CN117022320A

CN117022320A - Control method and device for automatic driving vehicle, electronic equipment and vehicle

Info

Publication number: CN117022320A
Application number: CN202310961965.6A
Authority: CN
Inventors: 刘金鑫; 李文博; 彭亮; 陈泰然; 包帅
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2023-08-01
Filing date: 2023-08-01
Publication date: 2023-11-10

Abstract

The disclosure provides a control method and device for an automatic driving vehicle, electronic equipment and the vehicle, and relates to the technical field of artificial intelligence, in particular to the technical field of automatic driving. The specific implementation scheme is as follows: acquiring initial driving profits of candidate driving strategies of the automatic driving vehicle and the interactive object; determining a final driving benefit of the initial driving benefit of the candidate driving strategy based on the long-term safety requirement and the short-term safety requirement; long-term safety requirements require safe passage of autonomous vehicles and interactive objects through a target site; short-term safety requirements require that an autonomous vehicle be able to safely travel in a first time domain; in the case where the candidate driving maneuver is selected as the target driving maneuver based on the final driving benefit, the autonomous vehicle is controlled to execute the target driving maneuver. In the embodiment of the disclosure, long-term and short-term driving benefits are comprehensively considered, and a target driving strategy which is beneficial to ensuring the driving safety of the vehicle can be obtained.

Description

Control method and device for automatic driving vehicle, electronic equipment and vehicle

Technical Field

The present disclosure relates to the field of artificial intelligence, and in particular, to the field of autopilot technology.

Background

As autopilot technology matures, autopilot vehicles become increasingly popular. An autonomous vehicle may encounter various road conditions and various emergencies during road travel. Therefore, it is important to decide how to make a driving strategy to ensure the running safety of the automatically driven vehicle.

Disclosure of Invention

The disclosure provides a control method and device for an automatic driving vehicle, electronic equipment and the vehicle.

According to an aspect of the present disclosure, there is provided a control method of an autonomous vehicle, including:

acquiring initial driving profits of candidate driving strategies of the automatic driving vehicle and the interactive object;

determining a final driving benefit of the initial driving benefit of the candidate driving strategy based on the long-term safety requirement and the short-term safety requirement; long-term safety requirements require safe passage of autonomous vehicles and interactive objects through a target site; short-term safety requirements require that an autonomous vehicle be able to safely travel in a first time domain;

in the case where the candidate driving maneuver is selected as the target driving maneuver based on the final driving benefit, the autonomous vehicle is controlled to execute the target driving maneuver.

According to another aspect of the present disclosure, there is provided a control apparatus of an autonomous vehicle, including:

The acquisition module is used for acquiring initial driving profits of candidate driving strategies of the automatic driving vehicle and the interactive object;

a determining module for determining a final driving benefit of the initial driving benefit of the candidate driving strategy based on the long-term safety requirement and the short-term safety requirement; long-term safety requirements require safe passage of autonomous vehicles and interactive objects through a target site; short-term safety requirements require that an autonomous vehicle be able to safely travel in a first time domain;

and the control module is used for controlling the automatic driving vehicle to execute the target driving strategy under the condition that the candidate driving strategy is selected as the target driving strategy based on the final driving income.

According to another aspect of the present disclosure, there is provided an electronic device including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform a method according to any one of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method according to any of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a vehicle including the electronic device provided in the embodiments of the present disclosure.

In the embodiment of the disclosure, the long-term and short-term running benefits are comprehensively considered, so that the long-term and short-term running benefits can be comprehensively considered and measured when the automatic driving vehicle makes interactive decisions. The initial driving benefit obtained by the method can be adapted and adjusted based on actual conditions, so that the final driving benefit is obtained, and the target driving strategy for ensuring the driving safety of the vehicle can be obtained based on the final driving benefit.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a flow chart of a method of controlling an autonomous vehicle according to one embodiment of the present disclosure;

FIG. 2 is a schematic illustration of a scenario of a control method of an autonomous vehicle according to an embodiment of the present disclosure;

FIG. 3a is a schematic diagram of determining a time difference in accordance with an embodiment of the present disclosure;

FIG. 3b is a schematic diagram of determining a time difference in accordance with another embodiment of the present disclosure;

FIG. 4 is a schematic illustration of determining a target site in accordance with an embodiment of the present disclosure;

FIG. 5a is a schematic block diagram of a method of controlling an autonomous vehicle according to one embodiment of the present disclosure;

FIG. 5b is a schematic frame diagram of a control method of an autonomous vehicle according to another embodiment of the present disclosure;

FIG. 6 is a schematic structural view of a control device for an autonomous vehicle according to another embodiment of the present disclosure;

fig. 7 is a block diagram of an electronic device for implementing a control method of an autonomous vehicle according to an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implying a number of technical features being indicated. Thus, a feature defining "first," "second," etc. may explicitly or implicitly include one or more such feature. In the description of the present disclosure, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

In a common interaction scenario of an autonomous vehicle, decision making and planning are required for the autonomous vehicle based on the running income of the vehicle to ensure the safety of the autonomous vehicle in the running process.

In some possible solutions, the decision making and planning methods for the autonomous vehicle based on the running returns of the vehicle are mainly divided into two categories. One type is to make decisions and plan for an autonomous vehicle based on the driving benefit of the short-term driving behavior of the autonomous vehicle. The short-term driving behavior is typically planning-level behavior information of the vehicle. It is understood as physical movement information of the autonomous vehicle. The motion information includes, for example, the speed or acceleration of the autonomous vehicle and nearby vehicles in a future horizon, facilitating subsequent trajectory planning by the autonomous vehicle. But this approach only considers the travel benefits of short-term travel behavior. Although the motion sequence information of the vehicle can be directly output, the vehicle is convenient to carry out track planning and vehicle control based on the motion sequence information. However, because long-term driving benefits of the vehicle are not considered, risk of sudden braking or collision of the vehicle during later interaction may be caused due to unreasonable results of earlier interaction decisions of the vehicle.

Another category is decision making and planning of autonomous vehicles based on the driving benefit of their long-term driving behavior. The long-term driving behavior is generally abstract level behavior information of a vehicle, such as acceleration overtaking or deceleration avoidance behavior of an automatically driven vehicle. This abstract level behavior will be used to indirectly guide the subsequent trajectory planning of the vehicle. According to the method, only the running benefit of long-term running behaviors is considered, and the abstract interaction behavior of the vehicle can be output according to the current interaction scene. Under the guidance of the behavior, the automatic driving vehicle can make reasonable decisions by integrating the consideration of global information. However, this approach may not allow planning according to a predetermined decision-making behavior when planning a vehicle trajectory later because short-term driving benefits of the vehicle are ignored.

In view of this, the embodiment of the disclosure provides a control method for an automatic driving vehicle, which comprehensively considers and measures long-term and short-term driving benefits of the vehicle, so that an output result of an automatic driving vehicle decision system can meet diversified requirements, and meanwhile, the rationality and safety of an automatic driving vehicle interactive decision are ensured. The specific flow of the method is shown in fig. 1, and comprises the following steps:

S101, obtaining initial driving benefits of candidate driving strategies of the automatic driving vehicle and the interactive object.

The application scenario of the method can be as shown in fig. 2, the automatic driving vehicle and the interactive object need to be in the same traffic scenario, and in the case that the automatic driving vehicle is the vehicle a in fig. 2, the interactive object can be the vehicle B which affects the driving safety of the vehicle a, or can be other obstacles which affect the driving safety. For example, it may be a non-motor vehicle, pedestrian, animal, etc. In the case where the interactive vehicle is also a vehicle, the interactive object may be a human-driven vehicle or an unmanned vehicle. The interactive object may be determined based on actual conditions, which is not limited by the present disclosure.

The candidate driving strategy may include preset driving behavior and speed of the autonomous vehicle and the interactive object, etc. The candidate driving strategy may be a plurality of strategies. For example, one of the candidate driving strategies may prepare for an autonomous vehicle to cut-in at a km/h speed for an interactive object traveling at b km/h speed; another candidate driving strategy is to prepare the autonomous vehicle to follow an interactive object traveling at a km/h speed; another candidate driving strategy is to prepare the vehicle for autonomous driving at a km/h speed versus c m/s ² An interactive object whose acceleration is accelerating makes a cut-in or the like.

As shown in fig. 2, the vehicle a overtakes the vehicle B, and pedestrians are in front of the vehicle B, so that the overtaking route needs to be designed by comprehensively considering the surrounding conditions of the vehicle a to avoid accidents.

S102, determining final driving benefit of initial driving benefit of the candidate driving strategy based on the long-term safety requirement and the short-term safety requirement.

Long-term safety requirements require safe passage of autonomous vehicles and interactive objects through a target site; short-term safety requirements require that the autonomous vehicle be able to travel safely during the first time period.

The first time domain in the embodiments of the present disclosure is used to represent a future time domain in the running revenues of short-term running behavior as described above in a short time. In the specific implementation, the specific value of the first time domain can be flexibly determined according to the driving decision.

S103, in the case where the candidate driving maneuver is selected as the target driving maneuver based on the final driving benefit, the autonomous vehicle is controlled to execute the target driving maneuver.

In some embodiments, there are a plurality of alternative driving vehicles, each of which may be referred to as a candidate driving maneuver, from which the target driving maneuver that yields the greatest final driving benefit may be selected. Candidate driving strategies corresponding to the final driving benefit meeting the preset threshold value can be selected from the multiple final driving benefits to serve as target driving strategies. The embodiments of the present disclosure are not limited in this regard.

In the embodiment of the disclosure, the long-term and short-term running benefits are comprehensively considered, so that the long-term and short-term running benefits can be comprehensively considered and measured when the automatic driving vehicle makes an interactive decision, and not only can the abstract layer interactive behavior of the vehicle be considered, but also the vehicle planning level interactive instruction can be considered, thereby meeting the diversified data requirements of vehicle track planning and control. The initial driving benefit provided by the mode can be adapted and adjusted based on actual conditions, so that the final driving benefit is obtained, and a target driving strategy which is beneficial to ensuring the safety of the vehicle can be obtained based on the final driving benefit.

The final driving benefit of the candidate driving strategy may be determined based on the autonomous vehicle, or may be determined based on the autonomous vehicle and the interaction object, and the two modes are respectively described in detail below:

1) A final driving benefit of the candidate driving maneuver is determined based on the driving benefit of the autonomous vehicle.

In some embodiments, obtaining initial driving profits for candidate driving strategies for autonomous vehicles and interactive objects may be implemented as:

and A1, acquiring the planning speed of the automatic driving vehicle corresponding to the candidate driving strategy.

Wherein the planned speed of the autonomous vehicle (v_des ₀ ) The candidate driving strategy can be determined according to the candidate driving strategy of the automatic driving vehicle and the interactive object, wherein the candidate driving strategy is possible interactive behaviors or actions, such as acceleration overtaking or deceleration avoiding behaviors, and different planning speeds can be obtained based on different behaviors. As shown in expression (1):

v_des ₀ ＝v ₀ +a_des ₀ ×Δt (1)

wherein v_des ₀ Representing a planned speed of the autonomous vehicle corresponding to the candidate driving strategy; Δt is the first time domain; v ₀ Representing a current travel speed of the autonomous vehicle; a_des ₀ Indicating acceleration corresponding to the automated driving vehicle taking the interactive action or action.

For example, in the case where the interaction behavior of an autonomous vehicle and an interaction object represents an acceleration overtaking behavior, a_des of that behavior ₀ The value of (2) is positive, i.e. the planned speed of the autonomous vehicle is a stepwise acceleration. In the case where the interaction behavior of the autonomous vehicle and the interaction object represents a deceleration avoidance behavior, a_des of that behavior ₀ The value of (2) is negative, i.e. the planned speed of the autonomous vehicle is a gradual deceleration.

Thus, the planned speed of the autonomous vehicle may either be a deceleration or an acceleration relative to the current speed.

Step A2, determining an initial driving benefit of the candidate driving strategy based on the planned speed and a first time period required for the autonomous vehicle to reach the position of the nearest obstacle in front of the autonomous vehicle.

In some embodiments, the expression of the objective function for deriving the initial driving benefit of the candidate driving strategy is based on the planned speed of the autonomous vehicle and the first time period required for the autonomous vehicle to reach the location of the nearest obstacle in front of the autonomous vehicle is as shown in equation (2):

wherein F is _{inter_0} Representing initial driving profits of the candidate driving strategy; v_des ₀ Representing a planned speed of the autonomous vehicle; dis_relative ₀ Indicating the distance from the autonomous vehicle to the nearest obstacle in front; the ratio of the distance to the planned speed is the first time required by the automatic driving vehicle to reach the position of the nearest obstacle in front of the automatic driving vehicle; t is t _{norm_0} And v _{norm_0} Representing the normalization factor; lambda (lambda) _{0_1} And lambda (lambda) _{0_2} The weight coefficient representing the autonomous vehicle may be determined based on the actual situation, which is not limited by the embodiments of the present disclosure.

In the embodiment of the disclosure, based on the planned speed of the automatic driving vehicle and the first time required by the automatic driving vehicle to reach the position of the nearest obstacle in front of the automatic driving vehicle, the initial driving benefit determined based on the mode can accurately reflect the driving benefit corresponding to the candidate driving strategy, and a powerful data basis is provided for screening the candidate driving strategy subsequently.

In some embodiments, determining a final driving benefit of the initial driving benefit of the candidate driving strategy based on the long-term safety requirement and the short-term safety requirement may be implemented as:

and step B1, determining the initial driving benefit as the final driving benefit under the condition that the long-term safety requirement is met and the short-term safety requirement is met.

And step B2, adjusting the initial driving income to a default first value under the condition that the long-term safety requirement is not met.

The first value may be a lower value, and may be a value such as-100, -200, or the like, that is, a value indicating that the candidate driving strategy cannot ensure safe driving of the vehicle.

And B3, under the condition that the short-term safety requirement is not met, adjusting a target sub-item in an objective function for calculating the initial running benefit to a second value so as to update the initial running benefit based on the objective function and obtain the final running benefit.

The second value may be set to a lower value in a similar manner to the first value. The target sub-term may be a sub-term representing a first time, as in expression (2)Or a sub-term representing the distance of the autonomous vehicle to the position of the nearest obstacle ahead, as dis_relative in expression (2) ₀ The present disclosure is not limited in this regard.

In some embodiments, determining the long-term security requirement may be implemented as:

step C1, determining the time difference between the automatic driving vehicle and the interactive object passing through the target site.

In some embodiments, a Time Head Way (THW) method may be used to obtain a Time difference between the autonomous vehicle and the interactive object through the target location. THW represents the time difference between the front ends of the front and rear vehicles passing through the same location, and can be generally calculated by dividing the vehicle speed by the vehicle head distance between the front and rear vehicles. In the embodiment of the disclosure, the judgment can be performed based on the candidate driving strategies of the automatic driving vehicle and the interaction object, which vehicle is used as the front vehicle and which vehicle is used as the rear vehicle, and then the time difference of the two vehicles can be obtained.

In another embodiment, the time to collision (Time To Collision, TTC) in the frontal collision warning system (Forward Collision Warning, FCW) can also be used as the time difference between the two. In the case where the interactive object is a reverse incoming vehicle, as shown in fig. 3a, TTC is the distance between the head of the interactive object (vehicle B) and the head of the autonomous vehicle (vehicle a) divided by the relative speed of the two vehicles. In the case where the interactive object is in the same direction as the autonomous vehicle and in front of the autonomous vehicle, as shown in fig. 3B, TTC is the distance between the tail of the interactive object (vehicle B) and the head of the autonomous vehicle (vehicle a) divided by the relative speed of the two vehicles.

In some embodiments, to accurately obtain the time difference between the two, determining the time difference between the autonomous vehicle and the interactive object passing through the target location may be further implemented as:

and D1, determining the intersection point of the planning track of the automatic driving vehicle and the predicted track of the interactive object to obtain the target site.

The planned track of the autopilot vehicle and the predicted track of the interactive object are shown in fig. 4, and the track of the interactive object (vehicle B) is shown in a dotted line part in fig. 4 as the track of the interactive object (vehicle B) is the target point, i.e. the point where the interactive object and the vehicle B need to pass through together.

Step D2, determining a first duration for the autonomous vehicle to reach the target site based on the planned speed of the autonomous vehicle; and determining a second duration of the interaction object reaching the target location based on the estimated speed of the interaction object.

In some embodiments, the expression for the first duration may be as shown in equation (3), and the expression for the second duration may be as shown in equation (4):

wherein t_arive ₀ Representing a first duration, t_arive ₁ Representing a second time period, dis _{pos_0} Indicating the distance of the autonomous vehicle to the target site, dis _{pos_1} The distance of the interactive object to the target location is represented, and the meaning of other parameter representations is the same as the meaning of the parameters in the expression (1), so that the embodiments of the present disclosure will not be described in detail.

And D3, determining a difference value between the first time length and the second time length to obtain a time difference.

In the embodiment of the disclosure, the target location is determined based on the planned track of the automatic driving vehicle and the predicted track of the interactive object, and the planning speed of the automatic driving vehicle and the predicted speed of the interactive object are combined, so that the time difference obtained by combining the information in the future time domain of the planning speed of the automatic driving vehicle and the predicted speed of the interactive object is accurate, and a powerful foundation is laid for subsequent long-term safety requirement judgment.

And step C2, determining that the long-term safety requirement is met under the condition that the time difference is within a first safety range.

And step C3, determining that the long-term safety requirement is not met under the condition that the time difference is not in the first safety range.

Wherein, the first safety range can be determined based on actual conditions, and the embodiment of the disclosure is not limited to this. And if the time difference is in the first safety range, the obtained planning speed and estimated speed of the automatic driving vehicle and the interactive object meet the requirement of long-term driving safety of the vehicle under the candidate driving strategy. If the time difference is not within the first safety range, it is indicated that the planned speed and the estimated speed under the candidate driving strategy may cause long-term driving collision risk, so that the initial driving benefit corresponding to the candidate driving strategy may be adjusted to a default first value, where the first value may be a lower value, may be a value such as-100, -200, or the like, that is, the candidate driving strategy may not ensure safe driving of the vehicle, and then may be discarded.

In the embodiment of the disclosure, the candidate driving strategy is judged based on the time difference and the first safety range, so that the collision risk of the automatic driving vehicle and the interactive object in long-term driving can be accurately obtained, and the safety of the automatic driving vehicle in the driving process is ensured.

In some embodiments, where the long-term safety requirement is met and the first difference in time difference from the lowest critical value of the first safety range is less than the first gap threshold, the target speed is updated such that the first difference is greater than the first gap threshold and the long-term safety requirement is met; wherein the target speed comprises a planned speed of the autonomous vehicle and/or an estimated speed of the interactive object.

The target speed in this case is the planned speed of the autonomous vehicle, as it is the final driving benefit determined based on the autonomous vehicle. Since the first safety range is a range that ensures that the autonomous vehicle passes exactly safely, in the case where the difference between the time difference and the lowest threshold value of the first safety range is small, it means that the corresponding candidate driving strategy in this case has just satisfied the long-term safety requirement. Therefore, in order to further ensure the driving safety of the automatic driving vehicle, the planning speed corresponding to the time difference can be updated. For example, in the case where the first safety range is (a, b), where a is smaller than b. The range determined based on the first gap threshold may be (a, a+0.5). In case the time difference is at (a, a+0.5), the planned speed of the autonomous vehicle may be adjusted, the time difference is calculated based on the adjusted planned speed, and the initial travel benefit is calculated based on the adjusted planned speed. And under the condition that the first difference value between the adjusted time difference and the lowest critical value of the first safety range is larger than a first difference threshold value, determining that the candidate driving strategy meets the long-term safety requirement.

Of course, in order to improve the driving efficiency while ensuring the driving safety of the vehicle, the planned speed of the autonomous vehicle may be adjusted when the time difference is around the upper limit of the first preset range, for example, when the difference between the time difference and the upper limit is within the range of (b-0.5, b).

It should be noted that, the foregoing 0.5 is only used for illustration, and the first preset range may take a smaller value based on practical situations, which is not limited by the embodiment of the present disclosure.

In the embodiment of the disclosure, when the first difference between the time difference and the lowest critical value of the first safety range is smaller than the first difference threshold, it is indicated that the candidate driving strategy just meets the long-term safety requirement under the condition, and in order to further ensure the safety of the automatic driving vehicle in the driving process, the planning speed of the automatic driving strategy can be adjusted to obtain the target driving strategy more adapted to the current traffic scene.

In some embodiments, determining short-term security requirements may be implemented as:

step E1, determining a first distance between the autonomous vehicle and a nearest obstacle in front of the autonomous vehicle.

The front nearest obstacle may be any dynamic object with a motion track closest to the autopilot vehicle, for example, a pedestrian, a vehicle, etc.

Step E2, determining a first time period required for the autonomous vehicle to travel a first distance based on the planned speed of the autonomous vehicle.

Wherein the expression of the first duration is shown as the expression (5),

wherein t_cooling ₀ Representing a first duration; dis_relative ₀ Representing the distance between the autonomous vehicle and the nearest obstacle in front of it, i.e. the first distance; v_des ₀ Representing the planning speed.

And E3, determining that the automatic driving vehicle meets the short-term safety requirement under the condition that the first duration is within the second safety range.

And E4, determining that the automatic driving vehicle does not meet the short-term safety requirement under the condition that the first duration is not in the second safety range.

In the embodiment of the disclosure, the distance between the nearest obstacle in front and the automatic driving vehicle is acquired, and then the first time length is acquired in combination with the planning speed, and the comparison is performed with the first time length based on the set second safety range, so that the short-term safety of the automatic driving vehicle in the running process of the automatic driving vehicle in the first time range is ensured.

In some embodiments, in the event that the autonomous vehicle meets the short-term safety requirement and the second difference between the first time length and the lowest critical value of the second safety range is less than a second gap threshold, the planned speed of the autonomous vehicle is updated such that the second difference is greater than the second gap threshold and the autonomous vehicle meets the short-term safety requirement.

The speed that needs to be updated in this case is the planned speed of the autonomous vehicle, as it is the final driving benefit determined based on the autonomous vehicle. Since the second safety range is a range for ensuring safe passage of the autonomous vehicle, in the case where the difference between the first time period and the lowest threshold value of the second safety range is small, it means that the corresponding candidate driving strategy in this case has just satisfied the short-term safety requirement. Under the condition that the difference between the first duration and the second safety range is smaller, the difference between the candidate driving strategy corresponding to the condition and the requirement for meeting short-term safety is not large, and the planning speed can be updated in order to further ensure the driving safety of the automatic driving vehicle.

For example, in the case where the second safety range is (c, d), where c is smaller than d. The second preset range may be (c, c+0.5). In the case where the first time is at (c, c+0.5), the planned speed of the autonomous vehicle may be adjusted, the first time being calculated based on the adjusted planned speed, while an initial travel benefit is determined based on the adjusted planned speed. And under the condition that a second difference value between the first time length corresponding to the adjusted planning speed and the lowest critical value of the second safety range is larger than a second difference threshold value, determining that the candidate driving strategy meets the short-term safety requirement.

Of course, in order to improve the driving efficiency, the second preset range may be set based on the upper limit of the second safety range, for example, (d-0.5, d) on the basis of ensuring the driving safety of the vehicle. And adjusting the planning speed of the automatic driving vehicle based on the preset range.

It should be noted that, the foregoing 0.5 is only used for illustration, and the second preset range may take a smaller value based on practical situations, which is not limited by the embodiment of the present disclosure.

In the embodiment of the disclosure, when the second difference between the first duration and the lowest critical value of the second safety range is smaller than the second difference threshold, it is indicated that the candidate driving strategy just meets the short-term safety requirement under the condition, and in order to further ensure the safety of the automatic driving vehicle in the driving process, the candidate driving strategy may be adjusted so as to obtain the target driving strategy more adapted to the current traffic scene.

In some embodiments, as shown in fig. 5a, on the basis of obtaining a candidate driving strategy, the candidate driving strategy may be first determined based on an objective function, if the candidate driving strategy meets the long-term safety requirement based on the first safety range, it is determined whether the candidate driving strategy meets the short-term safety requirement, and if the candidate driving strategy meets the short-term safety requirement based on the second safety range, the final driving benefit of the candidate driving strategy is obtained. And determining a target driving strategy of the automatic driving vehicle based on the final driving income, wherein the target driving strategy comprises abstract level interaction behavior of the automatic driving vehicle and automatic driving vehicle planning level interaction behavior, so as to control the automatic driving vehicle to execute the target driving strategy.

In other embodiments, on the basis of obtaining the candidate driving strategy, the short-term safety requirement may be determined based on the objective function, where the candidate driving strategy meets the short-term safety requirement, whether the candidate driving strategy meets the long-term safety requirement is determined, and where the long-term safety requirement is met, the final driving benefit of the candidate driving strategy is obtained. And determining a target driving strategy of the automatic driving vehicle based on the final driving income, wherein the target driving strategy comprises abstract level interaction behavior of the automatic driving vehicle and automatic driving vehicle planning level interaction behavior, so as to control the automatic driving vehicle to execute the target driving strategy.

In other embodiments, the long-term security requirement and the short-term security requirement may also be determined simultaneously. Based on the mode of judging the long-term safety requirement, long-term running benefits are obtained, and based on the mode of judging the short-term safety requirement, short-term running benefits are obtained. The final travel benefit may be obtained by a weighted summation based on the long-term travel benefit and the short-term travel benefit. The final driving benefit can be obtained in a manner of averaging long-term driving benefit and short-term driving benefit. Any manner in which final travel benefits may be obtained based on both may be applicable to the embodiments of the present disclosure.

In the embodiment of the disclosure, the driving benefits of long-term safety requirements and short-term safety requirements are comprehensively considered and measured, the abstract layer interaction behavior of the vehicle can be considered, the vehicle planning level interaction instruction can be considered, and the diversified data requirements of vehicle track planning and control can be met. Meanwhile, aiming at various driving conditions of the automatic driving vehicle, the objective function provided by the embodiment of the disclosure can be adapted and adjusted, and the diversified development requirements of the interactive decision system of the automatic driving vehicle can be met.

2) Determining a final driving benefit of the candidate driving maneuver based on the driving benefit of the autonomous vehicle and the driving benefit of the interactive object

In some embodiments, determining the initial driving benefit of the candidate driving strategy may be implemented as:

and F1, acquiring the planning speed of the automatic driving vehicle and the estimated speed of the interactive object corresponding to the candidate driving strategy.

The planned speed of the autopilot vehicle may be shown in expression (1), and will not be described in detail herein. The estimated speed of the interactive object is determined in a similar manner to the planned speed of the automatic driving vehicle, as shown in expression (6):

v_des ₁ ＝v ₁ +a_des ₁ ×Δt (6)

wherein v_des ₁ Representing the estimated speed of the interactive object corresponding to the candidate driving strategy; Δt is the first time domain; v ₁ Representing the current running speed of the interactive object; a_des ₁ Representing acceleration corresponding to the interaction behavior or action taken by the interaction object. The current running speed of the interactive object may be obtained based on a sensing module of the automatic driving vehicle, or may be inferred based on the speed of the automatic driving vehicle, and any manner of obtaining the current running speed of the interactive object may be applied to the embodiments of the present disclosure.

For example, in the case where the candidate driving maneuver indicates that the interactive object has acceleration overtaking behavior, a_des of that behavior ₁ The value of (1) is positive, i.e. representing interactionThe estimated speed of the object is a gradual acceleration. In the case that the candidate driving strategy indicates that the interaction object has deceleration avoidance behavior, a_des of the behavior ₁ The value of (2) is a negative value, that is, the estimated speed of the interactive object is gradually decelerated.

Thus, the estimated speed of the interactive object may be either a deceleration or an acceleration relative to the current speed.

Step F2, determining a first sub-benefit of the autonomous vehicle based on a first time period required for the autonomous vehicle to reach a position of a nearest obstacle in front of the autonomous vehicle based on the planned speed; and determining a second sub-benefit of the interactive object based on a second time period required for the interactive object to reach the position of the nearest obstacle in front of the interactive object based on the estimated speed; wherein the initial travel benefit includes a first sub-benefit and a second sub-benefit.

Wherein, when the initial running benefit is decided together based on the interactive object and the automatic driving vehicle, the first sub benefit is equivalent to F _{inter_0} The objective function expression may be represented by the formula (2), and will not be described in detail herein.

The objective function expression of the second sub-benefit is shown in formula (7):

wherein F is _{inter_1} A second sub-benefit representing a candidate driving maneuver; v_des ₁ Representing the estimated speed of the interactive object; dis_relative ₁ Representing the distance of the interactive object reaching the position of the nearest obstacle in front; the ratio of the distance to the estimated speed is the second time length required by the interactive object to reach the position of the nearest obstacle in front of the interactive object; t is t _{norm_1} And v _{norm_1} A normalization factor representing an interaction object; lambda (lambda) _{1_1} And lambda (lambda) _{1_2} The weight coefficient representing the interactive object may be determined based on the actual situation, which is not limited by the embodiments of the present disclosure.

In the embodiment of the disclosure, the first sub-benefits of the automatic driving vehicle and the second sub-benefits of the interactive object are comprehensively considered, and the initial driving benefits determined based on the mode can accurately reflect the driving benefits corresponding to the candidate driving strategies, so that a powerful data basis is provided for screening the candidate driving strategies subsequently.

and G1, determining the initial driving benefit as the final driving benefit under the condition that the long-term safety requirement is met and the short-term safety requirement is met.

Step G2, under the condition that the long-term safety requirement is not met, updating the sub-benefits corresponding to the updated speed in the planning speed and the estimated speed into a default first value; the planning speed corresponds to the first sub-benefit, and the estimated speed corresponds to the second sub-benefit.

In some embodiments, determining the long-term security requirement may be implemented as: determining a time difference between the autonomous vehicle and the interactive object passing through the target location; determining that the long-term security requirement is met if the time difference is within a first security range; in the event that the time difference is not within the first safety range, it is determined that the long-term safety requirement is not met.

The manner of determining the time difference is described above, and this is not described in detail in the embodiments of the present disclosure.

Wherein, the first safety range can be determined based on actual conditions, and the embodiment of the disclosure is not limited to this. And if the time difference is in the first safety range, the obtained planning speed and estimated speed of the automatic driving vehicle and the interactive object meet the requirement of long-term driving safety of the vehicle under the candidate driving strategy. If the time difference is not within the first safety range, it is indicated that the planned speed and the estimated speed under the candidate driving strategy may cause a long-term driving collision risk. In the event that it is determined that the time difference is not within the first safety range due to a planned speed of the autonomous vehicle, a first sub-benefit corresponding to the planned speed may be adjusted to a default first value. And under the condition that the time difference is not in the first safety range due to the estimated speed of the interactive object, the second sub-benefit corresponding to the estimated speed can be adjusted to be a default first value. In the event that it is determined that the time difference is not within the first safety range due to the planned speed of the autonomous vehicle and the estimated speed of the interactive object, both the first sub-benefit and the second sub-benefit may be adjusted to a default first value.

The first value may be a lower value, that is, it indicates that the candidate driving strategy is discarded because the candidate driving strategy cannot guarantee safe driving of the vehicle.

The target speed in this case includes the planned speed of the autonomous vehicle and/or the estimated speed of the interactive object, as it is the final driving benefit based on the co-decision of the autonomous vehicle and the interactive object. In case it is determined that the planned speed of the autonomous vehicle results in a first difference of the time difference from the critical value of the first safety range being smaller than a first gap threshold, the planned speed may be adjusted. The estimated speed may be adjusted if it is determined that the estimated speed of the interactive object results in a first difference between the time difference and the critical value of the first safety range being less than a first gap threshold. In the event that it is determined that the first difference between the time difference and the critical value of the first safety range is less than the first gap threshold by both, both may be adjusted together. The specific adjustment manner is similar to the foregoing adjustment manner, and this disclosure will not be repeated here.

Step G3, updating the sub-benefits corresponding to the target object under the condition that the short-term safety requirement is not met, so as to obtain the final driving benefits; wherein, in the event that the autonomous vehicle does not meet the short-term safety requirement, the target object comprises the autonomous vehicle; in the event that the interactive object does not meet short-term security requirements, the target object comprises the interactive object.

In some embodiments, updating sub-benefits corresponding to target objects in the autonomous vehicle and the interactive object that do not meet short-term security requirements may be implemented as:

and step H1, in the case that the automatic driving vehicle does not meet the short-term safety requirement, adjusting the target sub-item in the target function for calculating the first sub-benefit to a second value so as to update the first sub-benefit based on the target function.

The second value may be set in a lower value similar to the above setting. The target sub-term may be a sub-term representing a first duration, as in expression (2)Or a sub-term representing the distance of the autonomous vehicle to the position of the nearest obstacle ahead, as dis_relative in expression (2) ₀ The present disclosure is not limited in this regard.

And step H2, in the case that the interactive object does not meet the short-term security requirement, adjusting the target sub-item in the target function for calculating the second sub-benefit to a second value so as to update the second sub-benefit based on the target function.

The target sub-term may be a sub-term representing a second duration, as in expression (7)Or a sub-term representing the distance of the interactive object to the position of the nearest obstacle in front, such as dis_relative in expression (7) ₁ The present disclosure is not limited in this regard. />

In the embodiment of the disclosure, the first sub-benefits of the automatic driving vehicle and the second sub-benefits of the interactive object are comprehensively considered, and under the condition that any one of the two sub-benefits does not meet the short-term safety requirement, the benefits corresponding to the two sub-benefits are respectively updated so as to ensure the respective driving safety of the automatic driving vehicle and the interactive object.

In the embodiment of the disclosure, the driving benefits of long-term safety requirements and short-term safety requirements are comprehensively considered and measured, and not only can abstract layer interaction behaviors of vehicles be considered, but also vehicle planning level interaction instructions can be considered. Under the condition that any one of the two requirements of short-term safety is not met, the corresponding benefits of the two requirements are updated respectively to obtain final driving benefits, and further the driving safety of the automatic driving vehicle and the driving safety of each interaction object are guaranteed.

In some embodiments, determining the short-term security requirement may be divided into a short-term security requirement of the autonomous vehicle and a short-term security requirement of the interactive object. The manner of determining the short-term safety requirement of the autonomous vehicle is the same as that set forth in steps E1-E4, and the disclosure is not repeated here.

In some embodiments, determining short-term security requirements for an interactive object may be implemented as:

step I1, determining a second distance between the interactive object and the nearest obstacle in front of the interactive object.

The front nearest obstacle may be any dynamic object with a motion track closest to the interactive object, for example, a pedestrian, a vehicle, etc.

And step I2, determining a second duration required for the interactive object to travel a second distance based on the estimated speed of the interactive object.

Wherein the expression of the second time period is shown as the expression (8),

wherein t_cooling ₁ Representing a second duration, dis_relative ₁ Representing a second distance, v_des ₁ Representing the estimated speed.

And step I3, determining that the interactive object meets the short-term security requirement under the condition that the second duration is within a third security range.

And step I4, determining that the interactive object does not meet the short-term security requirement under the condition that the second duration is not in the third security range.

In the embodiment of the disclosure, in order to ensure the safety of the automatic driving vehicle in the running process, consideration is taken into consideration in combination with the short-term safety requirement of the interaction object. And acquiring the distance between the nearest obstacle in front and the interactive object, further acquiring a second duration by combining the estimated speed, and comparing the second duration with a third safety range set based on the second duration to ensure the short-term safety of the interactive object and the automatic driving vehicle in the advancing process of the interactive object and the automatic driving vehicle in the first time range.

In some embodiments, the first sub-benefit of the autonomous vehicle and the second sub-benefit of the interchange object are required to meet short-term safety requirements because they are based on the final travel benefit that the autonomous vehicle and the interchange object together decide. Therefore, in the case where the autonomous vehicle meets the short-term safety requirement and the second difference between the first time period and the lowest critical value of the second safety range is less than the second gap threshold, the planned speed of the autonomous vehicle may be adjusted, the first time period may be calculated based on the adjusted planned speed, and the first sub-benefit may be determined based on the adjusted planned speed. And under the condition that a second difference value between the first time length corresponding to the adjusted planning speed and the lowest critical value of the second safety range is larger than a second difference threshold value, determining that the candidate driving strategy meets the short-term safety requirement. The specific adjustment manner is similar to the foregoing adjustment manner, and this is not described in detail in the embodiments of the present disclosure.

In some embodiments, in the event that the interactive object meets the short-term security requirement and a third difference between the second duration and a lowest critical value of the third security range is less than a third gap threshold, the estimated speed of the interactive object is updated such that the third difference is greater than the third gap threshold and the interactive object meets the short-term security requirement.

Since the third safety range is a range that ensures that the autonomous vehicle and the interactive object are just safely traveling. Thus, in the case where the difference between the second time period and the lowest threshold value of the third safety range is small, it means that the corresponding candidate driving strategy in this case has just satisfied the short-term safety requirement. Under the condition that the difference between the second duration and the third safety range is smaller, the difference between the candidate driving strategy corresponding to the condition and meeting the short-term safety requirement is not large, and the estimated speed can be updated in order to further ensure the driving safety of the automatic driving vehicle and the interactive object. The specific adjustment manner is similar to the adjustment manner of the planned speed of the automatic driving vehicle, and the embodiments of the present disclosure will not be described in detail herein.

In the embodiment of the disclosure, when the third difference between the second duration and the lowest critical value of the third safety range is smaller than the third difference threshold, it is indicated that the candidate driving strategy just meets the short-term safety requirement under the condition, and in order to further ensure the safety of the automatic driving vehicle and the interactive object in the driving process, the candidate driving strategy may be adjusted so as to obtain a target driving strategy more adapted to the current traffic scene.

In some embodiments, as shown in fig. 5b, on the basis of obtaining a candidate driving strategy, the candidate driving strategy may be first determined based on an objective function, if the candidate driving strategy meets the long-term safety requirement based on the first safety range, the candidate driving strategy is determined whether to meet the short-term safety requirement, and if the candidate driving strategy meets the short-term safety requirement based on the second safety range and the third safety range, the final driving benefit of the candidate driving strategy is obtained. A target driving strategy for the autonomous vehicle is determined based on the final driving benefit, the target driving strategy including abstract level interactions of the autonomous vehicle and autonomous vehicle planning level interactions. And further realizing the control of the automatic driving vehicle to execute the target driving strategy.

In other embodiments, the long-term security requirement and the short-term security requirement may also be determined simultaneously. Based on the mode of judging the long-term safety requirement, long-term running benefits are obtained, and based on the mode of judging the short-term safety requirement, short-term running benefits are obtained. The final travel benefit may be obtained by a weighted summation based on the long-term travel benefit and the short-term travel benefit. The final driving benefit can be obtained in a manner of averaging long-term driving benefit and short-term driving benefit. A target driving strategy for the autonomous vehicle is determined based on the final driving benefit, the target driving strategy including abstract level interactions of the autonomous vehicle and autonomous vehicle planning level interactions. And further realizing the control of the automatic driving vehicle to execute the target driving strategy. Any manner in which final travel benefits may be obtained based on both may be applicable to the embodiments of the present disclosure.

In some embodiments, the final driving benefit is determined based on the first sub-benefit of the autonomous vehicle and the second sub-benefit of the interactive object obtained in the foregoing manner. Deciding whether the candidate driving maneuver is the target driving maneuver on this basis may be implemented as: inputting the first sub-benefits of the automatic driving vehicle and the second sub-benefits of the interactive object into a game model to obtain the final driving benefits of the candidate driving strategy; in the case where the candidate driving maneuver is selected as the target driving maneuver based on the final driving benefit, the autonomous vehicle is controlled to execute the target driving maneuver.

Taking a game scene as an interaction object to enter a lane where an automatic driving vehicle is located, wherein the candidate driving strategy 1 is that the automatic driving vehicle dodges, and the interaction object does not dodge; the candidate driving strategy 2 is that the automatic driving vehicle does not avoid, and the interactive object does not avoid; the candidate driving strategy 3 is that the automatic driving vehicle does not avoid, and the interactive object avoids; the candidate driving strategy 4 is for avoiding the automatic driving vehicle and avoiding the interactive object. And respectively calculating the final driving profits of the four candidate driving strategies based on the mode, and inputting the final driving profits into a game model to obtain respective corresponding profits information. If the candidate driving strategy 1 is determined to be avoidance as the target driving strategy of the automatic driving vehicle through the game model, the automatic driving vehicle decides that the driving behavior is avoidance based on the target driving strategy.

Based on the same technical concept, the embodiment of the present disclosure further provides a control apparatus 600 of an autonomous vehicle, as shown in fig. 6, including:

an obtaining module 601, configured to obtain an initial driving benefit of a candidate driving strategy of an automatic driving vehicle and an interactive object;

a determining module 602 for determining a final driving benefit of the initial driving benefit of the candidate driving strategy based on the long-term safety requirement and the short-term safety requirement; long-term safety requirements require safe passage of autonomous vehicles and interactive objects through a target site; short-term safety requirements require that an autonomous vehicle be able to safely travel in a first time domain;

A control module 603 for controlling the autonomous vehicle to execute the target driving maneuver in case the candidate driving maneuver is selected as the target driving maneuver based on the final driving benefit.

In some embodiments, the acquisition module is configured to:

acquiring the planning speed of the automatic driving vehicle corresponding to the candidate driving strategy;

an initial driving benefit of the candidate driving maneuver is determined based on the planned speed and a first time period required for the autonomous vehicle to reach the location of the nearest obstacle in front of the autonomous vehicle.

In some embodiments, the determining module is configured to:

determining the initial driving benefit as the final driving benefit under the condition that the long-term safety requirement is met and the short-term safety requirement is met;

under the condition that the long-term safety requirement is not met, the initial running income is adjusted to a default first value;

and under the condition that the short-term safety requirement is not met, adjusting the target sub-item in the target function for calculating the initial running benefit to a second value so as to update the initial running benefit based on the target function and obtain the final running benefit.

In some embodiments, the acquisition module is configured to:

acquiring the planning speed of the automatic driving vehicle corresponding to the candidate driving strategy and the estimated speed of the interactive object;

Determining a first sub-benefit of the autonomous vehicle based on a first time period required for the autonomous vehicle to reach a location of a nearest obstacle in front of the autonomous vehicle based on the planned speed; the method comprises the steps of,

determining a second sub-benefit of the interactive object based on a second time length required by the interactive object to reach the position of the nearest obstacle in front of the interactive object based on the estimated speed;

wherein the initial travel benefit includes a first sub-benefit and a second sub-benefit.

In some embodiments, the determining module comprises:

a determining unit for determining that the initial travel benefit is a final travel benefit in the case where the long-term security requirement is satisfied and the short-term security requirement is satisfied;

the first updating unit is used for updating the sub-benefits corresponding to the updated speed in the planning speed and the estimated speed into a default first value under the condition that the long-term safety requirement is not met; the planning speed corresponds to the first sub-benefit, and the estimated speed corresponds to the second sub-benefit;

the second updating unit is used for updating the sub-benefits corresponding to the target object under the condition that the short-term safety requirement is not met so as to obtain the final driving benefits;

wherein, in the event that the autonomous vehicle does not meet the short-term safety requirement, the target object comprises the autonomous vehicle;

In the event that the interactive object does not meet short-term security requirements, the target object comprises the interactive object.

In some embodiments, the second updating unit is configured to:

in the event that the autonomous vehicle does not meet the short-term safety requirement, adjusting a target sub-item in an objective function for calculating the first sub-benefit to a second value to update the first sub-benefit based on the objective function;

in the event that the interactive object does not meet the short-term security requirement, the target sub-item in the objective function used to calculate the second sub-benefit is adjusted to a second value to update the second sub-benefit based on the objective function.

In some embodiments, the system further comprises a long-term security determination module for:

determining a time difference between the autonomous vehicle and the interactive object passing through the target location;

determining that the long-term security requirement is met if the time difference is within a first security range;

in the event that the time difference is not within the first safety range, it is determined that the long-term safety requirement is not met.

In some embodiments, the method further comprises a first update module for:

in the case that the long-term safety requirement is met and the first difference between the time difference and the lowest critical value of the first safety range is less than the first gap threshold, updating the target speed so that the first difference is greater than the first gap threshold and the long-term safety requirement is met;

Wherein the target speed comprises a planned speed of the autonomous vehicle and/or an estimated speed of the interactive object.

In some embodiments, the long-term security determination module comprises:

the location determining unit is used for determining the intersection point of the planning track of the automatic driving vehicle and the predicted track of the interactive object to obtain a target location;

a time length determining unit for determining a first time length for the autonomous vehicle to reach the target location based on the planned speed of the autonomous vehicle; determining a second time length for the interactive object to reach the target place based on the estimated speed of the interactive object;

and the time difference determining unit is used for determining the difference between the first time length and the second time length to obtain a time difference.

In some embodiments, a first short-term security determination module is further included for:

determining a first distance between the autonomous vehicle and a nearest obstacle in front of the autonomous vehicle;

determining a first time period required for the autonomous vehicle to travel a first distance based on the planned speed of the autonomous vehicle;

determining that the autonomous vehicle meets short-term safety requirements if the first duration is within a second safety range;

in the event that the first duration is not within the second safety range, it is determined that the autonomous vehicle does not meet the short-term safety requirement.

In some embodiments, the method further comprises a second update module for:

and updating the planning speed of the automatic driving vehicle under the condition that the automatic driving vehicle meets the short-term safety requirement and the second difference value between the first time length and the lowest critical value of the second safety range is smaller than the second difference threshold value, so that the second difference value is larger than the second difference threshold value and the automatic driving vehicle meets the short-term safety requirement.

In some embodiments, a second short-term security determination module is further included for:

determining a second distance between the interactive object and a nearest obstacle in front of the interactive object;

determining a second duration required for the interactive object to travel a second distance based on the estimated speed of the interactive object;

under the condition that the second duration is within a third safety range, determining that the interactive object meets short-term safety requirements;

and in the case that the second duration is not within the third safety range, determining that the interactive object does not meet the short-term safety requirement.

In some embodiments, a third update module is further included for:

and under the condition that the interactive object meets the short-term security requirement and the third difference value between the second time length and the lowest critical value of the third security range is smaller than a third difference threshold value, updating the estimated speed of the interactive object so that the third difference value is larger than the third difference threshold value and the interactive object meets the short-term security requirement.

Of course, in the technical scheme of the disclosure, the acquisition, storage, application and the like of the related user personal information all conform to the regulations of related laws and regulations, and the public sequence is not violated.

For descriptions of specific functions and examples of each module and sub-module of the apparatus in the embodiments of the present disclosure, reference may be made to the related descriptions of corresponding steps in the foregoing method embodiments, which are not repeated herein.

According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

Fig. 7 illustrates a schematic block diagram of an example electronic device 700 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile apparatuses, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing apparatuses. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 7, the apparatus 700 includes a computing unit 701 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 may also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

Various components in device 700 are connected to I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, etc.; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, an optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The computing unit 701 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The calculation unit 701 executes the respective methods and processes described above, for example, a control method of an autonomous vehicle. For example, in some embodiments, the method of controlling an autonomous vehicle may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 700 via ROM 702 and/or communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the above-described control method of the autonomous vehicle may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the control method of the autonomous vehicle by any other suitable means (e.g. by means of firmware).

Based on the foregoing electronic device, the disclosure further provides an automatic driving vehicle, which may include the electronic device, and may further include a communication component, a display screen, an information acquisition device for acquiring surrounding environment information, and the like, where the communication component, the display screen, the information acquisition device and the electronic device are in communication connection. The electronic device included in the autonomous vehicle may execute the control method of the autonomous vehicle provided by the embodiment of the disclosure.

According to the embodiment of the disclosure, the electronic device may be integrally integrated with the communication part, the display screen and the information acquisition device, or may be separately provided with the communication part, the display screen and the information acquisition device.

Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, 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. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, 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.

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

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions, improvements, etc. that are within the principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. A control method of an autonomous vehicle, comprising:

determining a final driving benefit of the initial driving benefit of the candidate driving strategy based on the long-term safety requirement and the short-term safety requirement; the long-term safety requirement requires safe passage of the autonomous vehicle and the interactive object through a target site; the short-term safety requirement requires that the autonomous vehicle be able to safely travel in a first time domain;

and controlling the automatic driving vehicle to execute the target driving strategy under the condition that the candidate driving strategy is selected as the target driving strategy based on the final driving benefit.

2. The method of claim 1, wherein the obtaining initial driving benefit of the candidate driving maneuver of the autonomous vehicle and the interactive object comprises:

and determining initial driving profits of the candidate driving strategies based on the planning speed and a first time period required by the automatic driving vehicle to reach the position of the nearest obstacle in front of the automatic driving vehicle.

3. The method of claim 2, wherein the determining a final driving benefit of the initial driving benefit of the candidate driving strategy based on the long-term safety requirement and the short-term safety requirement comprises:

determining the initial travel benefit as the final travel benefit if the long-term safety requirement is met and the short-term safety requirement is met;

adjusting the initial travel benefit to a default first value if the long-term safety requirement is not met;

and under the condition that the short-term safety requirement is not met, adjusting a target sub-item in an objective function for calculating the initial running benefit to a second value so as to update the initial running benefit based on the objective function and obtain the final running benefit.

4. The method of claim 1, wherein the determining the initial driving benefit of the candidate driving maneuver comprises:

acquiring the planning speed of the automatic driving vehicle and the estimated speed of the interactive object corresponding to the candidate driving strategy;

determining a first sub-benefit of the autonomous vehicle based on the planned speed for a first time period required for the autonomous vehicle to reach a location of a nearest obstacle in front of the autonomous vehicle; the method comprises the steps of,

Determining a second sub-benefit of the interactive object based on a second time period required by the interactive object to reach the position of the nearest obstacle in front of the interactive object;

wherein the initial travel benefit includes the first sub-benefit and the second sub-benefit.

5. The method of claim 4, wherein the determining a final driving benefit of the initial driving benefit of the candidate driving strategy based on the long-term safety requirement and the short-term safety requirement comprises:

under the condition that the long-term safety requirement is not met, updating the sub-benefits corresponding to the updated speed in the planning speed and the estimated speed into a default first value; the planning speed corresponds to the first sub-benefit, and the estimated speed corresponds to the second sub-benefit;

under the condition that the short-term safety requirement is not met, updating the sub-benefits corresponding to the target object to obtain the final driving benefits;

wherein the target object comprises the autonomous vehicle if the autonomous vehicle does not meet the short-term safety requirement;

In the event that the interactive object does not meet the short-term security requirement, the target object comprises the interactive object.

6. The method of claim 5, wherein the updating the sub-revenue corresponding to the target object comprises:

adjusting a target sub-item in an objective function for calculating the first sub-benefit to a second value to update the first sub-benefit based on the objective function if the autonomous vehicle does not meet the short-term safety requirement;

and in the case that the interactive object does not meet the short-term security requirement, adjusting a target sub-item in an objective function for calculating the second sub-benefit to a second value so as to update the second sub-benefit based on the objective function.

7. The method of any of claims 1-6, further comprising:

determining a time difference between the autonomous vehicle and the interactive object passing through a target location;

8. The method of claim 7, further comprising:

updating a target speed such that the first difference is greater than a first gap threshold and meets the long-term safety requirement if the long-term safety requirement is met and a first difference of the time difference from a lowest critical value of the first safety range is less than the first gap threshold;

9. The method of claim 7, wherein the determining a time difference between the autonomous vehicle and the interactive object passing through a target location comprises:

determining the intersection point of the planning track of the automatic driving vehicle and the predicted track of the interactive object to obtain the target site;

determining a first duration for the autonomous vehicle to reach the target location based on a planned speed of the autonomous vehicle; the method comprises the steps of,

determining a second duration of the interaction object reaching the target location based on the estimated speed of the interaction object;

and determining a difference value between the first time length and the second time length to obtain the time difference.

10. The method of any of claims 2-9, further comprising:

determining a first time period required for the autonomous vehicle to travel the first distance based on a planned speed of the autonomous vehicle;

determining that the autonomous vehicle meets the short-term safety requirement if the first duration is within a second safety range;

and if the first duration is not within the second safety range, determining that the autonomous vehicle does not meet the short-term safety requirement.

11. The method of claim 10, further comprising:

and updating the planning speed of the automatic driving vehicle under the condition that the automatic driving vehicle meets the short-term safety requirement and a second difference value between the first duration and the lowest critical value of the second safety range is smaller than a second difference threshold value, so that the second difference value is larger than the second difference threshold value and the automatic driving vehicle meets the short-term safety requirement.

12. The method of any of claims 4-11, further comprising:

determining a second duration required for the interactive object to travel the second distance based on the estimated speed of the interactive object;

determining that the interactive object meets the short-term security requirement when the second duration is within a third security range;

and if the second duration is not within the third safety range, determining that the interactive object does not meet the short-term safety requirement.

13. The method of claim 12, further comprising:

and under the condition that the interactive object meets the short-term security requirement and a third difference value between the second duration and the lowest critical value of the third security range is smaller than a third difference threshold value, updating the estimated speed of the interactive object so that the third difference value is larger than the third difference threshold value and the interactive object meets the short-term security requirement.

14. A control device for an autonomous vehicle, comprising:

a determining module for determining a final driving benefit of the initial driving benefit of the candidate driving strategy based on the long-term safety requirement and the short-term safety requirement; the long-term safety requirement requires safe passage of the autonomous vehicle and the interactive object through a target site; the short-term safety requirement requires that the autonomous vehicle be able to safely travel in a first time domain;

15. The apparatus of claim 14, wherein the means for obtaining is configured to:

16. The apparatus of claim 15, wherein the means for determining is configured to:

17. The apparatus of claim 14, wherein the means for obtaining is configured to:

18. The apparatus of claim 17, wherein the means for determining comprises:

a determining unit configured to determine the initial travel benefit as the final travel benefit in a case where the long-term security requirement is satisfied and the short-term security requirement is satisfied;

19. The apparatus of claim 18, wherein the second updating unit is configured to:

20. The apparatus of any of claims 14-19, further comprising a long-term security determination module to:

21. The apparatus of claim 20, further comprising a first update module to:

22. The apparatus of claim 20, wherein the long-term security determination module comprises:

the location determining unit is used for determining the intersection point of the planned track of the automatic driving vehicle and the predicted track of the interactive object to obtain the target location;

a time length determining unit configured to determine a first time length for the autonomous vehicle to reach the target location based on a planned speed of the autonomous vehicle; and determining a second duration of the interaction object reaching the target location based on the estimated speed of the interaction object;

And the time difference determining unit is used for determining the difference value between the first time length and the second time length to obtain the time difference.

23. The apparatus of any of claims 15-22, further comprising a first short-term security determination module to:

24. The apparatus of claim 23, further comprising a second update module to:

25. The apparatus of any of claims 17-24, further comprising a second short-term security determination module to:

26. The apparatus of claim 25, further comprising a third update module to:

27. An electronic device, comprising:

At least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-13.

28. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-13.

29. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-13.

30. A vehicle comprising the electronic device of claim 27.