Automatic driving vehicle following target decision-making method in lane-free environment

Abstract

The invention discloses an automatic driving vehicle following target decision-making method in a lane-free environment. The method comprises the steps that 1, an automatic driving vehicle obtains state information and surrounding environment information in the lane-free environment; 2, determining an observation area and a risk area; 3, calculating transverse and longitudinal distances between each front vehicle and the vehicle; 4, determining a car-following target, and constructing a car-following model; and 5, determining the acceleration of the vehicle by using the car-following model. According to the method, the behavior planning problem of the automatic driving vehicle in an environment lacking clear lane marks can be solved without depending on lane marks and parameters, so that the traffic efficiency of lane-free traffic on the road is improved and the vehicle delay is reduced on the premise of ensuring the safe driving of the vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation, and more specifically, it relates to a following target decision-making method for autonomous vehicles in a lane-free environment. Background Art

[0002] With the rapid development of autonomous driving technology, autonomous vehicles have been able to improve traffic safety and efficiency, reduce energy consumption and emissions. These technologies achieve intelligent speed control by precisely monitoring the position and speed of the vehicle ahead, bringing a smoother and more comfortable travel experience for commuters. However, current autonomous driving technologies rely heavily on lane markings and parameters, which are the basis for many following and lane-changing algorithms. In a lane-free environment and future lane-free strategies, this dependence poses a major challenge to the behavior planning of autonomous vehicles. In an environment without clear lane markings, such as poorly maintained urban roads and highways, vehicles often fail to form an orderly queue, and the traffic flow is variable, making it difficult for autonomous vehicles to make appropriate driving decisions. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and proposes a following target decision-making method for autonomous vehicles in a lane-free environment, aiming to adapt to the particularity of the lane-free environment, improve the traffic efficiency of lane-free traffic on general urban roads, and reduce vehicle delays on the premise of ensuring the safe driving of the vehicle, so as to ensure that autonomous vehicles can navigate safely and efficiently under current and future road conditions.

[0004] The present invention adopts the following technical solutions to achieve the above invention objectives:

[0005] A following target decision-making method for autonomous vehicles in a lane-free environment according to the present invention is characterized in that it is applied to a road scenario without lane markings; taking the forward direction of the autonomous vehicle as the positive x-axis direction, that is, the longitudinal direction, setting the longitudinal coordinate of the centroid position of the autonomous vehicle to zero and the transverse coordinate of the road center line position to zero, the following target decision-making method for autonomous vehicles includes the following steps:

[0006] Step 1, obtain the driving behavior state information and surrounding environment information of an autonomous vehicle car at time t, where the driving behavior state information includes: the vehicle speed of the autonomous vehicle car , vehicle width , vehicle length and the position coordinates of the vehicle, and the surrounding environment information includes: the speeds, vehicle widths, vehicle lengths and position coordinates of all the vehicles ahead of the autonomous vehicle car;

[0007] Step 2, determine the observation area DZ and the risk area RZ;

[0008] Step 3: Determine whether there is a vehicle ahead in the risk zone RZ; if not, execute Step 4; if so, execute Step 5;

[0009] Step 4: Calculate the acceleration of the autonomous vehicle car at time t according to the Free-IDM method shown in Equation (3) and then execute Step 6;

[0010] (3)

[0011] In Equation (3), is the maximum acceleration; is the desired speed;

[0012] Step 5: Determine the following target of the autonomous vehicle car and calculate the acceleration at time t ;

[0013] Step 6: After assigning t + 1 to t, return to Step 1 and execute sequentially until the autonomous vehicle car ends driving.

[0014] The feature of a following target decision method for an autonomous vehicle in a lane-free environment according to the present invention also lies in that the Step 2 includes:

[0015] Step 2.1: Calculate the observation zone DZ of the autonomous vehicle car according to Equation (1);

[0016] (1)

[0017] In Equation (1), is the longitudinal range of the observation zone DZ; is the desired time interval; is the comfortable acceleration; is the lateral range of the observation zone DZ; is the lateral coordinate of the right boundary of the road; is the lateral coordinate of the left boundary of the road;

[0018] Step 2.2: Number all the vehicles ahead in the observation zone DZ of the autonomous vehicle car, and denote any j-th vehicle ahead as ;

[0019] Step 2.3: Calculate the risk zone RZ of the autonomous vehicle car according to Equation (2);

[0020] (2)

[0021] In Equation (2), is the longitudinal range of the risk zone RZ, is the lateral range of the risk zone RZ, is the lateral position coordinate of the autonomous driving vehicle car at time t, is the vehicle in front, width, is the safety factor; is the minimum lateral safety gap.

[0022] Further, the step 5 includes:

[0023] Step 5.1, use Equation (4) to determine the vehicle in front with the minimum longitudinal distance from the autonomous driving vehicle car within the risk zone RZ , and take as the following target of the autonomous driving vehicle car;

[0024] (4)

[0025] In Equation (4), is the longitudinal position coordinate of the vehicle in front at time t, is the lateral position coordinate of the vehicle in front at time t;

[0026] Step 5.2, calculate the acceleration of the autonomous driving vehicle car at time t when following the vehicle in front according to the SIDM method shown in Equation (5):

[0027] (5)

[0028] In Equation (5), is the acceleration intensity, is the longitudinal position of the vehicle in front at time t, is the speed of the vehicle in front at time t, is the cautious following distance, is the safe stopping distance; is the desired headway, and there is:

[0029] (6).

[0030] An electronic device of the present invention, including a memory and a processor, is characterized in that the memory is used to store a program that supports the processor to execute the collaborative control method, and the processor is configured to execute the program stored in the memory.

[0031] A computer-readable storage medium of the present invention, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, it executes the steps of the following target decision-making method.

[0032] Compared with the prior art, the beneficial technical effects of the present invention are reflected in:

[0033] 1. The present invention no longer relies on lane markings and parameters, specifically targeting the scenario of general roads without lanes, solves the problem of behavior planning for autonomous vehicles in an environment lacking clear lane markings, adapts to the lane-less environment, and overcomes the limitation of the prior art that severely relies on lane markings and parameters and is difficult to make appropriate driving decisions in a lane-less environment.

[0034] 2. On the premise of ensuring the safe driving of the vehicle, the present invention improves the traffic flow efficiency of general roads without lanes and reduces vehicle delays, helps to improve the traffic conditions in a lane-less environment, provides a more effective driving strategy for autonomous vehicles in complex urban road lane-less scenarios, and enhances the overall traffic operation effect.

[0035] 3. The present invention determines the following vehicle target and vehicle acceleration by comprehensively considering the horizontal and vertical distances, which helps to improve the driving safety of autonomous vehicles in a lane-less environment, reduces the collision risk. Especially in a lane-less scenario where the driving direction of the vehicle is not clear and the traffic order is relatively chaotic, this decision-making method considering multiple factors can more effectively ensure the safety of vehicles and pedestrians.

[0036] 4. The present invention provides a general method for decision-making of following vehicle targets for autonomous vehicles in a lane-less environment, which is not only applicable to the current general road lane-less scenario, but its principle and framework may have certain universality, and can provide a reference and expansion basis for future other similar lane-less scenarios or application scenarios after traffic rules change, helping to promote the application development of autonomous driving technology in a wider and more complex environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is the overall flowchart of the present invention;

[0038] Figure 2 is the decision flowchart of the present invention;

[0039] Figure 3 is the scenario schematic diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] In this embodiment, a method for decision-making of following vehicle targets for autonomous vehicles in a lane-less environment is as Figure 3 shown, characterized in that the scenario involved in the method for decision-making of following vehicle targets for autonomous vehicles is a road scenario without lane markings, including environments without lane markings or with blurred lane markings, such as poorly maintained urban roads and highways, etc.; as Figure 3As shown in part (a) thereof, a plane rectangular coordinate system is established, with the forward direction of the autonomous vehicle as the positive x-axis direction, i.e., the longitudinal direction. At this time, the positive y-axis direction is perpendicular to the road boundary line and points to the left boundary. Let the longitudinal coordinate of the centroid position of the autonomous vehicle be zero, and the transverse coordinate of the road center line position be zero. As Figure 1 and Figure 2 shown, the following steps are included in the following steps of the autonomous vehicle following target decision-making method:

[0041] Step 1. Obtain the driving behavior state information and surrounding environment information of an autonomous vehicle car at time t. The driving behavior state information includes: the vehicle speed of the autonomous vehicle car , vehicle width , vehicle length and the position coordinates of the vehicle. The surrounding environment information includes: the speeds, vehicle widths, vehicle lengths and position coordinates of all the vehicles in front of the autonomous vehicle car, and the road boundary positions.

[0042] Step 2. Determine the observation area and the risk area;

[0043] Step 2.1. Calculate the observation area DZ of the autonomous vehicle car according to Equation (1), that is, the observation range of the autonomous vehicle car;

[0044] (1)

[0045] In Equation (1), is the longitudinal range of the observation area DZ; is the desired speed; is the desired time interval; is the comfortable acceleration; is the transverse range of the observation area DZ; is the transverse coordinate of the right road boundary; is the transverse coordinate of the left road boundary.

[0046] Step 2.2. Number all the vehicles in front of the observation area DZ of the autonomous vehicle car, and denote any j-th vehicle in front as ;

[0047] Step 2.3. Calculate the risk area RZ of the autonomous vehicle car according to Equation (2). When the position of the intelligent vehicle is close to the road boundary, take the close road boundary as the boundary of the risk area on this side, as shown in part (b) of Figure 3 ;

[0048] (2)

[0049] In Equation (2), is the longitudinal range of the risk area RZ, is the lateral range of the risk zone RZ, is the lateral position coordinate of the autonomous vehicle car at time t, is the leading vehicle width, is the safety factor; is the minimum lateral safety gap.

[0050] Step 3. Determine whether there is a leading vehicle in the risk zone RZ; if not, as shown in part (c) of Figure 3 , there is no leading vehicle in the risk zone, and the autonomous vehicle car will not be affected by the leading vehicle in the risk zone and can drive freely, then execute Step 4. If so, there is a leading vehicle in the risk zone, then execute Step 5.

[0051] Step 4. Calculate the acceleration of the autonomous vehicle car at time t according to Equation (3) Free-IDM and then execute Step 6;

[0052] (3)

[0053] In Equation (3), is the maximum acceleration.

[0054] Step 5. Determine the following-distance target of the autonomous vehicle car and calculate the acceleration at time t ;

[0055] Step 5.1. Use Equation (4) to determine the leading vehicle in the risk zone RZ with the minimum longitudinal distance from the autonomous vehicle car , the risk of collision between the autonomous vehicle car and this leading vehicle is relatively high, and is used as the following-distance target of the autonomous vehicle car;

[0056] (4)

[0057] In Equation (4), is the longitudinal position coordinate of the leading vehicle at time t, is the longitudinal position coordinate of the leading vehicle at time t.

[0058] Step 5.2. Calculate the acceleration of the autonomous vehicle car at time t when following the leading vehicle according to Equation (5) SIDM :

[0059] (5)

[0060] In Equation (5), is the acceleration intensity, is the leading vehicle The longitudinal position at time t, is the leading vehicle The speed at time t, is the cautious following distance, is the safe stopping distance; is the desired headway, and there is:

[0061] (6)

[0062] Step 6: After assigning t + 1 to t, return to Step 1 and execute sequentially until the autonomous vehicle car ends driving.

[0063] In this embodiment, an electronic device includes a memory and a processor. The memory is used to store a program that supports the processor to execute the above-mentioned following target decision-making method, and the processor is configured to execute the program stored in the memory.

[0064] In this embodiment, a computer-readable storage medium stores a computer program, and when the computer program is run by a processor, it executes the steps of the above-mentioned following target decision-making method.

Claims

1. A method for making a car-following target decision for an autonomous driving vehicle in a laneless environment, characterized in that: The method is applied to a road scene without lane markings; the forward direction of the autonomous driving vehicle is the positive direction of the x-axis, that is, the longitudinal direction, the longitudinal coordinate of the center of mass position of the autonomous driving vehicle is set to zero, and the transverse coordinate of the road centerline position is set to zero. The autonomous driving vehicle following target decision method includes the following steps: Step 1: Obtain driving behavior status information and surrounding environment information of a certain autonomous driving vehicle car at time t, wherein the driving behavior status information includes: the speed of the autonomous driving vehicle car , Vehicle width , Carriage Captain and the position coordinates of the vehicle, the surrounding environment information includes: the speed, width, length and position coordinates of all the vehicles ahead of the autonomous driving vehicle car; Step 2: Determine the observation zone DZ and risk zone RZ; Step 3: Determine whether there is a preceding vehicle in the risk zone RZ; if not, proceed to step 4; if yes, proceed to step 5; Step 4: Calculate the acceleration of the autonomous driving vehicle car at time t using the Free-IDM method shown in formula (3): Then, proceed to step 6; (3) In formula (3), is the maximum acceleration; is the expected speed; Step 5: Determine the following target of the autonomous vehicle car and calculate the acceleration at time t ; Step 6: After assigning t+1 to t, return to step 1 and execute sequentially until the autonomous driving vehicle car finishes driving.

2. The method for determining a target for an autonomous driving vehicle to follow a vehicle in a laneless environment according to claim 1, characterized in that: The step 2 comprises: Step 2.1, calculate the observation area DZ of the autonomous driving vehicle car according to formula (1); (1) In formula (1), is the longitudinal extent of the observation zone DZ; is the expected time interval; It is the comfortable acceleration; is the lateral extent of the observation zone DZ; is the lateral coordinate of the right edge of the road; is the horizontal coordinate of the left boundary of the road; Step 2.2: Number all the front vehicles in the observation area DZ of the autonomous driving vehicle car, and record any j-th front vehicle as ; Step 2.3, calculate the risk zone RZ of the autonomous driving vehicle car according to formula (2); (2) In formula (2), is the longitudinal extent of the risk zone RZ, is the lateral extent of the risk zone RZ, is the lateral position coordinate of the autonomous driving vehicle car at time t, For the front car The width of is the safety factor; is the minimum lateral safety clearance.

3. The method for determining a target for an autonomous driving vehicle to follow a vehicle in a laneless environment according to claim 2, characterized in that: The step 5 comprises: Step 5.1: Use formula (4) to determine the leading vehicle with the smallest longitudinal distance to the autonomous driving vehicle car in the risk zone RZ , and As the following target of the autonomous vehicle car; (4) In formula (4), It's the front car The vertical position coordinate at time t, It's the front car The horizontal position coordinates at time t; Step 5.2: Calculate the speed of the autonomous driving vehicle car in the following vehicle according to the SIDM method shown in formula (5). The acceleration at time t : (5) In formula (5), For acceleration strength, For the front car The vertical position at time t, For the front car The speed at time t, To be careful about following distance, For safe parking spacing; is the desired headway, and: (6)。 4. An electronic device, comprising a memory and a processor, characterized in that: The memory is used to store a program that supports the processor to execute the collaborative control method described in any one of claims 1 to 3, and the processor is configured to execute the program stored in the memory.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the following target decision method described in any one of claims 1 to 3 are executed.

Images