Vehicle obstacle avoidance decision determination method and device, equipment and medium

Abstract

The invention discloses a vehicle obstacle avoidance decision determination method and device, equipment and a medium. The method comprises the following steps: acquiring dynamic sensing environment information of a current vehicle and reference line information in a memory path; identifying static feature information of a driving road based on the reference line information, and judging whether obstacle information exists on the driving road based on the dynamic sensing environment information; if the obstacle information exists on the driving road, determining the safe vehicle width distance of the current vehicle based on the static feature information; and determining a vehicle obstacle avoidance decision according to the safe vehicle width distance, the static feature information and the obstacle information. According to the technical scheme, the corresponding vehicle obstacle avoidance decision is determined by combining the static characteristics and the dynamic sensing environment information, the safety of the vehicle obstacle avoidance decision is improved, and the reasonability of the vehicle obstacle avoidance decision is also ensured.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to a method, device, equipment and medium for determining a vehicle obstacle avoidance decision. Background Art

[0002] The rapid development of intelligent driving is an inevitable trend in the automotive industry. Memory parking has significantly improved the driving experience and is becoming increasingly popular. Memory parking is an optimization process based on automatic parking. The vehicle only needs to manually complete the operation of reaching the designated parking space once, and the operation is recorded. In subsequent driving, when the user activates the memory parking function, the vehicle will automatically start and park according to the user's preset route.

[0003] Current memory parking detour decisions are based solely on dynamically perceived environmental information. Obstacle avoidance decisions are made by assessing the passability of the channel and the reversibility of the obstacle after detours. However, dynamically perceived environmental information is unstable and prone to missing some information, resulting in irrational vehicle detour decisions. Summary of the Invention

[0004] The present invention provides a method, device, equipment and medium for determining vehicle obstacle avoidance decisions. By combining static features and dynamic perception environment information to determine the corresponding vehicle obstacle avoidance decisions, the safety of the vehicle obstacle avoidance decisions is improved and the rationality of the vehicle obstacle avoidance decisions is ensured.

[0005] According to one aspect of the present invention, a method for determining a vehicle obstacle avoidance decision is provided, comprising:

[0006] Obtain the current vehicle's dynamic perception environment information and the reference line information in the memory path;

[0007] identifying static feature information of a driving road based on the reference line information, and determining whether there is obstacle information on the driving road based on the dynamic perceived environment information;

[0008] If there is obstacle information on the driving road, determining a safe vehicle width distance of the current vehicle based on the static feature information;

[0009] A vehicle obstacle avoidance decision is determined based on the safe vehicle width distance, the static feature information, and the obstacle information.

[0010] According to another aspect of the present invention, a vehicle obstacle avoidance decision-making device is provided, comprising:

[0011] An acquisition module is used to obtain the dynamic perception environment information of the current vehicle and the reference line information in the memory path;

[0012] an identification module, configured to identify static feature information of a driving road based on the reference line information, and determine whether there is obstacle information on the driving road based on the dynamic perception environment information;

[0013] a distance determination module, configured to determine a safe vehicle width distance of the current vehicle based on the static feature information if there is obstacle information on the driving road;

[0014] The obstacle avoidance decision determination module is used to determine the vehicle obstacle avoidance decision based on the safe vehicle width distance, the static feature information and the obstacle information.

[0015] According to another aspect of the present invention, an electronic device is provided, comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the vehicle obstacle avoidance decision-making method described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the vehicle obstacle avoidance decision-making method described in any embodiment of the present invention when executed.

[0020] The technical solution of an embodiment of the present invention obtains the current vehicle's dynamic perception environment information and reference line information from a memorized path; identifies static feature information of the travel path based on the reference line information; and determines whether there is any obstacle information on the travel path based on the dynamic perception environment information; if there is any obstacle information on the travel path, determines the current vehicle's safe vehicle width distance based on the static feature information; and determines the vehicle's obstacle avoidance decision based on the safe vehicle width distance, the static feature information, and the obstacle information. This technical solution improves the safety and rationality of vehicle obstacle avoidance decisions by combining static features with dynamic perception environment information to determine the corresponding vehicle obstacle avoidance decisions.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 This is a flowchart of a vehicle obstacle avoidance decision-making method provided in accordance with the first embodiment of the present invention;

[0024] Figure 2 This is a flowchart of a vehicle obstacle avoidance decision-making method provided in accordance with a second embodiment of the present invention;

[0025] Figure 3 2 is a schematic structural diagram of a vehicle obstacle avoidance decision-making device provided according to a third embodiment of the present invention;

[0026] Figure 4 It is a structural diagram of an electronic device provided according to the fourth embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," and "target" in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or that are inherent to these processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1This is a flow chart of a vehicle obstacle avoidance decision determination method provided in accordance with a first embodiment of the present invention. This embodiment is applicable to the determination of vehicle obstacle avoidance when a vehicle has a memory path. The method can be executed by a vehicle obstacle avoidance decision determination device. The vehicle obstacle avoidance decision determination device can be implemented in the form of hardware and / or software. The vehicle obstacle avoidance decision determination device can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0031] S110: Acquire dynamic perception environment information of the current vehicle and reference line information in the memory path.

[0032] The current vehicle can be considered to be the vehicle currently traveling or the vehicle currently using the memory parking function. Dynamically perceived environmental information can be understood as information about the surrounding environment dynamically detected by the current vehicle. In this embodiment, the dynamic perceived environmental information of the current vehicle can refer to dynamic changes in the surrounding environment acquired in real time by the vehicle through various sensors, such as road conditions such as other vehicles, pedestrians, obstacles, and traffic signals. A memory path can refer to a previously learned or recorded driving path in the current vehicle. In this embodiment, the current vehicle can use the memory path function to record information about previously traveled paths. In this embodiment, when the user sets a path memory while driving, the system will record information such as landmarks and turning points along the way. When retracing the route, the system can simply call up the memory path and navigate to the same route. Reference line information can be understood as information such as lane markings, walls, and ground markings in the recorded memory path. Specifically, the reference line information in this embodiment can include reference line curvature information and reference line height information. In this embodiment, in the memory parking function, the reference line can be the path pre-recorded by the vehicle during the memory parking process. It is typically composed of a series of discrete coordinate points that describe the complete trajectory of the vehicle from the starting point to the parking space.

[0033] In this embodiment, the surrounding dynamic environment information detected in real time by the sensors in the current vehicle and the reference line curvature information and reference line height information contained in the pre-recorded memory path can be obtained.

[0034] S120: Identify static feature information of the driving road based on the reference line information, and determine whether there is obstacle information on the driving road based on the dynamic perception environment information.

[0035] Static feature information may refer to static feature information in static scenes on the road. In this embodiment, static feature information may include curve feature information and slope feature information. Obstacle information may refer to information about obstacles on the road that require avoidance. Obstacle information may be obtained by determining whether there are required obstacles based on set judgment conditions based on dynamically perceived environmental information. In this embodiment, obstacle information may refer to information about pedestrians, vehicles, and other obstacles.

[0036] In this embodiment, inference operations can be performed on static scenes on the road based on the vslam positioning reference line information, thereby determining corresponding static features in the static scene. In this embodiment, a specific method for identifying static feature information of the road based on the reference line information can be to analyze the reference line curvature information and height information to determine a static scene of a curve and a static scene of a slope, respectively. This allows the corresponding curve feature information to be determined based on the static scene of the curve, and the corresponding slope feature information to be determined based on the static scene of the slope.

[0037] In this embodiment, the specific method for determining whether there are obstacles on the road based on dynamic environmental information is to filter obstacles of interest near a reference line from the dynamic environmental information and use pre-set judgment conditions to determine whether there are obstacles that require avoidance. The pre-set judgment conditions in this embodiment may include: a. being within 15 meters in front of the vehicle; b. being less than a lateral safety threshold; c. being a static or slow-moving object. The lateral safety threshold can be pre-set based on actual needs.

[0038] It can be understood that in this embodiment, obstacles of interest near each reference line in the driving road can be screened based on dynamic perception environment information. If the screened obstacles of interest meet all the set judgment conditions, it can be determined that there is obstacle information on the driving road that needs to be avoided.

[0039] S130: If there is obstacle information on the driving road, determine the safe vehicle width distance of the current vehicle based on the static feature information.

[0040] The safe vehicle width distance refers to the safe lateral distance that should be maintained between the left and right sides of a vehicle and other vehicles, obstacles, or the road edge to ensure driving safety. It is understood that different vehicle models have different body widths, corresponding to different actual vehicle widths, and therefore different safe vehicle width distances. In this embodiment, the safe vehicle width distance can be determined based on the vehicle's width, information about obstacles in the road, and static feature information.

[0041] In this embodiment, if there are obstacles on the road, the vehicle width compensation calculation can be performed on the vehicle based on the detected static feature information to determine the corresponding compensated vehicle width distance, so that the determined supplementary vehicle width can be used as the safe vehicle width distance.

[0042] In addition, in this embodiment, when it is determined that there is an obstacle on the road but no corresponding static features are detected, the basic safe vehicle width distance of the vehicle can be determined. The specific determination process can be to add the actual vehicle width and the first safety threshold to obtain the safe vehicle width distance. The calculation formula of the basic safe vehicle width distance safe_dst can be:

[0043] safe_dst=car width+safe_buffer1;

[0044] Here, safe_buffer1 may be a first safety threshold; illustratively, the first safety threshold may be 15 cm.

[0045] S140: Determine a vehicle obstacle avoidance decision based on the safe vehicle width distance, static feature information, and obstacle information.

[0046] The vehicle obstacle avoidance decision may refer to a decision on whether the vehicle can avoid the obstacle. In this embodiment, the vehicle obstacle avoidance decision may include a decision to avoid the obstacle and a decision not to avoid the obstacle. It is understood that the decision not to avoid the obstacle is a decision to maintain the vehicle's original path or to stop driving.

[0047] In this embodiment, the vehicle's obstacle avoidance decision is determined by comprehensively considering whether road conditions are met based on the safe vehicle width distance, static feature information, and obstacle information. Specifically, in this embodiment, the vehicle's detour path boundary information is determined by dynamically sensing obstacle information. This detour boundary information is then compared with the safe vehicle width distance to determine whether the obstacle avoidance conditions are met. The vehicle's obstacle avoidance decision is then determined based on the constraints determined by the static feature information.

[0048] In this embodiment, the static feature information may include curve feature information and slope feature information; specifically, the curve feature information may include sharp bends and S-shaped bends within the curve feature information. Slope feature information may specifically include uphill and downhill slopes. Therefore, in this embodiment, the restriction conditions determined based on the static feature information may include prohibiting the vehicle from detouring if the vehicle is currently in an uphill or downhill scenario, and prohibiting the vehicle from detouring if the vehicle is currently in a sharp bend or S-shaped bend. For example, in this embodiment, if the current detour boundary information is determined to be greater than the safe vehicle width, it can be preliminarily determined that the obstacle avoidance condition is met. Furthermore, if static feature information such as uphill and downhill slopes, sharp bends, and S-shaped bends is present, the final obstacle avoidance decision for the vehicle can be determined to be not to detour. If the current detour boundary information is determined to be greater than the safe vehicle width, it can be preliminarily determined that the obstacle avoidance condition is met. Furthermore, if static feature information such as uphill and downhill slopes, sharp bends, and S-shaped bends is not present, the final obstacle avoidance decision for the vehicle can be determined to be to detour.

[0049] In this embodiment, by analyzing the reference lines obtained when memorizing the parking map, static road features are identified, such as calculating static scene reasoning information such as road curves and slopes. Combined with dynamically perceived obstacle information, the obstacle avoidance decision logic is optimized to achieve more flexible and safe obstacle avoidance decisions during memorized parking.

[0050] The technical solution of the embodiments of the present invention obtains the current vehicle's dynamic perception environment information and reference line information from a memorized path; identifies static feature information of the travel path based on the reference line information; and determines whether there are obstacles on the travel path based on the dynamic perception environment information; if there are obstacles on the travel path, determines the current vehicle's safe vehicle width distance based on the static feature information; and determines the vehicle's obstacle avoidance decision based on the safe vehicle width distance, static feature information, and obstacle information. This technical solution improves the safety and rationality of vehicle obstacle avoidance decisions by combining static features with dynamic perception environment information.

[0051] Example 2

[0052] Figure 2 This is a flow chart of a vehicle obstacle avoidance decision-making method provided in accordance with the second embodiment of the present invention. This embodiment is optimized based on the above embodiment. The specific optimization is as follows: static feature information includes curve features and ramp features; reference line information includes curvature information and height information; based on the reference line information, static feature information of the driving road is identified, including: obtaining the current vehicle speed and set time; determining the screening range of the reference line according to the speed and set time; within the screening range, determining the curve features and the distance between the current vehicle and the curve entrance according to the curvature information; within the screening range, determining the ramp features and the distance between the current vehicle and the ramp entrance according to the height information. Figure 2 As shown, the method includes:

[0053] S210: Acquire dynamic perception environment information of the current vehicle and reference line information in the memory path.

[0054] In this embodiment, the static feature information may include curve features and slope features; the reference line information includes curvature information and height information. The curvature information may refer to the reference line curvature information, and the height information may refer to the reference line height information.

[0055] S220: Obtain the current vehicle speed and set time.

[0056] The speed may be the current speed of the vehicle. The set time may be a pre-set time. In this embodiment, the corresponding time can be determined according to actual needs, ensuring that the vehicle can make advance predictions in various scenarios. In this embodiment, the current vehicle speed and the set time information can be directly obtained.

[0057] S230: Determine a screening range of the reference line according to the speed and the set time.

[0058] The screening range may refer to a range determined by screening the reference line. In this embodiment, the curve features and slope features of the driving road may be identified within the screening range determined by the reference line.

[0059] Because the reference line in the memory path is very long, it is not necessary to traverse the entire reference line information during road feature recognition. For example, when memorizing parking, the reference line may contain hundreds of meters of information. If the curve feature needs to be identified, the reference line can be filtered to a range of at least 20 meters. Therefore, inference can be performed based on the vehicle's speed and time. The inference range can be considered as the reference line filtering range, and the corresponding static features are determined within the inference range forward from the vehicle's current position.

[0060] In this embodiment, the Lookahead calculation formula for determining the screening range of the reference line based on the speed and the set time can be as follows:

[0061] Lookahead=max(20m, v ego *T);

[0062] Among them, v ego is the vehicle speed, and T is the inference time, which can be calibrated to ensure advance prediction in high-speed scenarios.

[0063] S240: Determine, within the screening range, the curve characteristics and the distance between the current vehicle and the curve entrance based on the curvature information.

[0064] The curve feature may refer to a specific curve type in a static curve scene. In this embodiment, the curve type may include left curves, right curves, and S-shaped curves, and may also include features such as sharp or gentle curves. The distance between the current vehicle and the curve entrance may refer to the distance from the current vehicle to the curve entrance.

[0065] In this embodiment, within a defined filtering range, the curve type (left, right, or S-curve) and the vehicle's current distance from the curve entrance can be identified based on the curvature of the reference line. Specifically, the corresponding coordinate information and curvature information from the reference line, as well as the index corresponding to the reference line, can be obtained. The starting point of the curve can be determined based on the curvature information and a set curvature threshold, thereby determining the curve type and the vehicle's current distance from the curve entrance.

[0066] In this embodiment, optionally, within the filtering range, the curve characteristics and the distance between the current vehicle and the curve entrance are determined based on the curvature information, including: traversing all curvature information within the filtering range, and taking multiple reference line position points whose curvature information is greater than the curvature threshold as multiple target position points; judging whether the multiple target position points meet the curve continuity condition; if the multiple target position points meet the curve continuity condition, determining the curve characteristics and the distance between the current vehicle and the curve entrance.

[0067] Among them, the curvature threshold can be a threshold set for the curvature information, which can be pre-set. Exemplarily, the curvature threshold in this embodiment can be 0.08. Multiple position points can be considered as position points where the reference line is located that is greater than the curvature threshold. The curve continuity condition can be used to determine whether there is specific continuity between multiple position points. In this embodiment, the curve continuity condition can be that the continuous range of multiple target position points exceeds a preset minimum curve length. Exemplarily, the minimum curve length in this embodiment can be 4 meters or 5 meters, which can be set according to actual conditions.

[0068] In this embodiment, it is first necessary to determine the index of the vehicle on the reference line. The nearest reference line position point can be found according to the position of the vehicle, and the reference line position point closest to the position of the vehicle is used as the position of the vehicle on the reference line; then, starting from vslam locating the position of the vehicle on the reference line, all reference line point sets within the curve screening range are traversed. The reference line point set includes multiple reference line position points, and there is curvature information between each reference line position point. Therefore, traversing all reference line point sets within the curve screening range can be considered as traversing all curvature information within the screening range. Multiple reference line position points whose curvature information is greater than the set curvature threshold can be used as multiple target position points to determine whether the multiple position points meet the curve continuity condition.

[0069] In this embodiment, the function of determining whether multiple location points satisfy the curve continuity condition is to determine the continuity between multiple target location points. Specifically, in this embodiment, the specific method for determining whether multiple target location points satisfy the curve continuity condition can be to determine whether the continuous range of the multiple target location points exceeds the preset minimum curve length; if the continuous range of the multiple target location points exceeds the preset minimum curve length, the multiple target location points can be considered to satisfy the curve continuity condition; if the continuous range of the multiple target location points does not exceed the preset minimum curve length, the multiple target location points can be considered to not satisfy the curve continuity condition. In this embodiment, when multiple target location points do not satisfy the curve continuity condition, the multiple target location points can be discarded.

[0070] In this embodiment, if multiple target locations meet the set curve continuity conditions, a static curve scene is considered to exist. The curve endpoint index is also recorded, and the curve characteristics of the static curve scene and the distance between the current vehicle and the curve entrance can be further determined. Specifically, in this embodiment, if a static curve scene is determined to exist, the curve is first determined to be an S-curve. If the curvature of the curve start point and the curve endpoint are opposite in sign, it indicates that the curve is an S-curve. If it is not an S-curve, the curve type is determined to be sharp or gentle based on the sharp curve threshold, thereby determining the corresponding curve type.

[0071] In this embodiment, after obtaining the curve type, the distance between the current vehicle and the curve entrance can be obtained by subtracting the distance between the determined curve starting point on the reference line and the current vehicle's position on the reference line. In this embodiment, the specific method for calculating the distance from the vehicle to the curve entrance distance2curve can be:

[0072] distance2curve=s curve_start -s ego ;

[0073] Among them, s curve-start is the distance s between the starting point of the curve and the reference line, s ego is the s distance matched by the ego-vehicle on the reference line.

[0074] Through such a setting in this embodiment, the curve characteristics (sharp bends / S-bends) in static curve scenarios can be pre-identified through the reference line information in the memory path, avoiding obstacle avoidance actions on driving sections with large curvature, and reducing the risk of collision caused by dynamic perception delay or misjudgment; and through curvature continuity analysis and S-bend detection (curvature positive and negative reversal judgment), complex curves (such as continuous S-bends) can be identified, thereby improving the reliability of curve feature detection.

[0075] S250: Within the screening range, determine ramp characteristics and the distance between the current vehicle and the ramp entrance based on the height information.

[0076] The ramp feature may refer to a specific ramp type in a static ramp scene. In this embodiment, the ramp type may include an uphill or downhill type. The distance between the current vehicle and the ramp entrance may refer to the distance between the current vehicle and the ramp entrance.

[0077] In this embodiment, within a defined screening range, the ramp type and the distance from the vehicle to the ramp entrance can be identified based on the change in reference line height. Specifically, this embodiment obtains the corresponding coordinate information and height information from the reference line information, as well as the index corresponding to the reference line. Based on the height information and the defined ramp determination criteria, the ramp starting point is determined, thereby determining the ramp type and the distance from the vehicle to the ramp entrance. The ramp determination criteria may include a ramp angle greater than a ramp threshold and passing a ramp continuity test.

[0078] In this embodiment, optionally, within the screening range, the ramp characteristics and the distance between the current vehicle and the ramp entrance are determined based on the height information, including: within the screening range, determining the slope angle between any adjacent reference lines based on the height information; when the slope angle is greater than or equal to the ramp threshold and the ramp continuity test is passed, determining the ramp characteristics and the distance between the current vehicle and the ramp entrance.

[0079] Among them, any adjacent reference lines can be any two adjacent reference lines within the screening range. The slope angle can be angle data determined based on the height information between the two adjacent reference lines. The ramp threshold can be a threshold set for the slope angle, which can be set according to actual needs. For example, the slope angle in this embodiment can be 0.05. The continuity test in this embodiment can be to test the ramp by setting a verification interval of the minimum ramp length.

[0080] In this embodiment, the elevation difference between any adjacent reference lines can be determined based on the height information within the screening range, and then the slope angle can be calculated based on the elevation difference. In this embodiment, the slope angle θ is calculated based on the elevation difference between adjacent reference line points. slope , the specific method can be:

[0081]

[0082] Among them, s i+1 It can refer to the distance corresponding to the index i+1 in the direction of the reference line; s i Refers to the distance corresponding to the index i in the direction of the reference line; z i+1 It can refer to the height information corresponding to the i+1 index on the reference line; z i It can refer to the height information corresponding to index i on the reference line.

[0083] In this embodiment, θ slope The ramp detection is triggered when the ramp threshold is greater than or equal to the ramp threshold. The index of the ramp starting point on the reference line is recorded, and then the continuity of the ramp is verified. The verification interval L of the minimum ramp length can be set. check , calculate the slope θ at the end point of the interval compared to the starting point of the ramp L , the specific method can be:

[0084]

[0085] Among them, s L It can refer to the distance of the corresponding reference line point with a length of L from the vehicle matching point; s start Refers to the distance corresponding to the determined index of the ramp starting point; z L It can be the height information of the corresponding reference line point with a length of L starting from the vehicle matching point; start It may refer to the height information corresponding to the determined ramp starting point index.

[0086] In this embodiment, if it is determined that θ slope >0&&0 L >0, indicating that there is a slope ahead, the corresponding slope feature is uphill and passes the continuity test; if it is judged that θ slope <0&&θ L <0 indicates that there is a slope ahead, and the corresponding slope feature is downhill and passes the continuity test.

[0087] In this embodiment, after determining whether the slope is uphill or downhill, the distance between the current vehicle and the ramp entrance can be obtained by subtracting the distance between the determined starting point of the ramp and the current vehicle's position on the reference line. In this embodiment, the specific method for calculating the distance from the vehicle to the starting point of the ramp, distance2slope, can be:

[0088] distance2slope=s slope_start -s ego ;

[0089] Among them, s slope_start is the distance s between the starting point of the ramp and the reference line, s ego is the s distance matched by the ego-vehicle on the reference line.

[0090] This configuration in this embodiment allows the system to pre-identify ramp characteristics (uphill or downhill) in static curve scenarios using reference line information from the memorized path, avoiding obstacle avoidance maneuvers on steep sections of road and reducing the risk of collisions caused by dynamic perception delays or misjudgments. Furthermore, consistency checks based on the minimum ramp length (dynamically adjusted with vehicle speed) and the direction of height change prevent misjudgment of temporary bumps as ramps, improving the accuracy of ramp feature detection.

[0091] S260: Determine whether there is any obstacle on the driving road based on the dynamic perception environment information.

[0092] S270: If there is obstacle information on the driving road, determine the safe vehicle width distance of the current vehicle based on the static feature information.

[0093] In this embodiment, optionally, the safe vehicle width distance of the current vehicle is determined based on the static feature information, including: when it is detected that the road curvature information in the static feature information is greater than the compensation threshold, determining the corresponding compensation vehicle width distance based on the curvature direction; determining the safe vehicle width distance according to the compensation vehicle width distance and the safety threshold; wherein the safety threshold is determined based on the static feature information.

[0094] Among them, the road curvature information may refer to the absolute value of the road curvature in a static scene, that is, the road curvature information when there are curve features or slope features. The compensation threshold may be a pre-set curvature compensation threshold. Exemplarily, the supplementary threshold in this embodiment may be 0.05. The compensated vehicle width distance may be the vehicle width distance calculated under curvature compensation. The safety threshold may be a pre-set threshold. In this embodiment, different safety thresholds may be determined based on the curve features in the static feature information. Specifically, in this embodiment, different safety thresholds may be set based on whether the curve features are sharp or gentle. In this embodiment, curvature compensation will be judged in a static scene, and the compensated vehicle width distance will be determined.

[0095] In this embodiment, when the absolute value of the road curvature detected in the static feature information is greater than the curvature compensation threshold, the curvature compensation is activated to calculate the safe vehicle width distance. The specific methods can be: a. Construct the vehicle envelope and calculate the four corner coordinates; b. Project the four corners of the vehicle onto the reference line coordinate system to obtain the SL coordinates; c. Calculate the compensated vehicle width distance safe according to the curvature direction. comp ;

[0096] In this embodiment, the specific method of calculating the compensation vehicle width distance based on the curvature method can be: when the curvature direction is left turn: safe comp =l fl -l rr ; It can be understood that when turning left, the left front corner and the right rear corner of the vehicle are the outermost points. When the curvature direction is turning right: safecomp =l fr -l rl It can be understood that when turning left, the right front corner and the left rear corner of the vehicle are the outermost points. fl is the projection coordinate of the left front corner of the vehicle, l rr is the projection coordinate of the right rear corner of the vehicle, l fr is the projection coordinate of the right front corner of the vehicle; l rl is the projection coordinate of the left rear corner of the vehicle.

[0097] In this embodiment, under curvature compensation, the safe vehicle width distance safe_dst is determined by the compensated vehicle width distance and the safety threshold, specifically:

[0098] safe_dst=safe comp +safe_buffer2;

[0099] Wherein, safe_buffer2 is a safety threshold value, which can be set according to actual needs. In this embodiment, safe_buffer2 is larger than safe_buffer1.

[0100] In this embodiment, through such a setting, the safe vehicle width distance is dynamically adjusted in combination with the curvature compensation amount (lateral buffer is increased in curves), ensuring that the actual distance between the vehicle envelope and the obstacle adapts to the changes in road geometry, effectively avoiding vehicle collisions.

[0101] S280: Determine a vehicle obstacle avoidance decision based on the safety vehicle width distance, static feature information, and obstacle information.

[0102] In this embodiment, optionally, a vehicle obstacle avoidance decision is determined based on the safe vehicle width distance, static feature information, and obstacle information, including: determining a bypass path boundary of the current vehicle based on the obstacle information; comparing the bypass path boundary with the safe vehicle width distance to obtain a comparison result; and determining a vehicle obstacle avoidance decision based on the comparison result and the static feature information.

[0103] The detour path boundary may refer to the path boundary of the current vehicle detouring around the obstacle area. The size of the detour path boundary may be obtained by performing a detailed calculation on the detour inner boundary and the detour outer boundary. In this embodiment, the detour inner boundary and the detour outer boundary may be determined based on the coordinate data of the obstacle information.

[0104] In this embodiment, the obstacle information can be obtained by traversing the real-time perception of obstacles based on the sl projection value of the reference line, and the update of the outer boundary l closest to the reference line is used. outer , calculate the l coordinate of the obstacle that needs to be avoided on the reference line as the inner boundary l of the detour inner, the detour path boundary size l of the current vehicle can be determined through =l outer -l inner . In this embodiment, the corresponding comparison result can be obtained by comparing the determined detour path boundary size of the current vehicle with the safe vehicle width distance. In this embodiment, if the detour path boundary size of the current vehicle is greater than the safe vehicle width distance, it can be considered that the detour path boundary of the current vehicle is passable. If the detour path boundary size of the current vehicle is less than or equal to the safe vehicle width distance, it can be considered that the detour path boundary of the current vehicle is not passable. Then, on the basis of determining whether the path is passable, corresponding restriction adjustments are made based on static feature information to determine the final vehicle obstacle avoidance decision.

[0105] In this embodiment, through such a setting, the processing of obstacles of interest is combined with static reasoning, which improves the success rate of obstacle avoidance path planning in complex scenarios such as narrow parking lots, thereby ensuring the reliability of vehicle obstacle avoidance decisions.

[0106] In this embodiment, optionally, a vehicle obstacle avoidance decision is determined based on the comparison result and the static feature information, including: if the bypass path boundary is greater than the safe vehicle width distance, determining the vehicle obstacle avoidance decision as a first pass obstacle avoidance decision; adjusting the first pass obstacle avoidance decision based on the static feature information to obtain a final vehicle obstacle avoidance decision.

[0107] The first obstacle avoidance decision may be considered as a decision that the current vehicle can travel through the bypass path to avoid the obstacle.

[0108] In this embodiment, by comparing the detour path boundary size l through The safe_dst distance from the safety car can be used to determine whether the passing conditions are met, thereby determining the first obstacle avoidance decision. through >safe_dst, indicating that the passable boundary can meet the obstacle avoidance conditions, that is, the vehicle obstacle avoidance decision can be determined as the first obstacle avoidance decision. through <=safe-dst, indicating that the passable boundary cannot meet the obstacle bypassing conditions.

[0109] In this embodiment, static scenario reasoning can be combined with the first pass obstacle avoidance decision to determine the final vehicle obstacle avoidance decision. The essence of adjusting the first pass obstacle avoidance decision based on static feature information in this embodiment is to determine whether the first obstacle avoidance decision can continue to pass based on the prohibition of detour restrictions corresponding to the static feature information, and then determine the final vehicle obstacle avoidance decision.

[0110] In this embodiment, the prohibition restriction corresponding to the static feature information may be adjusted to prohibit the vehicle from circumventing the obstacle when the vehicle is currently in an uphill or downhill scenario, a sharp curve scenario, or an S-curve scenario. In other words, the final vehicle obstacle avoidance decision may be a decision not to circumvent the obstacle. However, if the uphill or downhill scenario, sharp curve scenario, or S-curve scenario corresponding to the static feature information is not present, the final vehicle obstacle avoidance decision may be a decision to allow the vehicle to circumvent the obstacle.

[0111] Furthermore, the vehicle obstacle avoidance decision of this embodiment can prohibit detours in the following situations: a. the vehicle is currently in an uphill or downhill scenario, a sharp turn scenario, or an S-curve scenario; b. the boundary size of the detour path is smaller than the vehicle width; c. if an oncoming vehicle is detected on the detour side, detours on that side are prohibited.

[0112] In this embodiment, through such a setting, static scenes (such as sharp turns and ramps) and oncoming vehicle detection are introduced into the prohibited detour conditions, and high-risk scenes are avoided from multiple dimensions to avoid obstacles.

[0113] The technical solution of the embodiment of the present invention obtains the dynamic perception environment information of the current vehicle and the reference line information in the memory path; obtains the speed and set time of the current vehicle; determines the screening range of the reference line based on the speed and set time; within the screening range, determines the curve characteristics and the distance between the current vehicle and the curve entrance based on the curvature information; within the screening range, determines the slope characteristics and the distance between the current vehicle and the slope entrance based on the height information; determines whether there is obstacle information on the driving road based on the dynamic perception environment information; if there is obstacle information on the driving road, determines the safe vehicle width distance of the current vehicle based on the static feature information; and determines the vehicle obstacle avoidance decision based on the safe vehicle width distance, the static feature information, and the obstacle information. This technical solution improves the safety of the vehicle obstacle avoidance decision by combining static features with dynamic perception environment information to determine the corresponding vehicle obstacle avoidance decision. By reasoning about static scenes and determining the obstacle avoidance decision based on the corresponding static features, it avoids the defects and limitations of dynamic perception and improves the rationality of the vehicle obstacle avoidance decision.

[0114] Example 3

[0115] Figure 3 FIG. 1 is a schematic diagram of a vehicle obstacle avoidance decision-making device according to the third embodiment of the present invention. Figure 3 As shown, the device includes:

[0116] An acquisition module 310 is used to acquire the dynamic perception environment information of the current vehicle and the reference line information in the memory path;

[0117] The recognition module 320 is used to identify static feature information of the driving road based on the reference line information, and determine whether there is obstacle information on the driving road based on the dynamic perception environment information;

[0118] The distance determination module 330 is configured to determine the safe vehicle width distance of the current vehicle based on the static feature information if there is obstacle information on the driving road;

[0119] The obstacle avoidance decision determination module 340 is used to determine the vehicle obstacle avoidance decision based on the safe vehicle width distance, static feature information and obstacle information.

[0120] Optionally, the static feature information includes curve features and slope features; the reference line information includes curvature information and height information;

[0121] The identification module 320 includes:

[0122] A data acquisition unit, used to obtain the current vehicle speed and set time;

[0123] A screening range determining unit, for determining a screening range of a reference line according to a speed and a set time;

[0124] A curve feature determination unit, configured to determine the curve feature and the distance between the current vehicle and the curve entrance within the screening range based on the curvature information;

[0125] The ramp feature determination unit is used to determine the ramp feature and the distance between the current vehicle and the ramp entrance according to the height information within the screening range.

[0126] Optionally, the curve feature determination unit is specifically configured to:

[0127] Traverse all curvature information within the screening range, and use multiple reference line position points whose curvature information is greater than the curvature threshold as multiple target position points;

[0128] Determine whether multiple target position points meet the curve continuity condition;

[0129] If multiple target position points meet the curve continuity condition, the curve characteristics and the distance between the current vehicle and the curve entrance are determined.

[0130] Optionally, the ramp feature determination unit is specifically configured to:

[0131] Within the screening range, the slope angle between any adjacent reference lines is determined based on the height information;

[0132] When the slope angle is greater than or equal to the ramp threshold and the ramp continuity test is passed, the ramp characteristics and the distance between the current vehicle and the ramp entrance are determined.

[0133] Optionally, the distance determination module 330 is specifically configured to:

[0134] When it is detected that the road curvature information in the static feature information is greater than the compensation threshold, the corresponding compensation vehicle width distance is determined based on the curvature direction;

[0135] The safe vehicle width distance is determined according to the compensated vehicle width distance and a safety threshold; wherein the safety threshold is determined based on static feature information.

[0136] Optionally, the obstacle avoidance decision determination module 340 includes:

[0137] A boundary determination unit, configured to determine a detour path boundary of the current vehicle based on obstacle information;

[0138] a comparison unit, configured to compare the detour path boundary with the safety vehicle width distance to obtain a comparison result;

[0139] The decision determination unit is used to determine the vehicle obstacle avoidance decision based on the comparison result and static feature information.

[0140] Optionally, the decision-making unit is specifically used to:

[0141] If the detour path boundary is greater than the safe vehicle width, the vehicle's obstacle avoidance decision is determined to be the first obstacle avoidance decision;

[0142] The first obstacle avoidance decision is adjusted based on the static feature information to obtain the final vehicle obstacle avoidance decision.

[0143] A vehicle obstacle avoidance decision-making and determination device provided in an embodiment of the present invention can execute a vehicle obstacle avoidance decision-making and determination method provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects of the execution method.

[0144] Example 4

[0145] Figure 4 1 is a schematic diagram of the structure of an electronic device provided according to embodiment four of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0146] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0147] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0148] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the vehicle obstacle avoidance decision-making method.

[0149] In some embodiments, the vehicle obstacle avoidance decision-making method can be implemented as a computer program that is tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the vehicle obstacle avoidance decision-making method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to execute the vehicle obstacle avoidance decision-making method in any other appropriate manner (e.g., by means of firmware).

[0150] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0151] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0152] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0153] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0154] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, 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: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0155] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0156] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0157] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A vehicle obstacle avoidance decision-making method, characterized in that: include: Obtain the current vehicle's dynamic perception environment information and the reference line information in the memory path; identifying static feature information of a driving road based on the reference line information, and determining whether there is obstacle information on the driving road based on the dynamic perceived environment information; If there is obstacle information on the driving road, determining a safe vehicle width distance of the current vehicle based on the static feature information; A vehicle obstacle avoidance decision is determined based on the safe vehicle width distance, the static feature information, and the obstacle information.

2. The method according to claim 1, characterized in that The static feature information includes curve features and slope features; the reference line information includes curvature information and height information; The identifying static feature information of the driving road based on the reference line information includes: Get the current vehicle speed and set time; Determining a screening range of the reference line according to the speed and the set time; Within the screening range, determining curve characteristics and the distance between the current vehicle and the curve entrance according to the curvature information; Within the screening range, ramp characteristics and a distance between the current vehicle and the ramp entrance are determined according to the height information.

3. The method according to claim 2, characterized in that Determining the curve characteristics and the distance between the current vehicle and the curve entrance according to the curvature information within the screening range includes: Traversing all curvature information within the screening range, and taking multiple reference line position points whose curvature information is greater than a curvature threshold as multiple target position points; Determining whether the plurality of target position points meet a curve continuity condition; If the multiple target position points meet the curve continuity condition, the curve characteristics and the distance between the current vehicle and the curve entrance are determined.

4. The method according to claim 2, characterized in that Within the screening range, determining ramp characteristics and the distance between the current vehicle and the ramp entrance according to the height information includes: Determining the slope angle between any adjacent reference lines within the screening range based on the height information; When the slope angle is greater than or equal to the slope threshold and the slope continuity test is passed, the slope characteristics and the distance between the current vehicle and the slope entrance are determined.

5. The method according to claim 2, characterized in that Determining a safe vehicle width distance of the current vehicle based on the static feature information includes: When it is detected that the road curvature information in the static feature information is greater than a compensation threshold, determining a corresponding compensation vehicle width distance based on the curvature direction; A safe vehicle width distance is determined according to the compensated vehicle width distance and a safety threshold; wherein the safety threshold is determined based on the static feature information.

6. The method according to claim 1, characterized in that Determining a vehicle obstacle avoidance decision according to the safe vehicle width, the static feature information, and the obstacle information includes: Determining a detour path boundary of the current vehicle based on the obstacle information; Comparing the detour path boundary with the safety vehicle width distance to obtain a comparison result; A vehicle obstacle avoidance decision is determined based on the comparison result and the static feature information.

7. The method according to claim 6, characterized in that Determining a vehicle obstacle avoidance decision based on the comparison result and the static feature information includes: If the detour path boundary is greater than the safe vehicle width distance, determining the vehicle obstacle avoidance decision as the first pass obstacle avoidance decision; The first vehicle obstacle avoidance decision is adjusted based on the static feature information to obtain a final vehicle obstacle avoidance decision.

8. A vehicle obstacle avoidance decision-making device, characterized in that: include: An acquisition module is used to obtain the dynamic perception environment information of the current vehicle and the reference line information in the memory path; an identification module, configured to identify static feature information of a driving road based on the reference line information, and determine whether there is obstacle information on the driving road based on the dynamic perception environment information; a distance determination module, configured to determine a safe vehicle width distance of the current vehicle based on the static feature information if there is obstacle information on the driving road; The obstacle avoidance decision determination module is used to determine the vehicle obstacle avoidance decision based on the safe vehicle width distance, the static feature information and the obstacle information.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the vehicle obstacle avoidance decision-making method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the vehicle obstacle avoidance decision-making method according to any one of claims 1 to 7 when executed.

Images