Vehicle speed control method for ramp to merge into main road and related device

Abstract

The invention discloses a vehicle speed control method for a ramp to merge into a main road and a related device. The method comprises the following steps: acquiring guide line information, road topological structure information, road environment information, lane traffic flow motion state information and own vehicle motion state information according to a ramp to merge into the main road instruction; according to the guide line information, the road topological structure information, the lane traffic flow motion state information, the road environment information and the self-vehicle motion state information, an afflux mode is judged, the target acceleration for activating the afflux mode is calculated, and the afflux mode comprises a pre-deceleration mode, an adaptive mode, a waiting mode and a failure mode. And controlling the target speed of the target vehicle when the target vehicle merges into the main road from the ramp according to the target acceleration, and controlling the target vehicle to run according to the target speed, so that the safety experience of automatic driving can be improved, and the comfort and robustness of the vehicle are improved through control of multiple merge modes.

Description

Technical Field

[0001] This application relates to the field of computers, and in particular, to a vehicle speed control method and related device for a ramp merging into a main road. Background Art

[0002] With the rapid development of the automotive industry, autonomous driving technology is also developing rapidly. In autonomous driving technology, the automatic on-ramp and off-ramp of vehicles is an important scenario. Among them, due to the characteristics of the road structure when a ramp merges into a main road, in most scenarios, there are relevant vehicles in front of and behind the target lane, and there may also be limiting factors such as congestion in the target lane. Therefore, the scenario of a ramp merging into a main road is one of the most difficult scenarios for autonomous driving technology. The performance of a vehicle merging from a ramp into a main road directly affects the user's experience of autonomous driving, as well as the safety and comfort of autonomous driving, and also affects the driving efficiency of the vehicle on the ramp.

[0003] Therefore, there is an urgent need for a vehicle speed control method for a ramp merging into a main road. Summary of the Invention

[0004] This application provides a vehicle speed control method and related device for a ramp merging into a main road, which can improve the safety and comfort of autonomous driving, and further improve the driving efficiency of the vehicle on the ramp.

[0005] This application provides a vehicle speed control method for a ramp merging into a main road, and the method includes:

[0006] Obtain guiding line information, road topology structure information, road environment information, lane traffic flow movement state information, and self-vehicle movement state information according to a ramp merging into main road instruction;

[0007] Judge the merging mode according to the guiding line information, the road topology structure information, the lane traffic flow movement state information, the road environment information, and the self-vehicle movement state information, and calculate the target acceleration for activating the merging mode. The merging modes include a pre-deceleration mode, an adaptive mode, a waiting mode, and a failure mode;

[0008] Control the target speed of the target vehicle when merging from the ramp into the main road according to the target acceleration, and control the driving of the target vehicle according to the target speed.

[0009] Optionally, when the merging mode is the pre-deceleration mode, the road topology structure information includes the form of the road topology structure, the starting distance of the main road merging opening, the ending distance of the main road merging opening, and the current lane cut-off point distance, and the self-vehicle movement state information includes the current vehicle speed of the self-vehicle;

[0010] Judging the merging mode based on the guiding line information, the road topology structure information, the lane traffic flow movement state information, the road environment information, and the ego-vehicle movement state information, and calculating the target acceleration for activating the merging mode includes:

[0011] Calculating the opening length of the ramp merging into the main road based on the starting distance of the main road merging opening, the ending distance of the main road merging opening, and the current lane cut-off point distance;

[0012] If the road topology structure form is the ramp merging form, and the opening length is less than the first distance threshold for a preset time, and the current lane cut-off point distance is less than the second distance threshold for the preset time, then it is judged to activate the pre-deceleration mode;

[0013] Calculating a preliminary ideal vehicle speed curve based on the starting distance of the main road merging opening, correcting the preliminary ideal vehicle speed curve using the opening length to obtain a corrected ideal vehicle speed curve, and calculating the target acceleration of the pre-deceleration mode based on the current vehicle speed of the ego-vehicle and the corrected ideal vehicle speed curve.

[0014] Optionally, calculating the opening length of the ramp merging into the main road based on the starting distance of the main road merging opening, the ending distance of the main road merging opening, and the current lane cut-off point distance includes:

[0015] The opening length of the ramp merging into the main road is the difference between the minimum value between the current lane cut-off point distance and the ending distance of the main road merging opening and the starting distance of the main road merging opening.

[0016] Optionally, the merging mode is the adaptive mode, the road topology structure information includes the road topology structure form and the current lane cut-off point distance, the ego-vehicle movement state information includes the current position of the ego-vehicle and the current vehicle speed of the ego-vehicle, the lane traffic flow movement state information includes the positions and driving speeds of multiple vehicles, the multiple vehicles include a first vehicle, a second vehicle, and a third vehicle, the first vehicle is the vehicle in front of the second vehicle during driving, the second vehicle is the vehicle in front of the target vehicle after merging into the main road lane, and the third vehicle is the vehicle behind the target vehicle after merging into the main road lane;

[0017] Judging the merging mode based on the guiding line information, the road topology structure information, the lane traffic flow movement state information, the road environment information, and the ego-vehicle movement state information, and calculating the target acceleration for activating the merging mode includes:

[0018] Calculating a first distance based on the current position of the ego-vehicle and the current lane cut-off point distance, where the first distance is the distance between the current position of the ego-vehicle and the current lane cut-off point distance;

[0019] If the road topology form is the ramp merging form and the first distance is less than the third distance threshold, it is determined to activate the adaptive mode;

[0020] Calculate the first control acceleration of the target vehicle based on the position and driving speed of the first vehicle; calculate the second control acceleration of the target vehicle based on the position and driving speed of the second vehicle; calculate the third control acceleration of the target vehicle based on the position and driving speed of the third vehicle;

[0021] Determine the minimum value among the first control acceleration, the second control acceleration, and the third control acceleration as the target acceleration of the adaptive mode.

[0022] Optionally, the calculating the first control acceleration of the target vehicle based on the position and driving speed of the first vehicle; calculating the second control acceleration of the target vehicle based on the position and driving speed of the second vehicle; calculating the third control acceleration of the target vehicle based on the position and driving speed of the third vehicle includes:

[0023] Obtain the ideal following distance and the collision time between the target vehicle and the third vehicle;

[0024] Calculate the first time distance value and the first actual following distance between the target vehicle and the first vehicle based on the current position of the host vehicle and the position of the first vehicle, calculate the first speed difference based on the current speed of the host vehicle and the driving speed of the first vehicle, calculate the first distance difference based on the first actual following distance and the ideal following distance, and calculate the first control acceleration based on the sum of the product of the first distance difference and the first error coefficient and the product of the first speed difference and the second error coefficient, where the second error coefficient is determined based on the first time distance value;

[0025] Calculate the second time distance value and the second actual following distance between the target vehicle and the second vehicle based on the current position of the host vehicle and the position of the second vehicle, calculate the second speed difference based on the current speed of the host vehicle and the driving speed of the second vehicle, calculate the second distance difference based on the second actual following distance and the ideal following distance, and calculate the second control acceleration based on the sum of the product of the second distance difference and the third error coefficient and the product of the second speed difference and the fourth error coefficient, where the fourth error coefficient is determined based on the second time distance value;

[0026] Calculate the third actual following distance between the target vehicle and the third vehicle based on the current position of the host vehicle and the position of the first vehicle. Determine whether the third vehicle is in a dangerous state based on whether the time to collision is less than the collision threshold or whether the third actual following distance is less than the following threshold. According to whether the third vehicle is in a dangerous state, respectively correct the driving speed and the third actual following distance of the third vehicle in the current state to obtain the corrected speed and the corrected following distance. Calculate the third speed difference based on the current speed of the host vehicle and the corrected speed. Calculate the third distance difference based on the corrected following distance and the ideal following distance. Calculate the third control acceleration based on the sum of the product of the third distance difference and the fifth error coefficient and the product of the third speed difference and the sixth error coefficient.

[0027] Optionally, the method further includes:

[0028] Judge whether the suppression condition of the adaptive mode is triggered. If the suppression condition has been triggered, exit the adaptive mode;

[0029] The suppression condition includes one or more of a state suppression condition, a vehicle suppression condition, and a guiding line suppression condition; the state suppression condition is that the distance to the end point of the current lane is greater than the fourth distance threshold or the autonomous driving system sends an instruction to exit the ramp and merge into the main road; if the target vehicle approaches the lane edge, the vehicle suppression condition is that the distances between the target vehicle and the first vehicle, the second vehicle, and the third vehicle are less than the too-close threshold, the times to collision between the target vehicle and the first vehicle, the second vehicle, and the third vehicle are less than the collision threshold, or whether the second control acceleration and the third control acceleration have opposite trends; the guiding line suppression condition is that the waiting mode has been activated and the monitoring acceleration of the waiting mode is less than the monitoring threshold for a fixed time.

[0030] Optionally, the host vehicle motion state information includes the current speed of the host vehicle, the lane traffic flow motion state information includes the positions and driving speeds of multiple vehicles, the multiple vehicles include a first vehicle, a second vehicle, and a third vehicle, the first vehicle is the vehicle in front of the second vehicle during driving, the second vehicle is the vehicle in front of the target vehicle after merging into the main road lane, the third vehicle is the vehicle behind the target vehicle after merging into the main road lane, and the road environment information includes lane line parameter information;

[0031] The determination of the merging mode based on the guiding line information, the road topology structure information, the lane traffic flow motion state information, the road environment information, and the host vehicle motion state information and the calculation of the target acceleration for activating the merging mode include:

[0032] Determine whether to activate the adaptive mode based on the road topology information, the lane traffic flow movement state information, and the host vehicle movement state information. If the adaptive mode is activated, determine whether the activation condition of the waiting mode is triggered. If the activation condition has been triggered, exit the adaptive mode and activate the waiting mode;

[0033] The activation conditions include a danger condition and a congestion condition. The danger condition is that the time to collision between the target vehicle and the third vehicle is less than the collision threshold, and the congestion condition is that the distances between the first vehicle, the second vehicle, and the third vehicle pairwise are less than the too-close distance threshold;

[0034] Calculate the ideal vehicle speed curve based on the cross-line longitudinal distance, calculate the target acceleration of the waiting mode based on the host vehicle's current speed and the ideal vehicle speed curve, and calculate the cross-line longitudinal distance for the target vehicle to merge into the main road based on the guiding line information and the lane line parameter information.

[0035] Optionally, the merging mode is the failure mode. The road topology information includes the distance to the end point of the current lane, and the host vehicle movement state information includes the host vehicle's current speed and the host vehicle's current position;

[0036] The determination of the merging mode and the calculation of the target acceleration for activating the merging mode according to the guiding line information, the road topology information, the lane traffic flow movement state information, the road environment information, and the host vehicle movement state information include:

[0037] Calculate a first distance based on the host vehicle's current position and the distance to the end point of the current lane. The first distance is the distance between the host vehicle's current position and the distance to the end point of the current lane;

[0038] If the first distance is greater than 0 and less than the fifth distance threshold, and both the lateral function and the longitudinal function of the automatic driving system are in the activated state, then determine to activate the failure mode;

[0039] Calculate the ideal vehicle speed curve based on the distance to the end point of the current lane, calculate the first acceleration of the failure mode based on the host vehicle's current speed and the ideal vehicle speed curve; calculate the ideal acceleration limit curve based on the distance to the end point of the current lane, and calculate the second acceleration of the failure mode based on the ideal acceleration limit curve; if the first distance is less than the too-close distance threshold, then obtain the third acceleration of the failure mode; determine the minimum value among the first acceleration, the second acceleration, and the third acceleration as the target acceleration of the failure mode.

[0040] Optionally, the method further includes:

[0041] Determine whether the suppression condition of the failure mode is triggered. If the suppression condition has been triggered, exit the failure mode;

[0042] The suppression condition includes one or more of a takeover suppression condition, a state suppression condition, and a cut-off point suppression condition; the takeover suppression condition is to receive an operation of the user on the vehicle, the state suppression condition is that the longitudinal function of the automatic driving system is in an inactive state or the lateral function is in a lane-changing state, and the cut-off point suppression condition is that the current lane cut-off point distance is greater than a sixth distance threshold or the increase amount of the current lane cut-off point distance within the same time interval is greater than an increase threshold.

[0043] Optionally, the method further includes:

[0044] If at least two merging modes are activated simultaneously, determine the actual acceleration of the target vehicle in the following order of decreasing priority, and the order of decreasing priority is the target acceleration of the waiting mode, the target acceleration of the adaptive mode, the target acceleration of the failure mode, and the target acceleration of the pre-deceleration mode.

[0045] Optionally, the self-vehicle motion state information includes the current speed of the self-vehicle, and the method further includes:

[0046] If the waiting mode has been activated, the current speed of the self-vehicle gradually decreases and the current speed of the self-vehicle is less than a first speed threshold, send a takeover reminder message to the user.

[0047] Optionally, the road topology structure information includes the current lane cut-off point distance, the self-vehicle motion state information includes the current speed of the self-vehicle, and the method further includes:

[0048] If the failure mode has been activated, the current lane cut-off point distance is less than a too-close distance threshold and the current speed of the self-vehicle is less than a second speed threshold, send a takeover reminder message to the user.

[0049] The present application provides a vehicle speed control device for merging from a ramp into a main road, and the device includes:

[0050] An acquisition unit, configured to acquire guiding line information, road topology structure information, road environment information, lane traffic flow motion state information, and self-vehicle motion state information according to a ramp merging into main road instruction;

[0051] A calculation unit, configured to determine a merging mode according to the guiding line information, the road topology structure information, the lane traffic flow motion state information, the road environment information, and the self-vehicle motion state information, and calculate a target acceleration for activating the merging mode, and the merging mode includes a pre-deceleration mode, an adaptive mode, a waiting mode, and a failure mode;

[0052] A control unit is configured to control the target speed of a target vehicle when merging from a ramp into a main road according to the target acceleration, and control the driving of the target vehicle according to the target speed.

[0053] The present application provides a computer-readable storage medium including instructions which, when running on a computer, cause the computer to execute the method described in any one of the above.

[0054] The present application provides a vehicle speed control method for merging from a ramp into a main road. The method includes: obtaining guiding line information, road topology information, road environment information, lane traffic flow movement state information, and own vehicle movement state information according to a ramp-merging-into-main-road instruction, and these information are all helpful for subsequent automatic vehicle speed control when merging from a ramp into a main road. Judging the merging mode and calculating the target acceleration for activating the merging mode according to the guiding line information, road topology information, lane traffic flow movement state information, road environment information, and own vehicle movement state information. The merging modes include a pre-deceleration mode, an adaptive mode, a waiting mode, and a failure mode, that is, by designing multiple merging modes for various situations of merging from a ramp into a main road, the scenarios of autonomous driving are greatly enriched, and the safety and comfort of autonomous driving can also be improved. Controlling the target speed of the target vehicle when merging from a ramp into a main road according to the target acceleration, and controlling the driving of the target vehicle according to the target speed, which can improve the experience of autonomous driving and improve the driving efficiency of the vehicle in the ramp through the control of multiple merging modes. Description of the Drawings

[0055] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0056] Figure 1 It is a flowchart of a vehicle speed control method for merging from a ramp into a main road provided by an embodiment of the present application;

[0057] Figure 2 It is a schematic diagram of a vehicle speed control logic for merging from a ramp into a main road provided by an embodiment of the present application;

[0058] Figure 3 It is a structural block diagram of a vehicle speed control device for merging from a ramp into a main road provided by an embodiment of the present application. Detailed Embodiments

[0059] To enable those skilled in the art to better understand the solution of this application, the following will clearly and completely describe the technical solutions in the embodiments of this application in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without making creative efforts shall fall within the scope of protection of this application.

[0060] With the rapid development of the automotive industry, autonomous driving technology is also developing rapidly. Autonomous driving technology includes intelligent pilot assistance functions, which integrate functions such as adaptive cruise control, lane keeping, automatic lane change, and autonomous decision-making for entering and exiting ramps. For the intelligent pilot assistance function, the automatic entry and exit of ramps by vehicles is an important scenario. Among them, due to the characteristics of the road structure when merging from a ramp into the main road, in most scenarios, there are relevant vehicles in front of and behind the target lane, and there may also be limiting factors such as congestion in the target lane. Therefore, the scenario of merging from a ramp into the main road is one of the most difficult scenarios for autonomous driving technology. The performance of a vehicle merging from a ramp into the main road directly affects the user experience of autonomous driving, as well as the safety and comfort of autonomous driving. It also affects the driving efficiency of the vehicle within the ramp.

[0061] There are some deficiencies in the current speed control methods for merging from a ramp into the main road: First, the speed control of the current intelligent driving assistance system is not comfortable. Although it can consider the traffic flow state for speed control, its speed control is not anthropomorphic enough, which easily reduces the user experience. Moreover, in the scenario of merging from a ramp into the main road, the robustness of the speed control function is poor, and the speed control function frequently exits. Second, the interaction experience of the speed control function is poor. Users have a low perception of the state of the speed control function, which easily reduces the user's safety experience of autonomous driving. Third, in the current speed control for merging from a ramp into the main road, it mostly relies on information such as vehicle-road cooperation and cloud technology for speed control. The popularization and application of such technologies are difficult, and it is difficult to be widely applied in a short time, so the practicality is poor.

[0062] Therefore, there is an urgent need for a speed control method for merging from a ramp into the main road.

[0063] Based on this, the present application provides a vehicle speed control method for a ramp merging into a main road. The method includes: obtaining guiding line information, road topology structure information, road environment information, lane traffic flow movement state information, and the movement state information of the host vehicle according to the ramp merging into the main road instruction. All these information contribute to the subsequent automatic vehicle speed control for the ramp merging into the main road. Judging the merging mode according to the guiding line information, road topology structure information, lane traffic flow movement state information, road environment information, and the movement state information of the host vehicle, and calculating the target acceleration for activating the merging mode. The merging modes include a pre-deceleration mode, an adaptive mode, a waiting mode, and a failure mode. That is, by designing multiple merging modes for various situations of the ramp merging into the main road, the scenarios of autonomous driving are greatly enriched, and the safety and comfort of autonomous driving can also be improved. Controlling the target speed of the target vehicle when merging from the ramp into the main road according to the target acceleration, and controlling the driving of the target vehicle according to the target speed, which can improve the experience of autonomous driving and improve the driving efficiency of the vehicle in the ramp through the control of multiple merging modes.

[0064] To better understand the technical solutions and technical effects of the present application, the following will describe specific embodiments in detail with reference to the accompanying drawings.

[0065] See Figure 1 , which is a flowchart of a vehicle speed control method for a ramp merging into a main road provided by an embodiment of the present application.

[0066] The vehicle speed control method for a ramp merging into a main road provided by this embodiment can be applied to an autonomous driving system, and the autonomous driving system can be an intelligent piloting system.

[0067] The vehicle speed control method for a ramp merging into a main road provided by this embodiment includes the following steps:

[0068] S101, obtaining guiding line information, road topology structure information, road environment information, lane traffic flow movement state information, and the movement state information of the host vehicle according to the ramp merging into the main road instruction.

[0069] In the embodiment of the present application, the intelligent piloting system can send a ramp merging into the main road instruction, and then obtain the information required for the ramp merging into the main road according to the ramp merging into the main road instruction, such as guiding line information, road topology structure information, road environment information, lane traffic flow movement state information, and the movement state information of the host vehicle. Among them, the host vehicle is the target vehicle.

[0070] The road topology structure information includes the form of the road topology structure, the starting distance of the opening for merging into the main road, the ending distance of the opening for merging into the main road, the distance of the current lane cut-off point, the distance of the left lane cut-off point, the distance of the right lane cut-off point, and the left-right direction of merging into the main road.

[0071] The guiding line information is the planned path generated based on the road topology information in the geodetic coordinate system. The specific calculation method is as follows:

[0072] Y = C0 + C1×S + C2×S2 + C3×S3 + C4×S4 + C5×S5,

[0073] Y' = C1 + 2×C2×S + 3×C3×S2 + 4×C4×S3 + 5×C5×S4,

[0074] Y” = 2×C2 + 6×C3×S + 12×C4×S2 + 20×C5×S3,

[0075] Where Y is the lateral movement distance of the vehicle, S is the longitudinal movement distance of the vehicle, Y' is the lateral movement speed of the vehicle, Y” is the lateral movement acceleration of the vehicle, and C0 - C5 are a set of coefficients representing a fifth-degree polynomial.

[0076] From the above formulas, it can be seen that through the guiding line information of the vehicle merging from the ramp into the main road, the lateral position of the vehicle at any longitudinal position can be obtained, and thus the vehicle's straddle position during the ramp merging into the main road and the movement relationship between the vehicle and the front and rear vehicles can be judged.

[0077] The road environment information includes the lane line parameter information on the left and right sides of the vehicle. The lane line parameter information on the left and right sides of the vehicle is the lane line equation in the vehicle's own coordinate system. The specific calculation method is as follows:

[0078] Y = C0 + C1×S + C2×S2 + C3×S3,

[0079] Where Y is the lateral distance of the vehicle from the lane line at S, S is the vehicle's preview distance, and C0 - C3 are a set of coefficients representing a third-degree polynomial. From the above formulas, it can be seen that the position relationship between the vehicle and the lane line can be known through different preview distances.

[0080] The lane traffic flow movement state information includes the positions of multiple vehicles, the accelerations of multiple vehicles, and the driving speeds of multiple vehicles. The multiple vehicles include the first vehicle, the second vehicle, the third vehicle, and the fourth vehicle. The first vehicle is the vehicle in front of the second vehicle during driving. The second vehicle is the vehicle in front of the target vehicle after it merges into the main road lane. The third vehicle is the vehicle behind the target vehicle after it merges into the main road lane. The fourth vehicle is the vehicle behind the third vehicle during driving. That is to say, the relationship between multiple vehicles is the relationship of the front and rear vehicles after the target vehicle merges into a certain lane of the main road.

[0081] The self-vehicle movement state information includes the current position of the self-vehicle, the current vehicle speed of the self-vehicle, the torque applied by the user to the steering wheel, and the state of whether the user steps on the accelerator pedal.

[0082] In an embodiment of the present application, after obtaining the road topology structure information, the road topology structure information can be verified to facilitate the subsequent merging mode determination process. If the verification fails, the subsequent merging mode determination process is not activated.

[0083] The specific verification process is as follows:

[0084] If the distance to the current lane cut-off point suddenly jumps from a large value to a value close to 0, it is determined that the road topology structure information is invalid, and this invalid determination is cancelled until the distance to the current lane cut-off point becomes a large value again.

[0085] If, when the vehicle has an obvious speed, the distance to the current lane cut-off point remains at a large value and does not change, it is determined that the road topology structure information is invalid.

[0086] S102, determine the merging mode based on the guiding line information, road topology structure information, lane traffic flow movement state information, road environment information, and own vehicle movement state information, and calculate the target acceleration for activating the merging mode.

[0087] In an embodiment of the present application, after obtaining the guiding line information, road topology structure information, lane traffic flow movement state information, road environment information, and own vehicle movement state information, the merging mode can be determined based on this information, and the target acceleration for activating the merging mode can be calculated. The merging mode can include a pre-deceleration mode, an adaptive mode, a waiting mode, and a failure mode. These merging modes cover several situations of merging from a ramp into the main road. Each merging mode has different activation conditions. By designing multiple merging modes for various situations of merging from a ramp into the main road, the scenarios of autonomous driving are greatly enriched. Different vehicle speed controls are performed according to different merging modes, which can improve the safety and comfort of autonomous driving and enhance the robustness of autonomous driving for merging from a ramp into the main road.

[0088] The activation conditions for each merging mode are introduced in detail below:

[0089] The first merging mode is the pre-deceleration mode. At this time, the opening length of merging from the ramp into the main road is calculated based on the starting distance of the merging opening into the main road, the ending distance of the merging opening into the main road, and the distance to the current lane cut-off point.

[0090] Specifically, the opening length of merging from the ramp into the main road is the difference between the minimum value between the distance to the current lane cut-off point and the ending distance of the merging opening into the main road and the starting distance of the merging opening into the main road. For example, the formula is expressed as follows:

[0091] L_RampLength = min(D_LaneEndCur, D_RampEnd) - D_RampStart,

[0092] Among them, D_LaneEndCur is the distance of the current lane end point, D_RampEnd is the ending distance of the on-ramp to the main road opening, and D_RampStart is the starting distance of the on-ramp to the main road opening.

[0093] The activation condition of the pre-deceleration mode is that the road topology form is the on-ramp merging form, the opening length is less than the first distance threshold for a preset time, and the distance of the current lane end point is less than the second distance threshold for a preset time. If the above activation conditions are met, it is determined that the pre-deceleration mode is activated. Among them, the first distance threshold is 150 meters (m), the second distance threshold is 400 m, and the preset time is 1 second (s).

[0094] After determining the activation of the pre-deceleration mode, the target acceleration of the target vehicle when the pre-deceleration mode is activated can be calculated. The preliminary ideal speed curve can be calculated based on the starting distance of the on-ramp to the main road opening. The preliminary ideal speed curve is corrected using the opening length to obtain the corrected ideal speed curve. The target acceleration of the pre-deceleration mode is calculated based on the current vehicle speed of the host vehicle and the corrected ideal speed curve. When correcting the preliminary ideal speed curve using the opening length, the range of the correction coefficient is 0.9 - 1, and the opening length and the correction coefficient are in a proportional relationship, that is, the smaller the opening length, the smaller the correction coefficient.

[0095] The second merging mode is the adaptive mode. At this time, the first distance is calculated based on the current position of the host vehicle and the distance of the current lane end point. The first distance is the distance between the current position of the host vehicle and the distance of the current lane end point.

[0096] The activation condition of the adaptive mode is that the road topology form is the on-ramp merging form, the intelligent pilot system has the intention of merging from the on-ramp to the main road, and the effective guiding line information for merging into the main road is obtained. The first distance is less than the third distance threshold. If the above activation conditions are met, it is determined that the adaptive mode is activated. Among them, the third distance threshold is 100 m.

[0097] After determining to activate the adaptive mode, the target acceleration of the target vehicle when the adaptive mode is activated can be calculated. The first control acceleration of the target vehicle can be calculated based on the position and driving speed of the first vehicle. The second control acceleration of the target vehicle can be calculated based on the position and driving speed of the second vehicle. The third control acceleration of the target vehicle can be calculated based on the position and driving speed of the third vehicle. The minimum value among the first control acceleration, the second control acceleration, and the third control acceleration is determined as the target acceleration of the adaptive mode. That is to say, when using the adaptive mode to control the speed of merging from a ramp into the main road, it is necessary to consider the situations of other vehicles in front of and behind the target vehicle when it merges into a certain lane on the main road, and intelligently adjust the acceleration of the target vehicle according to the situations of other vehicles. For example, the control accelerations of the target vehicle can be determined respectively for the first vehicle, the second vehicle, and the third vehicle, and then the target acceleration of the target vehicle can be obtained. This can improve the safety and comfort of the autonomous driving when merging from a ramp into the main road.

[0098] Specifically, to calculate the control acceleration of the target vehicle intelligently adjusted according to the first vehicle, the second vehicle, and the third vehicle, the ideal following distance of the host vehicle when the target vehicle merges into a certain lane on the main road can be calculated first, and then the ideal following distance of the host vehicle can be corrected in combination with the normal following distance on the main road. The correction coefficient can be 0.6 to obtain the ideal following distance. The collision times between the target vehicle and the first vehicle, the second vehicle, the third vehicle, and the fourth vehicle when the target vehicle merges into a certain lane on the main road can also be calculated.

[0099] Then, the control accelerations of the target vehicle intelligently adjusted according to the first vehicle, the second vehicle, and the third vehicle are calculated respectively, and the specific introduction is as follows:

[0100] Calculating the control acceleration of the target vehicle intelligently adjusted according to the first vehicle: Calculate the first time distance value between the target vehicle and the first vehicle and the first actual following distance between the target vehicle and the first vehicle based on the current position of the host vehicle and the position of the first vehicle. Calculate the first speed difference based on the current speed of the host vehicle and the driving speed of the first vehicle. Calculate the first distance difference based on the first actual following distance and the ideal following distance. Calculate the first control acceleration based on the sum of the product of the first distance difference and the first error coefficient and the product of the first speed difference and the second error coefficient. Among them, the second error coefficient is determined according to the first time distance value. For example, the second error coefficient can be obtained by correcting the original error coefficient using the first time distance value. The second error coefficient is in a proportional relationship with the first time distance value, that is, if the first time distance value is small, the second error coefficient decreases accordingly, which can improve the influence of the distance difference between the first vehicle and the target vehicle on the control of the target vehicle.

[0101] The control acceleration of the target vehicle intelligently adjusted according to the first vehicle can be expressed by a formula:

[0102] a_veh1 = v_err1 × v_err_coe1 + d_err1 × d_err_coe1,

[0103] v_err_coe1 = v_err_coe_ori1 × min(max(THW1, 0.2), 1),

[0104] where a_veh1 is the first control acceleration, v_err1 is the first speed difference, v_err_coe1 is the second error coefficient, d_err1 is the first distance difference, d_err_coe1 is the first error coefficient, v_err_coe_ori1 is the original error coefficient, and THW1 is the time to collision between the target vehicle and the first vehicle.

[0105] Calculate the control acceleration of the target vehicle intelligently adjusted according to the second vehicle: Calculate the second time - distance value between the target vehicle and the second vehicle and the second actual following distance between the target vehicle and the second vehicle based on the current position of the host vehicle and the position of the second vehicle. Calculate the second speed difference based on the current speed of the host vehicle and the traveling speed of the second vehicle. Calculate the second distance difference based on the second actual following distance and the ideal following distance. Calculate the second control acceleration based on the sum of the product of the second distance difference and the third error coefficient and the product of the second speed difference and the fourth error coefficient. Among them, the fourth error coefficient is determined according to the second time - distance value. For example, the fourth error coefficient can be obtained by correcting the original error coefficient using the second time - distance value, and the fourth error coefficient is in a direct - proportion relationship with the second time - distance value. That is, if the second time - distance value is small, the fourth error coefficient decreases accordingly, so as to improve the influence of the distance difference between the second vehicle and the target vehicle on the control of the target vehicle.

[0106] The control acceleration of the target vehicle intelligently adjusted according to the second vehicle can be expressed by a formula:

[0107] a_veh2 = v_err2 × v_err_coe2 + d_err2 × d_err_coe2,

[0108] v_err_coe2 = v_err_coe_ori2 × min(max(THW2, 0.2), 1),

[0109] Where, a_veh2 is the second control acceleration, v_err2 is the second speed difference, v_err_coe2 is the fourth error coefficient, d_err2 is the second distance difference, d_err_coe2 is the third error coefficient, v_err_coe_ori2 is the original error coefficient, and THW2 is the time to collision between the target vehicle and the second vehicle.

[0110] Calculate the control acceleration of the target vehicle intelligently adjusted according to the third vehicle: Calculate the third actual following distance between the target vehicle and the third vehicle based on the current position of the host vehicle and the position of the first vehicle, determine whether the third vehicle is in a dangerous state according to whether the time to collision is less than the collision threshold or whether the third actual following distance is less than the following threshold, and respectively correct the driving speed and the third actual following distance of the third vehicle in the current state according to whether the third vehicle is in a dangerous state to obtain the corrected speed and the corrected following distance, calculate the third speed difference based on the current vehicle speed of the host vehicle and the corrected speed, calculate the third distance difference based on the corrected following distance and the ideal following distance, and calculate the third control acceleration based on the sum of the product of the third distance difference and the fifth error coefficient and the product of the third speed difference and the sixth error coefficient.

[0111] The calculation of the control acceleration of the target vehicle intelligently adjusted according to the third vehicle can be expressed by a formula:

[0112] a_veh3 = v_err3 × v_err_coe3 + d_err3 × d_err_coe3,

[0113] Where, a_veh3 is the third control acceleration, v_err3 is the third speed difference, v_err_coe3 is the sixth error coefficient, d_err3 is the third distance difference, and d_err_coe3 is the fifth error coefficient.

[0114] Before calculating the control acceleration of the target vehicle intelligently adjusted according to the third vehicle, it is necessary to determine whether the third vehicle is in a dangerous state. The judgment condition is whether the time to collision between the target vehicle and the third vehicle is less than the collision threshold or whether the third actual following distance is less than the following threshold. If the time to collision is less than the collision threshold or the third actual following distance is less than the following threshold, it is a dangerous state. If the time to collision is greater than the collision threshold or the first actual following distance is greater than the following threshold, it is a safe state, or, except for the conditions of being in a dangerous state, it is in a safe state. For example, the collision threshold is 15 s and the following threshold is 10 m.

[0115] When the third vehicle is in different states, the corrections to the driving speed and the third actual following distance of the third vehicle are different:

[0116] When the third vehicle is in a dangerous state, the corrected following distance is the ideal following distance multiplied by 2 minus the actual following distance of the third vehicle, and the corrected speed is the driving speed of the third vehicle.

[0117] When the third vehicle is in a safe state, the corrected following distance is the ideal following distance plus 2, and the corrected speed is the current vehicle speed of the host vehicle.

[0118] The third merging mode is the waiting mode. The activation condition of the waiting mode is to judge whether to activate the adaptive mode according to the road topology structure information, the lane traffic flow movement state information and the host vehicle movement state information. If the adaptive mode is activated, whether the activation condition of the waiting mode is triggered. If the activation condition has been triggered, then exit the adaptive mode and activate the waiting mode.

[0119] Among them, the activation conditions include dangerous conditions and congestion conditions. The dangerous condition is that the time to collision between the target vehicle and the third vehicle is less than the collision threshold. The dangerous condition can also be that the time to collision between the target vehicle, the third vehicle and the fourth vehicle is less than the collision threshold. For example, the collision threshold is 7s. The congestion condition is that the distances between the first vehicle, the second vehicle and the third vehicle are less than the too-close distance threshold, that is, the congestion condition can be that the number of other vehicles in front of and behind the target vehicle is greater than 2 and the average distance between vehicles is less than the too-close distance threshold. For example, the too-close distance threshold can be 20m.

[0120] After judging to activate the waiting mode, the target acceleration of the target vehicle when the waiting mode is activated can be calculated. The ideal vehicle speed curve can be calculated according to the cross-line longitudinal distance. The target acceleration of the waiting mode is calculated according to the current vehicle speed of the host vehicle and the ideal vehicle speed curve. Among them, the cross-line longitudinal distance for the target vehicle to merge into the main road can be calculated according to the guiding line information and the lane line parameter information.

[0121] The fourth merging mode is the failure mode. At this time, the first distance is calculated according to the distance between the current position of the host vehicle and the cut-off point of the current lane. The first distance is the distance between the current position of the host vehicle and the cut-off point of the current lane.

[0122] The activation condition of the failure mode is that the first distance is greater than 0 and less than the fifth distance threshold, and both the lateral function and the longitudinal function of the automatic driving system are in the activated state. If the above conditions are met, it is judged to activate the failure mode. For example, the fifth distance threshold is 150m.

[0123] After determining the activation failure mode, the target acceleration of the target vehicle in the activation failure mode can be calculated. The ideal vehicle speed curve can be calculated based on the current lane cut-off point distance. The first acceleration of the failure mode can be calculated based on the current vehicle speed of the host vehicle and the ideal vehicle speed curve. The ideal acceleration limit curve can be calculated based on the current lane cut-off point distance, and the second acceleration of the failure mode can be calculated based on the ideal acceleration limit curve. If the first distance is less than the too-close distance threshold, the third acceleration of the failure mode is obtained. The minimum value among the first acceleration, the second acceleration, and the third acceleration is determined as the target acceleration of the failure mode. That is to say, when using the failure mode for speed control of merging from a ramp into the main road, it is necessary to consider that the target vehicle may not be able to merge into the main road. At this time, the current vehicle speed, the ideal vehicle speed curve, the speed limit for waiting to merge into the main road, and the distance to the main road can be considered, and then the target acceleration of the target vehicle is obtained. This can improve the safety and comfort of the automatic driving for merging from a ramp into the main road. For example, the too-close distance threshold can be 20 m.

[0124] In the embodiments of the present application, the adaptive mode and the failure mode not only have activation conditions but also inhibition conditions. When the inhibition conditions are triggered, the adaptive mode or the failure mode will automatically exit. That is to say, the triggering priority of the inhibition conditions of the adaptive mode and the failure mode is higher than that of the activation conditions. This helps the exit of the adaptive mode and the failure mode and improves the robustness.

[0125] The inhibition conditions for the adaptive mode include a status inhibition condition, a vehicle inhibition condition, and a guide line inhibition condition. As long as any one of the above three inhibition conditions is satisfied, the inhibition of the adaptive mode is triggered.

[0126] The status inhibition condition is that the current lane cut-off point distance is greater than the fourth distance threshold or the automatic driving system sends an instruction to exit the ramp and merge into the main road. For example, the fourth distance threshold is 500 m.

[0127] If the target vehicle approaches the lane edge, the vehicle inhibition condition is that the distances between the target vehicle and the first vehicle, the second vehicle, and the third vehicle are less than the too-close threshold, the collision times between the target vehicle and the first vehicle, the second vehicle, and the third vehicle are less than the collision threshold, or whether the second control acceleration and the third control acceleration have opposite trends. That is to say, as long as any one of the above three conditions is met, the vehicle inhibition condition is triggered. The distances between the target vehicle and the first vehicle, the second vehicle, and the third vehicle being less than the too-close threshold means whether the target vehicle is too close to other vehicles in a certain lane after merging into the main road, and the other vehicles can also include the fourth vehicle. The collision times between the target vehicle and the first vehicle, the second vehicle, and the third vehicle being less than the collision threshold means whether the target vehicle has a small collision time with other vehicles in a certain lane after merging into the main road, with a relatively high collision risk, and the other vehicles can also include the fourth vehicle. Whether the second control acceleration and the third control acceleration have opposite trends means whether the second control acceleration and the third control acceleration have contradictory attributes. Among them, the target vehicle approaching the lane edge can be judged based on the width of the target vehicle and the longitudinal distance across the line.

[0128] The guiding line inhibition condition is that the waiting mode has been activated and the monitored acceleration in the waiting mode is less than the monitoring threshold for a fixed time. For example, the monitoring threshold can be -2.6 m / s 2 , and the fixed time can be 0.2 s. The average deceleration required to brake to the cross-line position when the current vehicle speed of the host vehicle is 0 can be calculated based on the current vehicle speed of the host vehicle and the longitudinal distance across the line, and this deceleration is used as the monitored acceleration.

[0129] The inhibition conditions for the failure mode include the takeover inhibition condition, the status inhibition condition, and the cut-off point inhibition condition. As long as any one of the above three inhibition conditions is met, the inhibition of the failure mode is triggered.

[0130] The takeover inhibition condition is to receive the user's operation on the vehicle. The user's operation on the vehicle can be, for example, the user stepping on the accelerator pedal, or the user crossing the line to an adjacent lane where the lane cut-off point distance is farther than the current lane cut-off point distance through the steering wheel.

[0131] The status inhibition condition is that the longitudinal function of the autonomous driving system is in an inactive state or the lateral function is in a lane-changing state.

[0132] The cut-off point inhibition condition is that the current lane cut-off point distance is greater than the sixth distance threshold or the increase in the current lane cut-off point distance within the same time interval is greater than the increase threshold. For example, the sixth distance threshold is 200 m and the increase threshold is 50 m, that is, the current lane cut-off point distance has increased by more than 50 m compared to the previous moment.

[0133] In an embodiment of the present application, if at least two merging modes are activated simultaneously, and different merging modes have different target accelerations, the actual acceleration of the target vehicle is determined in the following order of decreasing priority: the target acceleration of the waiting mode, the target acceleration of the adaptive mode, the target acceleration of the failure mode, and the target acceleration of the pre-deceleration mode. That is to say, when more than one merging mode is activated, to avoid confusion in the vehicle speed control of the target vehicle, priorities are set for the target accelerations of different merging modes. The target acceleration of the waiting mode is preferentially selected, followed by the target acceleration of the adaptive mode and the target acceleration of the failure mode, and finally the target acceleration of the pre-deceleration mode. This can ensure that each merging mode works in coordination without interfering with each other, and improve the integrity of the function of autonomous driving when merging from a ramp onto the main road.

[0134] S103, control the target speed of the target vehicle when merging from the ramp onto the main road according to the target acceleration, and control the driving of the target vehicle according to the target speed.

[0135] In an embodiment of the present application, after selecting the target acceleration of a certain merging mode, the target speed of the target vehicle when merging from the ramp onto the main road can be controlled according to the target acceleration, and the driving of the target vehicle can be controlled according to the target speed.

[0136] In an embodiment of the present application, during the process of merging from the ramp onto the main road, information interaction can be carried out with the user, so as to provide the user with current driving information and possible assistance required from the user, thereby improving the user's sense of safety regarding autonomous driving.

[0137] Specifically, if the waiting mode has been activated, and the current vehicle speed of the host vehicle gradually decreases and the current vehicle speed of the host vehicle is less than the first vehicle speed threshold, a takeover reminder message is sent to the user so that the user can drive the target vehicle autonomously. For example, the first vehicle speed threshold can be 5 kilometers per hour (kph).

[0138] Specifically, if the failure mode has been activated, and the distance to the end point of the current lane is less than the too-close distance threshold and the current vehicle speed of the host vehicle is less than the second vehicle speed threshold, a takeover reminder message is sent to the user so that the user can drive the target vehicle autonomously. For example, the second vehicle speed threshold can be 15 kph, and the too-close distance threshold can be 20 m.

[0139] Reference Figure 2As shown in the figure, it is a schematic diagram of the vehicle speed control logic for ramp merging into the main road provided by an embodiment of the present application. Obtain the guiding line information, road topology information, road environment information, and the motion state information of the host vehicle when the ramp merges into the main road. After obtaining the above information, verify the road topology information, and perform environmental information integration after passing the verification. Judge the validity of the integrated environmental information. If the environmental information is judged to be valid, enter the merging mode judgment and acceleration calculation process. The ramp merging into the main road is divided into four merging modes: pre-deceleration mode, adaptive mode, waiting mode, and failure mode. If the environmental information is judged to be valid, respectively perform mode judgment and acceleration calculation for the four merging modes. Further, perform unified arbitration management on the above four merging modes, and output a reasonable target acceleration for vehicle speed control. Finally, during the process of the ramp merging into the main road, perform functional status user interaction information processing, and generate and send interaction information in a timely manner.

[0140] It can be seen that the vehicle speed control method for ramp merging into the main road provided by the embodiment of the present application takes into account the complexity of the ramp merging into the main road scenario, designs four merging modes for vehicle speed control, improves the robustness in this scenario. At the same time, the activation conditions, inhibition conditions, and acceleration calculation strategies under different merging modes can optimize the driving safety and comfort of the vehicle. And by reasonably designing the priorities of different merging modes, it is ensured that each merging mode works in coordination without interfering with each other, improving the integrity of the function. By designing the information interaction strategy, the subjective sense of security of the user when the ramp merges into the main road is enhanced, and the user acceptance in practical applications is improved.

[0141] The present application provides a vehicle speed control method for ramp merging into the main road. The method includes: obtaining guiding line information, road topology information, road environment information, lane traffic flow motion state information, and the motion state information of the host vehicle according to the ramp merging into the main road instruction. These information all contribute to the subsequent automatic vehicle speed control for ramp merging into the main road. Judge the merging mode according to the guiding line information, road topology information, lane traffic flow motion state information, road environment information, and the motion state information of the host vehicle, and calculate the target acceleration for activating the merging mode. The merging modes include pre-deceleration mode, adaptive mode, waiting mode, and failure mode. That is, by designing multiple merging modes for various situations of ramp merging into the main road, the scenarios of autonomous driving are greatly enriched, and the safety and comfort of autonomous driving can also be improved. Control the target speed of the target vehicle when merging from the ramp into the main road according to the target acceleration, and control the driving of the target vehicle according to the target speed, which can improve the experience of autonomous driving and improve the driving efficiency of the vehicle in the ramp through the control of multiple merging modes.

[0142] Based on the vehicle speed control method for ramp merging into the main road provided in the above embodiments, the embodiments of the present application also provide a vehicle speed control device for ramp merging into the main road. The working principle thereof will be described in detail below with reference to the accompanying drawings.

[0143] Refer to Figure 3 , which is a structural block diagram of a vehicle speed control device for ramp merging into the main road provided by the embodiments of the present application.

[0144] The vehicle speed control device 200 for ramp merging into the main road provided in this embodiment includes:

[0145] An acquisition unit 210, configured to obtain guiding line information, road topology structure information, road environment information, lane traffic flow movement state information, and own vehicle movement state information according to a ramp merging into the main road instruction;

[0146] A calculation unit 220, configured to judge the merging mode according to the guiding line information, the road topology structure information, the lane traffic flow movement state information, the road environment information, and the own vehicle movement state information, and calculate a target acceleration for activating the merging mode, where the merging mode includes a pre - deceleration mode, an adaptive mode, a waiting mode, and a failure mode;

[0147] A control unit 230, configured to control the target speed of the target vehicle when merging from the ramp into the main road according to the target acceleration, and control the driving of the target vehicle according to the target speed.

[0148] Optionally, when the merging mode is the pre - deceleration mode, the road topology structure information includes the road topology structure form, the starting distance of the ramp merging into the main road opening, the ending distance of the ramp merging into the main road opening, and the current lane cut - off point distance, and the own vehicle movement state information includes the current vehicle speed of the own vehicle;

[0149] The calculation unit 220 is configured to:

[0150] Calculate the opening length of the ramp merging into the main road according to the starting distance of the ramp merging into the main road opening, the ending distance of the ramp merging into the main road opening, and the current lane cut - off point distance;

[0151] If the road topology structure form is a ramp merging form, and the opening length is less than a first distance threshold for a preset time, and the current lane cut - off point distance is less than a second distance threshold for the preset time, then judge to activate the pre - deceleration mode;

[0152] Calculate a preliminary ideal vehicle speed curve according to the starting distance of the ramp merging into the main road opening, correct the preliminary ideal vehicle speed curve by using the opening length to obtain a corrected ideal vehicle speed curve, and calculate the target acceleration of the pre - deceleration mode according to the current vehicle speed of the own vehicle and the corrected ideal vehicle speed curve.

[0153] Optionally, the calculation unit 220 is configured to:

[0154] The opening length of the ramp merging into the main road is the difference between the minimum value between the current lane cut-off point distance and the end distance of the merging into the main road opening and the starting distance of the merging into the main road opening.

[0155] Optionally, the merging mode is the adaptive mode, the road topology structure information includes the road topology structure form and the current lane cut-off point distance, the self-vehicle motion state information includes the current position of the self-vehicle and the current speed of the self-vehicle, the lane traffic flow motion state information includes the positions and driving speeds of multiple vehicles, the multiple vehicles include a first vehicle, a second vehicle, and a third vehicle, the first vehicle is the vehicle in front of the second vehicle during driving, the second vehicle is the vehicle in front of the target vehicle after merging into the main road lane, and the third vehicle is the vehicle behind the target vehicle after merging into the main road lane;

[0156] The calculation unit 220 is configured to:

[0157] Calculate a first distance based on the current position of the self-vehicle and the current lane cut-off point distance, where the first distance is the distance between the current position of the self-vehicle and the current lane cut-off point distance;

[0158] If the road topology structure form is the ramp merging form and the first distance is less than the third distance threshold, determine to activate the adaptive mode;

[0159] Calculate a first control acceleration of the target vehicle based on the position and driving speed of the first vehicle; calculate a second control acceleration of the target vehicle based on the position and driving speed of the second vehicle; calculate a third control acceleration of the target vehicle based on the position and driving speed of the third vehicle;

[0160] Determine the minimum value among the first control acceleration, the second control acceleration, and the third control acceleration as the target acceleration of the adaptive mode.

[0161] Optionally, the calculation unit 220 is configured to:

[0162] Obtain the ideal following distance and the collision time between the target vehicle and the third vehicle;

[0163] Calculate a first time distance value between the target vehicle and the first vehicle and a first actual following distance between the target vehicle and the first vehicle based on the current position of the host vehicle and the position of the first vehicle, calculate a first speed difference based on the current speed of the host vehicle and the traveling speed of the first vehicle, calculate a first distance difference based on the first actual following distance and the ideal following distance, and calculate a first control acceleration based on the sum of the product of the first distance difference and a first error coefficient and the product of the first speed difference and a second error coefficient, where the second error coefficient is determined based on the first time distance value;

[0164] Calculate a second time distance value between the target vehicle and the second vehicle and a second actual following distance between the target vehicle and the second vehicle based on the current position of the host vehicle and the position of the second vehicle, calculate a second speed difference based on the current speed of the host vehicle and the traveling speed of the second vehicle, calculate a second distance difference based on the second actual following distance and the ideal following distance, and calculate a second control acceleration based on the sum of the product of the second distance difference and a third error coefficient and the product of the second speed difference and a fourth error coefficient, where the fourth error coefficient is determined based on the second time distance value;

[0165] Calculate a third actual following distance between the target vehicle and the third vehicle based on the current position of the host vehicle and the position of the first vehicle, determine whether the third vehicle is in a dangerous state based on whether the time to collision is less than a collision threshold or whether the third actual following distance is less than a following threshold, and respectively correct the traveling speed and the third actual following distance of the third vehicle in the determined state to obtain a corrected speed and a corrected following distance, calculate a third speed difference based on the current speed of the host vehicle and the corrected speed, calculate a third distance difference based on the corrected following distance and the ideal following distance, and calculate a third control acceleration based on the sum of the product of the third distance difference and a fifth error coefficient and the product of the third speed difference and a sixth error coefficient.

[0166] Optionally, the device further includes a first inhibition condition triggering unit;

[0167] The first inhibition condition triggering unit is configured to:

[0168] Judge whether the inhibition condition of the adaptive mode is triggered. If the inhibition condition has been triggered, exit the adaptive mode;

[0169] The suppression conditions include one or more of a status suppression condition, a vehicle suppression condition, and a guiding line suppression condition; the status suppression condition is that the current lane cut-off point distance is greater than a fourth distance threshold or the autonomous driving system sends an instruction to exit the ramp and merge into the main road; if the target vehicle approaches the lane edge, the vehicle suppression condition is that the distances between the target vehicle and the first vehicle, the second vehicle, and the third vehicle are less than a too-close threshold, the collision times between the target vehicle and the first vehicle, the second vehicle, and the third vehicle are less than a collision threshold, or whether the second control acceleration and the third control acceleration have opposite trends; the guiding line suppression condition is that the waiting mode has been activated and the monitoring acceleration of the waiting mode is less than a monitoring threshold and remains fixed for a certain time.

[0170] Optionally, the self-vehicle motion state information includes the current speed of the self-vehicle, the lane traffic flow motion state information includes the positions and driving speeds of multiple vehicles, the multiple vehicles include a first vehicle, a second vehicle, and a third vehicle, the first vehicle is the vehicle in front of the second vehicle in terms of driving, the second vehicle is the vehicle in front of the target vehicle after it merges into the main road lane, the third vehicle is the vehicle behind the target vehicle after it merges into the main road lane, and the road environment information includes lane line parameter information;

[0171] The calculation unit 220 is configured to:

[0172] Determine whether to activate the adaptive mode according to the road topology structure information, the lane traffic flow motion state information, and the self-vehicle motion state information. If the adaptive mode is activated, determine whether the activation condition of the waiting mode is triggered. If the activation condition has been triggered, exit the adaptive mode and activate the waiting mode;

[0173] The activation conditions include a danger condition and a congestion condition. The danger condition is that the collision time between the target vehicle and the third vehicle is less than a collision threshold, and the congestion condition is that the distances between the first vehicle, the second vehicle, and the third vehicle pairwise are less than a too-close distance threshold;

[0174] Calculate an ideal vehicle speed curve based on the cross-line longitudinal distance, calculate the target acceleration of the waiting mode according to the current speed of the self-vehicle and the ideal vehicle speed curve, and calculate the cross-line longitudinal distance for the target vehicle to merge into the main road according to the guiding line information and the lane line parameter information.

[0175] Optionally, the merging mode is the failure mode, the road topology structure information includes the current lane cut-off point distance, and the self-vehicle motion state information includes the current speed of the self-vehicle and the current position of the self-vehicle;

[0176] The calculation unit 220 is configured to:

[0177] Calculate a first distance based on the current position of the host vehicle and the distance to the current lane cut-off point, where the first distance is the distance between the current position of the host vehicle and the distance to the current lane cut-off point;

[0178] If the first distance is greater than 0 and less than a fifth distance threshold, and both the lateral function and the longitudinal function of the autonomous driving system are in an active state, then determine an activation failure mode;

[0179] Calculate an ideal vehicle speed curve based on the distance to the current lane cut-off point, calculate a first acceleration of the failure mode based on the current vehicle speed of the host vehicle and the ideal vehicle speed curve; calculate an ideal acceleration limit curve based on the distance to the current lane cut-off point, calculate a second acceleration of the failure mode based on the ideal acceleration limit curve; if the first distance is less than a too-close distance threshold, obtain a third acceleration of the failure mode; determine the minimum value among the first acceleration, the second acceleration, and the third acceleration as the target acceleration of the failure mode.

[0180] Optionally, the device further includes a second inhibition condition trigger unit;

[0181] The second inhibition condition trigger unit is configured to:

[0182] Judge whether the inhibition condition of the failure mode is triggered, and if the inhibition condition has been triggered, exit the failure mode;

[0183] The inhibition condition includes one or more of a takeover inhibition condition, a state inhibition condition, and a cut-off point inhibition condition; the takeover inhibition condition is receiving an operation of the user on the vehicle, the state inhibition condition is that the longitudinal function of the autonomous driving system is in a non-active state or the lateral function is in a lane-changing state, and the cut-off point inhibition condition is that the distance to the current lane cut-off point is greater than a sixth distance threshold or the increase amount of the distance to the current lane cut-off point within the same time interval is greater than an increase threshold.

[0184] Optionally, the device further includes a determination unit;

[0185] The determination unit is configured to:

[0186] If at least two merging modes are activated simultaneously, determine the actual acceleration of the target vehicle in the following order of decreasing priority, where the order of decreasing priority is the target acceleration of the waiting mode, the target acceleration of the adaptive mode, the target acceleration of the failure mode, and the target acceleration of the pre-deceleration mode.

[0187] Optionally, the self-vehicle motion state information includes the current speed of the self-vehicle, and the device further includes a first takeover unit;

[0188] The first takeover unit is configured to:

[0189] If the waiting mode has been activated, and the current speed of the self-vehicle gradually decreases and is less than the first speed threshold, send a takeover reminder message to the user.

[0190] Optionally, the road topology structure information includes the distance to the end point of the current lane, the self-vehicle motion state information includes the current speed of the self-vehicle, and the device further includes a second takeover unit;

[0191] The second takeover unit is configured to:

[0192] If the failure mode has been activated, and the distance to the end point of the current lane is less than the too-close distance threshold and the current speed of the self-vehicle is less than the second speed threshold, send a takeover reminder message to the user.

[0193] An embodiment of the present application further provides a computer-readable storage medium for storing program code, and the program code is used to execute any one of the methods in the foregoing various embodiments.

[0194] In the context of the present application, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, 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 a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0195] It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, a computer-readable storage medium can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. And in this application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0196] When introducing the elements of the various embodiments of this application, the articles "a", "an", "this", and "the" are all intended to mean that there is one or more elements. The words "comprising", "including", and "having" are all inclusive and mean that there can be other elements in addition to the listed elements.

[0197] It should be noted that those of ordinary skill in the art can understand that to implement all or part of the processes in the above method embodiments, it can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), etc.

[0198] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0199] When introducing the elements of various embodiments of this application, the articles "a", "an", "this", and "the" are all intended to mean one or more elements. The words "comprising", "including", and "having" are all inclusive and mean that there may be other elements in addition to the listed elements.

[0200] It should be noted that those of ordinary skill in the art can understand that to implement all or part of the processes in the above method embodiments, it can be completed by instructing relevant hardware through a computer program. The said program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0201] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the partial description of the method embodiments. The device embodiments described above are merely illustrative. The units and modules described as separate components may or may not be physically separated. In addition, some or all of the units and modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0202] The above are only specific embodiments of the present application. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A vehicle speed control method for a ramp merging into a main road, characterized in that, the method includes: obtaining guiding line information, road topology structure information, road environment information, lane traffic flow movement state information and own vehicle movement state information according to a ramp merging into main road instruction; judging an merging mode according to the guiding line information, the road topology structure information, the lane traffic flow movement state information, the road environment information and the own vehicle movement state information, and calculating a target acceleration for activating the merging mode, where the merging modes include a pre - deceleration mode, an adaptive mode, a waiting mode and a failure mode; controlling a target speed of a target vehicle when merging from a ramp into a main road according to the target acceleration, and controlling the target vehicle to travel according to the target speed.

2. The method according to claim 1, characterized in that, the merging mode is the pre - deceleration mode, the road topology structure information includes a road topology structure form, a starting distance of the merging into main road opening, an ending distance of the merging into main road opening and a current lane cut - off point distance, and the own vehicle movement state information includes the current vehicle speed of the own vehicle; the judging the merging mode according to the guiding line information, the road topology structure information, the lane traffic flow movement state information, the road environment information and the own vehicle movement state information and calculating the target acceleration for activating the merging mode includes: calculating an opening length of the ramp merging into the main road according to the starting distance of the merging into main road opening, the ending distance of the merging into main road opening and the current lane cut - off point distance; if the road topology structure form is a ramp merging form, and the opening length is less than a first distance threshold for a preset time and the current lane cut - off point distance is less than a second distance threshold for the preset time, then judge to activate the pre - deceleration mode; calculating a preliminary ideal vehicle speed curve according to the starting distance of the merging into main road opening, correcting the preliminary ideal vehicle speed curve by using the opening length to obtain a corrected ideal vehicle speed curve, and calculating the target acceleration of the pre - deceleration mode according to the current vehicle speed of the own vehicle and the corrected ideal vehicle speed curve.

3. The method according to claim 2, characterized in that, the calculating the opening length of the ramp merging into the main road according to the starting distance of the merging into main road opening, the ending distance of the merging into main road opening and the current lane cut - off point distance includes: the opening length of the ramp merging into the main road is the difference between the minimum value between the current lane cut - off point distance and the ending distance of the merging into main road opening and the starting distance of the merging into main road opening.

4. The method according to claim 1, characterized in that, The merging mode is the adaptive mode. The road topology structure information includes the form of the road topology structure and the distance from the current lane cut-off point. The self-vehicle motion state information includes the current position of the self-vehicle and the current speed of the self-vehicle. The lane traffic flow motion state information includes the positions and driving speeds of multiple vehicles. The multiple vehicles include a first vehicle, a second vehicle, and a third vehicle. The first vehicle is the vehicle in front of the second vehicle during driving. The second vehicle is the vehicle in front of the target vehicle after the target vehicle merges into the main road lane. The third vehicle is the vehicle behind the target vehicle after the target vehicle merges into the main road lane; The judgment of the merging mode and the calculation of the target acceleration for activating the merging mode according to the guiding line information, the road topology structure information, the lane traffic flow motion state information, the road environment information, and the self-vehicle motion state information include: Calculate a first distance based on the current position of the self-vehicle and the distance from the current lane cut-off point. The first distance is the distance between the current position of the self-vehicle and the distance from the current lane cut-off point; If the form of the road topology structure is ramp merging, and the first distance is less than a third distance threshold, then judge to activate the adaptive mode; Calculate a first control acceleration of the target vehicle based on the position and driving speed of the first vehicle; calculate a second control acceleration of the target vehicle based on the position and driving speed of the second vehicle; calculate a third control acceleration of the target vehicle based on the position and driving speed of the third vehicle; Determine the minimum value among the first control acceleration, the second control acceleration, and the third control acceleration as the target acceleration of the adaptive mode.

5. The method according to claim 4, wherein, calculate a first control acceleration of the target vehicle based on the position and driving speed of the first vehicle; calculate a second control acceleration of the target vehicle based on the position and driving speed of the second vehicle; calculate a third control acceleration of the target vehicle based on the position and driving speed of the third vehicle includes: Obtain the ideal following distance and the collision time between the target vehicle and the third vehicle; Calculate a first time distance value and a first actual following distance between the target vehicle and the first vehicle based on the current position of the self-vehicle and the position of the first vehicle. Calculate a first speed difference based on the current speed of the self-vehicle and the driving speed of the first vehicle. Calculate a first distance difference based on the first actual following distance and the ideal following distance. Calculate a first control acceleration based on the sum of the product of the first distance difference and a first error coefficient and the product of the first speed difference and a second error coefficient. The second error coefficient is determined according to the first time distance value; Calculate a second time distance value between the target vehicle and the second vehicle and a second actual following distance between the target vehicle and the second vehicle according to the current position of the host vehicle and the position of the second vehicle, calculate a second speed difference according to the current speed of the host vehicle and the driving speed of the second vehicle, calculate a second distance difference according to the second actual following distance and the ideal following distance, and calculate a second control acceleration according to the sum of the product of the second distance difference and a third error coefficient and the product of the second speed difference and a fourth error coefficient, where the fourth error coefficient is determined according to the second time distance value; Calculate a third actual following distance between the target vehicle and the third vehicle according to the current position of the host vehicle and the position of the first vehicle, determine whether the third vehicle is in a dangerous state according to whether the time to collision is less than a collision threshold or whether the third actual following distance is less than a following threshold, respectively correct the driving speed and the third actual following distance of the third vehicle in the corresponding state according to whether the third vehicle is in a dangerous state to obtain a corrected speed and a corrected following distance, calculate a third speed difference according to the current speed of the host vehicle and the corrected speed, calculate a third distance difference according to the corrected following distance and the ideal following distance, and calculate a third control acceleration according to the sum of the product of the third distance difference and a fifth error coefficient and the product of the third speed difference and a sixth error coefficient.

6. The method according to claim 5, wherein, the method further includes: judging whether a suppression condition of the adaptive mode is triggered, and if the suppression condition is triggered, exiting the adaptive mode; the suppression condition includes one or more of a state suppression condition, a vehicle suppression condition, and a guiding line suppression condition; the state suppression condition is that the distance to the current lane cut-off point is greater than a fourth distance threshold or the autonomous driving system sends an instruction to exit the ramp and merge into the main road; if the target vehicle approaches the lane edge, the vehicle suppression condition is that the distances between the target vehicle and the first vehicle, the second vehicle, and the third vehicle are less than a too-close threshold, the times to collision between the target vehicle and the first vehicle, the second vehicle, and the third vehicle are less than a collision threshold, or whether the second control acceleration and the third control acceleration have opposite trends; the guiding line suppression condition is that the waiting mode is activated and the monitoring acceleration of the waiting mode is less than a monitoring threshold and remains fixed for a certain time.

7. The method according to claim 1, wherein, the motion state information of the host vehicle includes the current speed of the host vehicle, the motion state information of the lane traffic flow includes the positions and driving speeds of multiple vehicles, the multiple vehicles include a first vehicle, a second vehicle, and a third vehicle, the first vehicle is the vehicle in front of the second vehicle in terms of driving, the second vehicle is the vehicle in front of the target vehicle after it merges into the main road lane, the third vehicle is the vehicle behind the target vehicle after it merges into the main road lane, and the road environment information includes lane line parameter information; Judging the merging mode based on the guiding line information, the road topology information, the lane traffic flow movement state information, the road environment information, and the ego-vehicle movement state information, and calculating the target acceleration for activating the merging mode includes: Judging whether to activate the adaptive mode according to the road topology information, the lane traffic flow movement state information, and the ego-vehicle movement state information. If the adaptive mode is activated, judging whether the activation condition of the waiting mode is triggered. If the activation condition has been triggered, exiting the adaptive mode and activating the waiting mode; The activation conditions include a danger condition and a congestion condition. The danger condition is that the time to collision between the target vehicle and the third vehicle is less than the collision threshold, and the congestion condition is that the distances between the first vehicle, the second vehicle, and the third vehicle pairwise are less than the too-close distance threshold; Calculating an ideal vehicle speed curve based on the cross-line longitudinal distance, calculating the target acceleration of the waiting mode according to the current vehicle speed of the ego-vehicle and the ideal vehicle speed curve, and calculating the cross-line longitudinal distance for the target vehicle to merge into the main road according to the guiding line information and the lane line parameter information.

8. The method according to claim 1, wherein, the merging mode is the failure mode, the road topology information includes the current lane cut-off point distance, and the ego-vehicle movement state information includes the current vehicle speed of the ego-vehicle and the current position of the ego-vehicle; Judging the merging mode based on the guiding line information, the road topology information, the lane traffic flow movement state information, the road environment information, and the ego-vehicle movement state information, and calculating the target acceleration for activating the merging mode includes: Calculating a first distance according to the current position of the ego-vehicle and the current lane cut-off point distance, where the first distance is the distance between the current position of the ego-vehicle and the current lane cut-off point distance; If the first distance is greater than 0 and less than the fifth distance threshold, and both the lateral function and the longitudinal function of the autonomous driving system are in the activated state, then judge to activate the failure mode; Calculating an ideal vehicle speed curve according to the current lane cut-off point distance, calculating the first acceleration of the failure mode according to the current vehicle speed of the ego-vehicle and the ideal vehicle speed curve; calculating an ideal acceleration limit curve according to the current lane cut-off point distance, and calculating the second acceleration of the failure mode according to the ideal acceleration limit curve; if the first distance is less than the too-close distance threshold, then obtaining the third acceleration of the failure mode; determining the minimum value among the first acceleration, the second acceleration, and the third acceleration as the target acceleration of the failure mode.

9. The method according to claim 8, wherein, the method further includes: Judging whether the suppression condition of the failure mode is triggered. If the suppression condition has been triggered, then exiting the failure mode; The suppression conditions include one or more of takeover suppression conditions, state suppression conditions, and cut-off point suppression conditions; the takeover suppression condition is to receive an operation of the user on the vehicle, the state suppression condition is that the longitudinal function of the automatic driving system is in an inactive state or the lateral function is in a lane-changing state, and the cut-off point suppression condition is that the current lane cut-off point distance is greater than a sixth distance threshold or the increase amount of the current lane cut-off point distance within the same time interval is greater than an increase threshold.

10. The method according to any one of claims 1-9, wherein, the method further includes: If at least two merging modes are simultaneously activated, the actual acceleration of the target vehicle is determined in the following order of decreasing priority, and the order of decreasing priority is the target acceleration of the waiting mode, the target acceleration of the adaptive mode, the target acceleration of the failure mode, and the target acceleration of the pre-deceleration mode.

11. The method according to any one of claims 1-9, wherein, the self-vehicle motion state information includes the current speed of the self-vehicle, and the method further includes: If the waiting mode has been activated, and the current speed of the self-vehicle gradually decreases and the current speed of the self-vehicle is less than a first speed threshold, a takeover reminder message is sent to the user.

12. The method according to any one of claims 1-9, wherein, the road topology structure information includes the current lane cut-off point distance, the self-vehicle motion state information includes the current speed of the self-vehicle, and the method further includes: If the failure mode has been activated, and the current lane cut-off point distance is less than a too-close distance threshold and the current speed of the self-vehicle is less than a second speed threshold, a takeover reminder message is sent to the user.

13. A vehicle speed control device for merging from a ramp into a main road, wherein, the device includes: An acquisition unit for acquiring guiding line information, road topology structure information, road environment information, lane traffic flow motion state information, and self-vehicle motion state information according to a ramp merging into main road instruction; A calculation unit for judging the merging mode according to the guiding line information, the road topology structure information, the lane traffic flow motion state information, the road environment information, and the self-vehicle motion state information, and calculating the target acceleration for activating the merging mode, and the merging mode includes a pre-deceleration mode, an adaptive mode, a waiting mode, and a failure mode; A control unit for controlling the target speed of the target vehicle when merging from the ramp into the main road according to the target acceleration, and controlling the target vehicle to travel according to the target speed.

14. A computer-readable storage medium, wherein, including instructions, when running on a computer, causing the computer to execute the method according to any one of claims 1-12.

Images