of trajectory jumps indicates a trajectory jump within the target time period, controlling the vehicle according to the control parameters within that period will cause wear and tear on the vehicle's control equipment. Therefore, to minimize the impact of trajectory jumps on the vehicle, the current jump threshold can be negatively adjusted based on the cumulative number of jumps within the target time period, i.e., the current jump threshold can be reduced.

[0071] If the target jump threshold is lower than the current jump threshold, the cumulative number of jumps is more likely to reach the target jump threshold. Therefore, trajectory jump detection based on the target jump threshold has higher sensitivity.

[0072] In this embodiment, in addition to negatively adjusting the current jump threshold based on the cumulative jump threshold, the adjustment amount of the current jump threshold can also be related to the cumulative jump count. For example, the adjustment amount of the current jump threshold is equal to the cumulative jump count. Thus, the target jump threshold can be obtained by subtracting the cumulative jump count from the current jump threshold.

[0073] In this embodiment, the target jump threshold can be calculated according to formula (1):

[0074] T1' = T1 -∫T2 dt (1)

[0075] Where T1' represents the target transition threshold, T1 represents the current transition threshold, and T2 represents the number of transitions at each time step. The number of transitions at each time step can be understood as the number of transitions between the control quantity at that time step and the control quantity at the adjacent previous time step. The cumulative number of transitions ∫T2 dt is obtained by integrating the number of transitions at each time step within the target time period relative to time.

[0076] In this embodiment, the larger the number of jumps at any moment within the target time period, the smaller the adjusted target jump threshold; the longer the duration of the target time period, the smaller the adjusted target jump threshold. Therefore, the target jump threshold is negatively correlated with the duration of the target time period and / or the number of jumps at each moment within the target time period.

[0077] In other embodiments, to ensure that the cumulative number of transitions ∫T2 dt does not become too large, an upper limit can be constrained for the cumulative number of transitions. If the cumulative number of transitions is greater than a threshold (e.g., 250), the threshold can be used as the cumulative number of transitions. For example, ∫T2 dt = max(0, min(∫T2 dt, 250)) can be set, indicating that the cumulative number of transitions takes the smaller value between ∫T2 dt and 250, and the cumulative number of transitions is greater than 0.

[0078] To avoid situations where the target jump threshold changes to zero or a negative value, the target jump threshold can be restricted. For example, the target jump threshold can be set between 2 and 5, with both values ​​rounded down. If T1' is less than 2, then 2 is used; if T1' is greater than 5, then 5 is used. For example, the restriction on the target jump threshold satisfies the following formula (2):

[0079] min(5,max(2,round(T1'))) (2)

[0080] Where max(2, round(T1')) means taking the maximum value between 2 and round(T1'), min(5, max(2, round(T1'))) means taking the minimum value between 5 and max(2, round(T1')), and round(T1') means rounding T1' to the nearest integer.

[0081] In this embodiment, for periodic or continuous low-frequency trajectory jumps that exist in actual applications, the cumulative number of jumps is obtained by integrating within the target time period, and the current jump threshold is adjusted based on the cumulative number of jumps. This allows the sensitivity of trajectory jump detection to adaptively increase with the duration, the number of jumps at a single moment, and the frequency of jumps occurring at multiple moments in the target time period, thereby avoiding the missed detection of periodic low-frequency trajectory jumps and improving the accuracy of trajectory jump detection.

[0082] Furthermore, when a continuous trajectory jump occurs, the target time period can be used as the first time period relative to the next target time period, and the target jump threshold can be used as the new current jump threshold, so as to achieve continuous detection of trajectory jumps using the above method. In this continuous detection process, the target jump threshold is obtained by continuous decay over multiple target time periods. Therefore, the embodiments of this application can also achieve an adaptive detection effect that improves the sensitivity of trajectory jump detection as the duration of the trajectory jump increases.

[0083] Figure 4 A schematic diagram illustrating trajectory transition detection according to an embodiment of this application is shown. Figure 4 As shown, there are 10 time points from t0 to t9.

[0084] For example, the target time period can be t0 to t4. The target jump threshold can be obtained by adjusting the current jump threshold of the first time period (not shown in the figure) based on the cumulative number of jumps from t0 to t4. Trajectory jump detection from t0 to t4 can be achieved by comparing the target jump threshold with the cumulative number of jumps from t0 to t4. In this embodiment, the number of jumps at time t0 exceeds a certain fixed threshold, while the number at other times does not exceed the fixed threshold.

[0085] Alternatively, the first time period may include times t0 to t4, the target time period may include times t5 to t9, and the periodic low-frequency trajectory jumps occurring within the target time period may have a number of jumps that are all below a fixed threshold.

[0086] Whether it is the case of time t0~t4 or time t5~t9, the method of this application embodiment can realize the overall trajectory jump detection of the target time period. Although related technologies can also detect the anomalies in time t0~t4 by using a fixed threshold, they can only detect the anomalies in time t0, but cannot detect the anomalies in time t1~t4.

[0087] According to an embodiment of this application, a target jump threshold is obtained by negatively adjusting the current jump threshold based on the cumulative number of jumps within a target time period. This includes: adjusting the cumulative number of jumps within the target time period using an adjustment coefficient, and negatively adjusting the current jump threshold based on the adjusted cumulative number of jumps to obtain the target jump threshold. The adjustment coefficient includes at least one of the following: a preset coefficient, a coefficient determined based on the vehicle's current environmental information, or a coefficient determined based on the cumulative number of jumps in at least one second time period preceding the target time period; or, the adjustment coefficient includes the sum of a coefficient determined based on the vehicle's current environmental information and a coefficient determined based on the cumulative number of jumps in at least one second time period preceding the target time period.

[0088] Before adjusting the current jump threshold using the cumulative number of jumps as the adjustment amount, the cumulative number of jumps can also be adjusted using an adjustment coefficient to regulate the impact of the cumulative number of jumps on the target jump threshold, thereby obtaining a target jump threshold that adapts to the current real working conditions.

[0089] For example, the target threshold can be obtained by subtracting the product of the cumulative number of transitions and the adjustment coefficient from the current transition threshold.

[0090] In this embodiment, the target jump threshold can be calculated according to formula (3):

[0091] T1' = T1 –k*∫T2 dt (3)

[0092] Where k represents the adjustment coefficient, and the explanation of other parameters can be found in the formula above.

[0093] In one specific embodiment, the adjustment coefficient can be a preset coefficient, that is, a preset value. For example, the adjustment coefficient can be 0.2.

[0094] In another specific embodiment, considering that mining operations are prone to severe weather conditions such as strong winds, dust storms, and sandstorms, as well as unstructured obstacles such as falling rocks, tumbleweeds, and puddles, which increase the likelihood of trajectory changes for the vehicle, the adjustment coefficient can be determined based on the vehicle's current environmental information. This environmental information indicates the vehicle's location, temperature, presence of obstacles, and surrounding environment.

[0095] In this embodiment, by determining the adjustment coefficient based on the current environmental information of the vehicle, the adjusted cumulative number of jumps can better adapt to the current real operating conditions of the vehicle. Then, by negatively adjusting the current jump threshold based on the adjusted cumulative number of jumps, a target jump threshold that is more in line with the current real operating conditions can be obtained, thereby improving the sensitivity and environmental adaptability of subsequent trajectory jump detection.

[0096] In another specific embodiment, considering that continuous trajectory jumps will have corresponding characteristics in multiple time periods, the cumulative number of jumps can be adjusted based on historical jump patterns. Therefore, the adjustment coefficient can be determined based on the cumulative number of jumps in at least one second time period preceding the target time period. The second time period includes the first time period; if there is only one second time period, the second time period can be the first time period; if there are multiple second time periods, one of the second time periods is the first time period.

[0097] In this embodiment, by determining the adjustment coefficient based on the cumulative number of jumps in at least one second time period prior to the target time period, the cumulative number of jumps can be adaptively adjusted using the historical patterns of continuous trajectory jumps. Then, the target jump threshold can be quickly obtained using the adjusted cumulative number of jumps, thereby improving the sensitivity and environmental adaptability of subsequent trajectory jump detection.

[0098] In another embodiment, the adjustment coefficient can be the sum of a coefficient determined based on the cumulative number of jumps in at least one second time period prior to the target time period and a coefficient determined based on the current environmental information of the vehicle, so as to realize trajectory jump detection by taking into account both the current actual working conditions of the vehicle and the historical patterns of continuous trajectory jumps.

[0099] According to an embodiment of this application, the environmental information includes the vehicle's position and ambient temperature; the adjustment coefficient is determined based on the current environmental information of the vehicle as follows: when the ambient temperature is less than a temperature threshold and the vehicle's position indicates that the vehicle is in the work area, a preset first coefficient is used as the adjustment coefficient; when the ambient temperature is greater than or equal to the temperature threshold, or the vehicle's position indicates that the vehicle is not in the work area, a preset second coefficient is used as the adjustment coefficient, wherein the first coefficient is greater than the second coefficient; wherein the temperature threshold indicates the threshold at which the temperature difference between the ground temperature of the work area and the ambient temperature causes fluctuations in the air refractive index.

[0100] In mining operations, autonomous vehicles or other unmanned vehicles can perform various tasks, such as soil extraction, waste disposal, and transportation. Within the work area, the continuous oxidation and heat generated by coal gangue, residual coal, pyrite, and other materials on the ground cause the ground temperature to be higher than the ambient temperature. If the temperature difference between the ground and the ambient temperature is too large, the heat dissipation from the surface will form "geothermal gas," causing fluctuations in the air refractive index and frequent jumps in millimeter-wave radar point clouds, leading to trajectory jumps. For example, in winter in northern open-pit mines, the ambient temperature in the work area may drop to -15 degrees Celsius, while the ground temperature can reach over 60 degrees Celsius, a temperature difference exceeding 70 degrees Celsius.

[0101] Therefore, when the ambient temperature is below the temperature threshold and the vehicle's position indicates that the vehicle is in the work area, it indicates that the vehicle's current actual working condition is prone to trajectory jumps. In order to detect the trajectory jump anomaly as early as possible, a larger first coefficient can be used as an adjustment coefficient so that the target jump threshold can quickly decay to the value that triggers the anomaly. Conversely, when the ambient temperature is greater than or equal to the temperature threshold or the vehicle's position indicates that the vehicle is not in the work area, the vehicle's current actual working condition is not prone to trajectory jumps. A smaller second coefficient can be used as an adjustment coefficient to avoid oversensitivity to trajectory jump detection.

[0102] For example, the temperature threshold could be -5 degrees Celsius, -15 degrees Celsius, or determined based on the actual situation. The first coefficient could be 0.3, and the second coefficient could be 0.2. The specific values ​​of the first and second coefficients could also be determined based on the actual situation, ensuring that the first coefficient is greater than the second coefficient.

[0103] In the embodiments of this application, by judging the ambient temperature and the vehicle's position, the current actual operating condition of the vehicle can be accurately located. Then, based on the current actual operating condition, a first coefficient or a second coefficient is adaptively selected as the adjustment coefficient. Subsequently, when adjusting the cumulative number of jumps using the adjustment coefficient to obtain the target jump threshold, the trajectory jump detection based on the target jump threshold can balance rapidly improving sensitivity and avoiding oversensitivity.

[0104] Continuous trajectory jumps often exhibit various trends across multiple time periods, such as a gradual increase or decrease in the number of jumps. To further improve the sensitivity of the cumulative number of jumps based on the target jump threshold, the adjustment coefficient used to obtain the target jump threshold can be optimized by combining the cumulative number of jumps in at least one second time period preceding the target time period.

[0105] According to an embodiment of this application, the adjustment coefficient is determined based on the cumulative number of jumps in at least one second time period preceding the target time period in the following manner: determining the relative trend factor of the cumulative number of jumps in the target time period relative to the cumulative number of jumps in a consecutive preset number of second time periods; determining the adjustment coefficient based on the relative trend factor, wherein the adjustment coefficient is positively correlated with the relative trend factor, and the rate of change of the relative trend factor decreases monotonically.

[0106] The relative trend factor is used to indicate the trend of the cumulative number of jumps in the target time period relative to the second time period. For example, the trend can be increasing or decreasing.

[0107] For example, if the consecutive preset number can be 1, then the ratio of the cumulative number of jumps in the second time period to the cumulative number of jumps in the target time period can be used as the relative trend factor. Alternatively, if the consecutive preset number can be an integer greater than 1, then the relative trend factor can be determined by combining the cumulative number of jumps in the consecutive preset number of second time periods.

[0108] An adjustment coefficient can be obtained by applying a non-linear transformation to the relative trend factor. The adjustment coefficient is positively correlated with the relative trend factor, and the rate of change of the relative trend factor decreases monotonically. For example, the adjustment coefficient = 0.3 × m / (1 + m), where m is the relative trend factor.

[0109] In this embodiment, the adjustment coefficient is determined by using the cumulative number of jumps in a preset number of second time periods preceding the target time period. This allows for adaptive adjustment of the cumulative number of jumps based on the historical patterns of continuous trajectory jumps. The adjusted cumulative number of jumps is then used to quickly obtain the target jump threshold, thereby improving the sensitivity and environmental adaptability of subsequent trajectory jump detection.

[0110] According to an embodiment of this application, determining the relative trend factor of the cumulative number of jumps in a target time period relative to the cumulative number of jumps in a consecutive preset number of second time periods includes: determining the average cumulative number of jumps based on the cumulative number of jumps in each of the consecutive preset number of second time periods; and using the ratio of the cumulative number of jumps in the target time period to the average cumulative number of jumps as the relative trend factor.

[0111] For example, the relative trend factor = average cumulative number of jumps / cumulative number of jumps in the specified time period. The preset number of consecutive jumps can be 3 or other values.

[0112] In addition, to avoid the impact of the cumulative number of jumps in the target time period being 0 on the calculation process, the relative trend factor m can also be determined by the following formula (4):

[0113] m = average cumulative number of jumps / max(1, cumulative number of jumps in the target time period) (4)

[0114] Where max(1, cumulative number of jumps in the target time period) represents the maximum value between 1 and the cumulative number of jumps in the target time period.

[0115] In other embodiments, the adjustment coefficient k can also be calculated according to the following formula (5):

[0116] (5)

[0117] in, , The coefficient, determined based on the vehicle's current environmental information, can be called the base attenuation coefficient. The coefficient is determined based on the cumulative number of jumps in at least one second time period preceding the target time period, where m is the relative trend factor.

[0118] For example, when the cumulative number of jumps in the target time period is higher than the average cumulative number of jumps in the previous three consecutive second time periods, the continuous trajectory jumps surge. In this case, m < 1. As k approaches 0, k approaches The target transition threshold decays slowly, thus avoiding excessive sensitivity degradation due to sudden high-frequency transitions within a single time period. When the cumulative number of transitions in the target time period is lower than the average cumulative number of transitions in the previous three consecutive second time periods, the sustained trajectory transitions gradually decrease or remain at a consistently low frequency. In this case, m>1, k>1. The target jump threshold decays rapidly, making trajectory jump detection more sensitive to persistent anomalies or the decay phase where jumps gradually decrease. When the cumulative number of jumps in the target time period is approximately equal to the average cumulative number of jumps in the preceding three consecutive second time periods, persistent trajectory jumps are stable, m is approximately equal to 1, and k is approximately equal to... +0.3*1 / (1+1). For example... When k = 0.3, k is approximately equal to 0.45. At this point, the trajectory jump detection based on the target jump threshold has medium sensitivity.

[0119] Therefore, by integrating the current environmental information of the vehicle and the cumulative number of jumps in at least one second time period before the target time period, the adjustment coefficient can be automatically adjusted according to the historical jump pattern to obtain the target jump threshold that balances instantaneous noise and continuous anomalies, so as to balance the sensitivity of trajectory jump detection based on the target jump threshold.

[0120] According to an embodiment of this application, adjusting the current jump threshold based on the cumulative number of jumps within a target time period to obtain a target jump threshold for the target time period further includes: when the cumulative number of jumps within the target time period is zero, resetting the current jump threshold to a standard jump threshold and using the standard jump threshold as the target jump threshold; wherein, the method further includes: when the control quantity meets the control conditions and / or the vehicle switches from an autonomous driving mode to another driving mode within the target time period, resetting the current jump threshold to a standard jump threshold and using the standard jump threshold as the target jump threshold, wherein the control conditions include at least one of the following: the start-stop intentions of the expected acceleration indications at various times within the target time period are the same, and the speeds at multiple consecutive times within the target time period are greater than the speed threshold.

[0121] A cumulative jump count of zero for the target time period indicates that there are no trajectory jumps at any point in time within the target time period, meaning there are no trajectory jumps for a sustained period. Considering that the target jump threshold for the current target time period can be used as the current jump threshold for the next target time period, to prevent the current jump threshold of the first time period from crossing the target time period and affecting subsequent trajectory jump detection, the current jump threshold can be reset to the standard jump threshold, and this standard jump threshold can be used as the target jump threshold.

[0122] Control conditions can be conditions indicating that there are no trajectory jumps. For example, control conditions can be that the start and stop intentions of the expected acceleration indications at various times within the target time period are the same. The judgment of whether the start and stop intentions are the same can be found above, and will not be repeated here.

[0123] Alternatively, as mentioned above, a vehicle in a parked state is highly attentive to start-stop intentions. It can be determined whether the vehicle has stably exited the parked state by judging whether its speed at multiple consecutive moments within the target time period is greater than a speed threshold. For example, if the speed is greater than the speed threshold of 2 km / h for 3 consecutive seconds, it can be determined that the vehicle has stably exited the parked state. Then, it is further judged whether the start-stop intentions indicated by the expected acceleration at each moment within the target time period are the same. If the vehicle has stably exited the parked state and the start-stop intentions indicated by the expected acceleration at each moment within the target time period are the same, the current jump threshold is reset to the standard jump threshold.

[0124] Other driving modes can be non-autonomous driving modes, such as remote manual driving modes. Since the vehicle's trajectory is controlled by manual operation in non-autonomous driving mode, there will be no trajectory jumps caused by control variables controlling the vehicle. Therefore, the current jump threshold can be directly reset to the standard jump threshold.

[0125] The standard transition threshold is predetermined and can be determined based on the actual situation. For example, it can be the maximum value of the current transition threshold, which is 5, as defined above.

[0126] Furthermore, it is understandable that when the current transition threshold is reset, the vehicle no longer experiences trajectory transitions, and the cumulative transition count for the next target time period is also 0. Alternatively, if the next target time period is obtained by sliding in steps shorter than the duration of the target time period, the transition count and / or cumulative transition count for each moment in the current target time period can be directly reset to 0 while resetting the standard transition threshold.

[0127] In the embodiments of this application, by resetting the current transition threshold, the current transition threshold obtained by the vehicle through continuous attenuation in the historical stage can be quickly reset, so as not to affect the subsequent trajectory transition detection.

[0128] Figure 5 A schematic block diagram of a vehicle control device for trajectory changes according to an embodiment of this application is shown. Figure 5 As shown, the vehicle control device 500 for trajectory changes includes a determination module 510, an adjustment module 520, and a control module 530.

[0129] The determination module 510 is used to determine the cumulative number of jumps in the vehicle trajectory within the target time period. The number of jumps indicates the number of times the control quantity used to obtain the vehicle trajectory changes between two adjacent moments in the autonomous driving mode. The cumulative number of jumps is obtained by the cumulative number of jumps.

[0130] The adjustment module 520 is used to adjust the current jump threshold based on the cumulative number of jumps within the target time period to obtain the target jump threshold for the target time period. The current jump threshold includes the jump threshold for the first time period before the target time period.

[0131] The control module 530 is used to control the vehicle based on the comparison result between the cumulative number of jumps within the target time period and the target jump threshold.

[0132] According to an embodiment of this application, the adjustment module 520 includes an adjustment submodule, which is used to negatively adjust the current jump threshold based on the cumulative number of jumps within the target time period to obtain a target jump threshold, so that the target jump threshold is negatively correlated with the duration of the target time period and / or the number of jumps at each moment within the target time period.

[0133] According to an embodiment of this application, the adjustment submodule includes: an adjustment unit, configured to adjust the cumulative number of jumps within a target time period using an adjustment coefficient, and negatively adjust the current jump threshold based on the adjusted cumulative number of jumps to obtain a target jump threshold; wherein the adjustment coefficient includes at least one of the following: a preset coefficient, a coefficient determined based on the environmental information of the vehicle currently in the time period, and a coefficient determined based on the cumulative number of jumps in at least one second time period prior to the target time period; or, the adjustment coefficient includes the sum of a coefficient determined based on the environmental information of the vehicle currently in the time period and a coefficient determined based on the cumulative number of jumps in at least one second time period prior to the target time period.

[0134] According to an embodiment of this application, the environmental information includes the vehicle's position and ambient temperature; the adjustment coefficient is determined as follows: when the ambient temperature is less than a temperature threshold and the vehicle's position indicates that the vehicle is in the work area, a preset first coefficient is used as the adjustment coefficient; when the ambient temperature is greater than or equal to the temperature threshold, or the vehicle's position indicates that the vehicle is not in the work area, a preset second coefficient is used as the adjustment coefficient, wherein the first coefficient is greater than the second coefficient; wherein the temperature threshold indicates the threshold at which the temperature difference between the ground temperature of the work area and the ambient temperature causes fluctuations in the air refractive index.

[0135] According to an embodiment of this application, the adjustment coefficient is determined as follows: the relative trend factor of the cumulative number of jumps in the target time period relative to the cumulative number of jumps in a consecutive preset number of second time periods is determined; the adjustment coefficient is determined based on the relative trend factor, wherein the adjustment coefficient is positively correlated with the relative trend factor, and the rate of change of the relative trend factor decreases monotonically.

[0136] According to an embodiment of this application, determining the relative trend factor of the cumulative number of jumps in a target time period relative to the cumulative number of jumps in a consecutive preset number of second time periods includes: determining the average cumulative number of jumps based on the cumulative number of jumps in each of the consecutive preset number of second time periods; and using the ratio of the cumulative number of jumps in the target time period to the average cumulative number of jumps as the relative trend factor.

[0137] According to an embodiment of this application, the control quantity includes a desired acceleration for controlling the vehicle to generate a vehicle trajectory; the vehicle control device 500 for trajectory jumps further includes: a first jump count determination module, used to determine the jump count in the later time of two adjacent time periods as one if the difference between the desired accelerations of two adjacent time periods is greater than an acceleration threshold.

[0138] Alternatively, the control quantity may also include speed, and the device may further include: a second jump number determination module, used to determine the number of jumps in the later time step of two adjacent time steps as one when the speed in the later time step is less than the starting speed threshold, the start-stop intentions of the expected acceleration indications in the two adjacent time steps are different, and the difference is greater than the acceleration threshold.

[0139] According to an embodiment of this application, the adjustment module 520 further includes: a first reset submodule, configured to reset the current jump threshold to a standard jump threshold when the cumulative number of jumps within the target time period is zero, and to use the standard jump threshold as the target jump threshold;

[0140] Alternatively, the second reset submodule is used to reset the current jump threshold to the standard jump threshold and use the standard jump threshold as the target jump threshold when the control quantity meets the control conditions and / or the vehicle switches from the autonomous driving mode to other driving modes within the target time period. The control conditions include at least one of the following: the start-stop intentions of the expected acceleration indications at each moment within the target time period are the same, and the speeds at multiple consecutive moments within the target time period are greater than the speed threshold.

[0141] According to an embodiment of this application, the control module 530 includes: interrupting the control of the vehicle using the control quantity at the last moment of the target time period when the cumulative number of transitions within the target time period is greater than or equal to the target transition threshold; and controlling the vehicle using the control quantity at the last moment of the target time period when the cumulative number of transitions within the target time period is less than the target transition threshold.

[0142] The device also includes an alarm module, which is used to send alarm information from the vehicle to the cloud when it is determined that there is a jump in the vehicle and / or the number of jumps at at least once exceeds an alarm threshold.

[0143] Any one or more of the modules, submodules, units, and subunits according to the embodiments of this application, or at least part of the functions of any one or more of them, can be implemented in one module. Any one or more of the modules, submodules, units, and subunits according to the embodiments of this application can be implemented by dividing them into multiple modules. Any one or more of the modules, submodules, units, and subunits according to the embodiments of this application can be at least partially implemented as hardware circuits, such as field-programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems-on-a-chip, systems-on-a-substrate, systems-on-package, application-specific integrated circuits (ASICs), or implemented by hardware or firmware in any other reasonable manner by integrating or packaging circuits, or implemented in any one of software, hardware, and firmware, or in a suitable combination of any of these. Alternatively, one or more of the modules, submodules, units, and subunits according to the embodiments of this application can be at least partially implemented as computer program modules, which, when run, can perform corresponding functions.

[0144] It should be noted that the apparatus portion in the embodiments of this application corresponds to the method portion in the embodiments of this application. The description of the apparatus portion is specifically referred to in the method portion, and will not be repeated here.

[0145] Figure 6 A block diagram of an unmanned vehicle suitable for implementing a vehicle control method for trajectory jumps, according to an embodiment of this application, is illustrated schematically. Figure 6The driverless vehicle shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments in this application. For example, Figure 6 The driverless vehicle shown can be considered as an electronic device with communication, control, and driving functions.

[0146] like Figure 6 As shown, the autonomous vehicle 600 according to an embodiment of this application includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage portion 608 into a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this application.

[0147] RAM 603 stores various programs and data required for the operation of the autonomous vehicle 600. Processor 601, ROM 602, and RAM 603 are interconnected via bus 604. Processor 601 executes various operations of the method flow according to embodiments of this application by executing programs in ROM 602 and / or RAM 603. It should be noted that the programs may also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 may also execute various operations of the method flow according to embodiments of this application by executing programs stored in said one or more memories.

[0148] According to embodiments of this application, the autonomous vehicle 600 may further include an input / output (I / O) interface 605, which is also connected to a bus 604. The autonomous vehicle 600 may also include one or more of the following components connected to the input / output (I / O) interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A driver 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the driver 610 as needed so that computer programs read from it can be installed into the storage section 608 as needed.

[0149] According to embodiments of this application, the method flow according to embodiments of this application can be implemented as a computer software program. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by processor 601, it performs the functions defined in the system of embodiments of this application. According to embodiments of this application, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0150] This application also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0151] According to embodiments of this application, the computer-readable storage medium can be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0152] For example, according to embodiments of this application, a computer-readable storage medium may include the ROM 602 and / or RAM 603 described above and / or one or more memories other than ROM 602 and RAM 603.

[0153] Embodiments of this application also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of this application. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the methods provided in the embodiments of this application.

[0154] When the computer program is executed by the processor 601, it performs the functions defined in the system / apparatus of this application embodiment. According to the embodiments of this application, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0155] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and downloaded and installed via the communication section 609, and / or installed from the removable medium 611. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0156] According to embodiments of this application, program code for executing the computer programs provided in the embodiments of this application can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0157] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features described in the various embodiments of this application can be combined and / or combined in various ways, even if such combinations are not explicitly described in this application. In particular, without departing from the spirit and teachings of this application, the features described in the various embodiments of this application can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of this application.

[0158] The embodiments of this application have been described above. However, these embodiments are merely illustrative and not intended to limit the scope of this application. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Without departing from the scope of this application, those skilled in the art can make various substitutions and modifications, all of which should fall within the scope of this application.

Claims

1. A vehicle control method for trajectory jumps, characterized in that, The method includes: The cumulative number of jumps in the vehicle trajectory within a target time period is determined, wherein the number of jumps indicates the number of times the control quantity used to obtain the vehicle trajectory in autonomous driving mode jumps between two adjacent time points, and the cumulative number of jumps is obtained by accumulating the number of jumps; Based on the cumulative number of jumps within the target time period, the current jump threshold is adjusted to obtain the target jump threshold for the target time period, wherein the current jump threshold includes the jump threshold for the first time period preceding the target time period; The vehicle is controlled based on the comparison between the cumulative number of jumps within the target time period and the target jump threshold.

2. The method according to claim 1, characterized in that, The step of adjusting the current jump threshold based on the cumulative number of jumps within the target time period to obtain the target jump threshold for the target time period includes: Based on the cumulative number of jumps within the target time period, the current jump threshold is negatively adjusted to obtain the target jump threshold, so that the target jump threshold is negatively correlated with the duration of the target time period and / or the number of jumps at each moment within the target time period.

3. The method according to claim 2, characterized in that, The step of negatively adjusting the current jump threshold based on the cumulative number of jumps within the target time period to obtain the target jump threshold includes: The cumulative number of jumps within the target time period is adjusted using an adjustment coefficient, and the current jump threshold is negatively adjusted based on the adjusted cumulative number of jumps to obtain the target jump threshold; The adjustment coefficient includes at least one of the following: a preset coefficient, a coefficient determined based on the environmental information of the current location of the vehicle, and a coefficient determined based on the cumulative number of jumps in at least one second time period prior to the target time period; Alternatively, the adjustment coefficient may include a coefficient determined based on the environmental information currently in which the vehicle is located, and a coefficient determined based on the cumulative number of jumps in at least one second time period prior to the target time period.

4. The method according to claim 3, characterized in that, The environmental information includes the vehicle's location and ambient temperature; the adjustment coefficient is determined as follows: When the ambient temperature is less than the temperature threshold and the vehicle position indicates that the vehicle is in the work area, the preset first coefficient is used as the adjustment coefficient. When the ambient temperature is greater than or equal to the temperature threshold, or when the vehicle position indicates that the vehicle is not in the work area, a preset second coefficient is used as the adjustment coefficient, wherein the first coefficient is greater than the second coefficient; The temperature threshold indicates the threshold at which the temperature difference between the ground temperature and the ambient temperature of the work area causes fluctuations in the air refractive index.

5. The method according to claim 3, characterized in that, The adjustment coefficient is determined in the following manner: Determine the relative trend factor of the cumulative number of jumps in the target time period relative to the cumulative number of jumps in a consecutive preset number of second time periods; The adjustment coefficient is determined based on the relative trend factor, wherein the adjustment coefficient is positively correlated with the relative trend factor, and the rate of change of the relative trend factor decreases monotonically.

6. The method according to claim 5, characterized in that, The factor for determining the relative trend of the cumulative number of jumps in the target time period relative to the cumulative number of jumps in a consecutive preset number of second time periods includes: Based on the cumulative number of transitions for each of the consecutive preset number of the second time periods, the average cumulative number of transitions is determined; and The ratio of the cumulative number of jumps during the target time period to the average cumulative number of jumps is used as the relative trend factor.

7. The method according to any one of claims 1 to 6, characterized in that, The control quantity includes a desired acceleration used to control the vehicle to generate the vehicle trajectory; The method further includes: If the difference between the expected accelerations at two adjacent moments is greater than the acceleration threshold, the number of jumps at the later moment in the two adjacent moments is determined to be one. Alternatively, the control quantity may also include speed, and the method may further include: If, in two adjacent moments, the speed at the later moment is less than the starting speed threshold, the start-stop intentions of the expected acceleration indications at the two adjacent moments are different, and the difference is greater than the acceleration threshold, then the number of jumps at the later moment in the two adjacent moments is determined to be one.

8. The method according to any one of claims 1 to 6, characterized in that, The step of adjusting the current jump threshold based on the cumulative number of jumps within the target time period to obtain the target jump threshold for the target time period further includes: If the cumulative number of transitions within the target time period is zero, the current transition threshold is reset to the standard transition threshold, and the standard transition threshold is used as the target transition threshold. The method further includes: If the control quantity meets the control conditions and / or the vehicle switches from the autonomous driving mode to another driving mode within the target time period, the current jump threshold is reset to the standard jump threshold, and the standard jump threshold is used as the target jump threshold. The control conditions include at least one of the following: the start-stop intentions of the expected acceleration indications at each moment within the target time period are the same, and the speeds at multiple consecutive moments within the target time period are greater than the speed threshold.

9. The method according to any one of claims 1 to 6, characterized in that, The control of the vehicle based on the comparison result between the cumulative number of jumps within the target time period and the target jump threshold includes: If the cumulative number of transitions within the target time period is greater than or equal to the target transition threshold, the control of the vehicle using the control quantity at the last moment of the target time period shall be interrupted. If the cumulative number of transitions within the target time period is less than the target transition threshold, the vehicle is controlled using the control quantity at the last moment of the target time period; The method further includes: If it is determined that the vehicle has a jump and / or the number of jumps at at least one time exceeds the alarm threshold, an alarm message is sent to the cloud via the vehicle.

10. An unmanned vehicle, comprising: One or more processors; Memory, used to store one or more programs. The feature is that, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of 1 to 9 above.

Images