Autonomous driving methods, devices, electronic devices, storage media and vehicles

Abstract

This disclosure provides an autonomous driving method, device, electronic device, storage medium, and vehicle, relating to the field of artificial intelligence, and particularly to the field of autonomous driving technology. The specific implementation scheme is as follows: upon detecting a target obstacle that meets the overtaking conditions, a safety check is performed on overtaking; if the check indicates safe overtaking, overtaking is carried out on the target obstacle; if a risky obstacle hindering overtaking is encountered during the overtaking process, a driving decision is made, resulting in a driving decision outcome, including continuing overtaking or abandoning overtaking; based on the driving decision outcome, autonomous driving operations are executed. This disclosure selects the target obstacle based on overtaking conditions and improves the safety of the overtaking process by performing an overtaking safety check before overtaking. During the overtaking process, it can perceive risky obstacles and make autonomous decisions, providing overtaking safety guarantees throughout the entire process from before to the end of overtaking.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence, and in particular to the field of autonomous driving technology. Background Technology

[0002] Undoubtedly, autonomous driving has become a major disruptive innovation since the invention of the automobile. Its impact extends beyond the automotive industry, having a profound influence on social development and transportation systems.

[0003] As autonomous driving technology matures, autonomous vehicles are becoming increasingly common. When encountering moving obstacles ahead while driving on the road, autonomous vehicles typically choose to follow slowly rather than overtake, thus significantly reducing traffic efficiency. Summary of the Invention

[0004] This disclosure provides an autonomous driving method, apparatus, electronic device, storage medium, and vehicle.

[0005] According to a first aspect of this disclosure, an autonomous driving method is provided, comprising:

[0006] If a target obstacle that meets the overtaking conditions is detected, the overtaking safety is checked.

[0007] If the inspection results indicate that it is safe to overtake, then overtake the target obstacle.

[0008] When encountering a risky obstacle that hinders overtaking during the overtaking process, a driving decision is made and a driving decision result is obtained, which includes continuing to overtake or abandoning the overtaking;

[0009] Based on the driving decision results, execute autonomous driving operations.

[0010] According to a second aspect of this disclosure, an autonomous driving device is provided, comprising:

[0011] The detection module is used to check the overtaking safety when a target obstacle that meets the overtaking conditions is detected.

[0012] The overtaking module is used to overtake a target obstacle when the inspection results indicate that it is safe to overtake.

[0013] The decision-making module is used to make driving decisions when encountering risky obstacles that hinder overtaking during the overtaking process, and to obtain driving decision results, including continuing to overtake or abandoning overtaking.

[0014] The execution module is used to perform autonomous driving operations based on the driving decision results.

[0015] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0016] At least one processor; and

[0017] A memory that is communicatively connected to at least one processor; wherein,

[0018] The memory stores instructions that can be executed by at least one processor, such that the instructions are executed by at least one processor to enable the at least one processor to perform the method in the first aspect.

[0019] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause a computer to perform the methods of any of the above aspects.

[0020] According to a fifth aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method of the first aspect above.

[0021] According to a sixth aspect of this disclosure, a vehicle is provided, including the electronic equipment provided in the third aspect.

[0022] In this embodiment, the decision to overtake an obstacle is based on its motion state. This approach solves the problems of low traffic efficiency caused by unreasonable slow following and low safety caused by unreasonable overtaking of obstacles about to change direction. Furthermore, a safety check is performed when deciding whether to overtake, taking into account the safety of abandoning the overtaking maneuver if already in a position to do so. This effectively improves traffic efficiency while ensuring vehicle safety.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0024] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0025] Figure 1 This is a schematic flowchart of an autonomous driving method according to an embodiment of the present disclosure;

[0026] Figure 2 This is a schematic diagram of an autonomous driving method scenario according to an embodiment of the present disclosure;

[0027] Figure 3(a) is a schematic diagram of a scenario for lane safety detection according to an embodiment of the present disclosure;

[0028] Figure 3(b) is a schematic diagram of a scenario for lane safety detection according to another embodiment of the present disclosure;

[0029] Figure 4(a) is a schematic diagram of an autonomous driving overtaking scenario according to an embodiment of the present disclosure;

[0030] Figure 4(b) is a schematic diagram of an autonomous driving overtaking scenario according to another embodiment of the present disclosure;

[0031] Figure 4(c) is a schematic diagram of an autonomous driving overtaking scenario according to another embodiment of the present disclosure;

[0032] Figure 4(d) is a schematic diagram of an autonomous driving overtaking scenario according to another embodiment of the present disclosure;

[0033] Figure 5 This is a schematic diagram of a scenario for an autonomous driving method according to another embodiment of the present disclosure;

[0034] Figure 6 This is a schematic diagram of the overall process of an autonomous driving method according to an embodiment of the present disclosure;

[0035] Figure 7 This is a schematic diagram of the overall process of an autonomous driving method according to another embodiment of the present disclosure;

[0036] Figure 8 This is a schematic diagram of the structure of an autonomous driving device according to an embodiment of the present disclosure;

[0037] Figure 9 This is a schematic diagram of the structure of an autonomous driving device according to another embodiment of the present disclosure;

[0038] Figure 10 This is a block diagram of an electronic device used to implement the autonomous driving method of the embodiments of this disclosure. Detailed Implementation

[0039] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0040] The terms “first,” “second,” etc., used in this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion, such as including a series of steps or units. A method, system, product, or apparatus is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or apparatuses.

[0041] According to a first aspect of this disclosure, an autonomous driving method is provided, applicable to autonomous vehicles, wherein the vehicle performing the method is referred to as the master vehicle. Figure 1 As shown, the method includes:

[0042] S101, when a target obstacle that meets the overtaking conditions is detected, the overtaking safety is checked.

[0043] The overtaking conditions are based on overtaking safety measures and are used to select suitable target obstacles for overtaking. In some embodiments, the overtaking conditions may require the target obstacle to continuously meet at least one of the following conditions for a specified duration:

[0044] 1) The target obstacle is located in an overtaking section of the road;

[0045] In some embodiments, the overtaking sections are all sections where overtaking is permitted based on traffic rules.

[0046] In addition, to improve overtaking safety, in addition to road sections where overtaking is permitted by traffic rules, sections with good visibility, unobstructed road surfaces, and wide, straight roads can be further designated as the final overtaking sections. Sections with a high overtaking risk factor are designated as non-overtaking sections, such as curves, intersections, uphill sections, downhill sections, narrow bridges, and tunnels.

[0047] 2) The speed of the target obstacle is lower than the speed threshold and lower than the maximum speed limit of the road segment;

[0048] In some embodiments, the speed threshold can be dynamically determined based on the road segment speed limit and the speeds of surrounding vehicles. For example, such as Figure 2 As shown, the speed limit for this road segment is 80 km / h. The speed of the obstacle vehicle in front of the main vehicle is 20 km / h. The obstacle vehicle is surrounded by a first vehicle, a second vehicle, and a third vehicle. The first vehicle's speed is 60 km / h, the second vehicle's speed is 72 km / h, and the third vehicle's speed is 57 km / h. At this time, the average speed of the vehicles around the obstacle is 63 km / h, which can be used as a speed threshold. Since the obstacle vehicle's speed is significantly lower than this speed threshold and the local road segment speed limit, the obstacle vehicle meets condition 2). It should be noted that the description of vehicle speed and the number of vehicles in this embodiment is only for illustrative purposes and is not intended to limit the scope of this disclosure. Different speed thresholds can be set for different road segments during implementation.

[0049] 3) The target obstacle does not intend to change direction.

[0050] The presence of a target obstacle with a change of direction can pose a risk to overtaking. Therefore, in order to ensure overtaking safety, this embodiment of the present disclosure uses the presence of a change of direction as a reference condition.

[0051] In some embodiments, images of the target obstacle can be acquired, and the images can be analyzed to determine whether the target obstacle has its turn signal activated. If the target obstacle has its turn signal activated, it is determined that the target obstacle intends to change direction. If the target obstacle has not activated its turn signal, it is determined that the target obstacle does not intend to change direction.

[0052] Of course, in addition to analyzing turn signals from images, it's also possible to analyze the movement and posture of target obstacles, such as tire orientation and driver gestures.

[0053] In other embodiments, whether a target obstacle intends to change direction can also be determined based on the angle between the target obstacle's direction of movement and the centerline of the lane it occupies. For example, if the angle is less than a threshold, it is determined that the target obstacle does not intend to change direction. If the angle is greater than or equal to the threshold, it is determined that the target obstacle intends to change direction.

[0054] The included angle threshold can be set based on the road width and target obstacle information, including but not limited to the target obstacle length, target obstacle width, and target obstacle speed.

[0055] In this embodiment of the disclosure, the angle between the direction of movement of the target obstacle and the centerline of the lane can be used to accurately determine the direction change intention of the target obstacle.

[0056] 4) The target obstacle travels along the boundary of its lane;

[0057] In this embodiment of the disclosure, the condition that the target obstacle needs to travel along the boundary of its lane before overtaking is added, which can effectively avoid collisions and scrapes with the target obstacle during overtaking and improve the safety of overtaking.

[0058] In some embodiments, it can be determined whether a target obstacle travels along a boundary based on the following:

[0059] First, determine the distance between the centerline of the target obstacle and the centerline of the lane it is in; if the distance is greater than the preset distance, determine that the target obstacle is traveling along the boundary of the lane it is in; if the distance is not greater than the preset distance, determine that the target obstacle is not traveling along the boundary of the lane it is in.

[0060] The preset spacing can be determined based on empirical values ​​or based on the lane width. For example, the lane width can be multiplied by a preset coefficient to obtain the preset spacing. The preset coefficient has a value range of (0, 1) and can be flexibly determined according to the lane width.

[0061] In this embodiment, the distance between the centerline of the target obstacle and the centerline of the lane it occupies can accurately measure whether the target obstacle is driving close to the edge. Moreover, by adding the condition that the target obstacle needs to travel along the boundary of its lane before overtaking, collisions and scrapes with the target obstacle during overtaking can be minimized, thus improving safety during the overtaking process.

[0062] 5) The distance between the target obstacle and the preset road section exceeds the specified distance.

[0063] The preset road segments can include railway crossings, curves, intersections, uphill sections, downhill sections, narrow bridges, tunnels, and other sections where overtaking is not permitted. The specified distance can be changed based on the type of preset road segment; there is no limitation here. In one example, taking an intersection as an example, the specified distance can be set to 50m. If the target obstacle is outside the intersection within 50m, overtaking can be selected; if the target obstacle is within the intersection within 50m, overtaking should be abandoned.

[0064] In this embodiment of the disclosure, by setting distance requirements between the target obstacle and the preset road section, overtaking safety can be further improved.

[0065] 6) The distance between the target obstacle and the main vehicle is greater than the safe distance.

[0066] In some embodiments, the safe distance can be set based on the speed of the target obstacle and the surrounding environment. A safe distance refers to the necessary distance that a following vehicle maintains while driving to avoid an accidental collision with the vehicle in front. The surrounding environment includes, but is not limited to, weather conditions, light intensity, driver visibility, braking devices, road conditions, etc.

[0067] In this embodiment, by setting a safe distance between the main vehicle and the target obstacle, overtaking safety can be further guaranteed.

[0068] The embodiments disclosed herein are not limited to the overtaking conditions mentioned above. Any conditions that can filter out dynamic obstacles that are traveling at low speeds, driving close to the side of the road, and have no intention of changing direction are applicable to the embodiments disclosed herein.

[0069] Furthermore, in this embodiment of the disclosure, a specified duration is given for example, 3 seconds, but the specific duration can be set according to actual needs.

[0070] In summary, this embodiment determines whether to overtake an obstacle based on its state. This approach solves the problem of low traffic efficiency caused by slow following. When using a change-of-direction intention as an overtaking condition, it also addresses the low safety issue caused by overtaking obstacles about to change direction. The combined use of these conditions allows for a comprehensive assessment of whether an obstacle is safe to overtake from multiple perspectives, thus improving overtaking safety. Furthermore, requiring the target obstacle to continuously meet the overtaking conditions for a specified duration ensures that overtaking is permitted only with suitable selected obstacles, further enhancing overtaking safety.

[0071] The overtaking safety check is used to examine the surrounding environment of the main vehicle and determine whether it is safe to overtake a target obstacle. In some embodiments, the overtaking safety check may include a safety check of vehicles approaching from behind in the same lane. For example, the time headway (THW) method can be used to check vehicles approaching from behind. THW represents the time difference between the front ends of two vehicles passing the same point, and is generally calculated by dividing the distance between the front ends of the two vehicles by the speed of the following vehicle. In some embodiments, if the THW is less than a safety threshold for the following vehicle, the safety check for the following vehicle fails; if the THW is not less than the safety threshold, the safety check for the following vehicle passes. The aforementioned safety threshold for the following vehicle can be set based on road conditions, the speed of surrounding vehicles, and the length and width of surrounding vehicles. This threshold is used to detect the safe distance between vehicles. In this embodiment of the present disclosure, when the adjacent lane of the main vehicle is in the opposite direction of travel to the lane in which the main vehicle is located, when it is necessary to use the adjacent lane to overtake, the distance between the front and rear of the vehicles is the distance between the front of the main vehicle and the front of the vehicle coming from behind in the same lane. THW represents the distance between the front of the main vehicle and the front of the vehicle coming from behind in the same lane divided by the speed of the vehicle coming from behind.

[0072] When the main vehicle lane and the adjacent lane are traveling in the same direction, and the main vehicle needs to use the adjacent lane to overtake, the following vehicles that need to be detected can include vehicles behind the main vehicle in the same lane.

[0073] In some embodiments, checking overtaking safety may further include: conducting safety checks on vehicles in adjacent lanes. This safety check may also be based on the direction of travel of the adjacent lanes relative to the lane in which the main vehicle is located.

[0074] When the adjacent lane is traveling in the opposite direction to the lane occupied by the main vehicle, a safety check is performed on the vehicles in the adjacent lane, i.e., a safety check on oncoming vehicles. For example, a safety check on oncoming vehicles can be performed using the Time To Collision (TTC) function of a Forward Collision Warning (FCW) system. TTC is the distance between the front of the oncoming vehicle and the front of the main vehicle divided by the relative speeds of the two vehicles. In some embodiments, if the TTC is less than the safe distance between adjacent vehicles, the safety check on the oncoming vehicle fails; if the TTC is not less than the safe distance between adjacent vehicles, the safety check on the oncoming vehicle passes. The aforementioned safe distance between adjacent vehicles can be set based on road conditions, the speed of surrounding vehicles, and the length and width of surrounding vehicles. This threshold is used to detect the estimated time when a potential collision between the main vehicle and surrounding vehicles is possible.

[0075] When the adjacent lane is traveling in the same direction as the lane where the main vehicle is located, a safety check is performed on the vehicle ahead in the adjacent lane. For example, a safety check on the vehicle ahead can be performed using the Time To Collision (TTC) function of a Forward Collision Warning (FCW) system. TTC is the distance between the rear of the vehicle ahead and the front of the main vehicle divided by the relative speeds of the two vehicles.

[0076] When vehicles in adjacent lanes are traveling in the same direction as the vehicle in the lane where the driver is located, safety checks on vehicles in the adjacent lanes may also include safety checks on vehicles approaching from behind. For example, safety checks on vehicles approaching from behind can use the Time To Collision (TTC) function of a Forward Collision Warning (FCW) system. TTC is the distance between the front of the following vehicle and the rear of the driver vehicle divided by the relative speeds of the two vehicles.

[0077] In summary, the above-mentioned overtaking safety checks can be used to assess the safety of overtaking before it is possible to overtake, thereby improving overtaking safety.

[0078] S102, if the inspection result indicates that it is safe to overtake, overtake the target obstacle.

[0079] Among them, the overtaking path and overtaking speed can be planned based on the motion state of the target obstacle, and overtaking can be carried out based on the overtaking path and overtaking speed.

[0080] S103, when encountering a risky obstacle that hinders overtaking during the overtaking process, makes a driving decision and obtains a driving decision result, which includes continuing to overtake or abandoning the overtaking.

[0081] S104 executes autonomous driving operations based on driving decision results.

[0082] In this embodiment, a target obstacle that can be safely overtaken is selected based on overtaking conditions before overtaking, and an overtaking safety check is performed before overtaking, thus improving the safety of the overtaking process. During overtaking, the system can perceive risky obstacles and make autonomous decisions, which can improve the safety factor in actual overtaking. Therefore, various guarantees are provided for overtaking safety throughout the entire process from before to after overtaking, which can solve the problem of low traffic efficiency caused by slow following in related technologies, and can also avoid the problem of low safety caused by unreasonable overtaking as much as possible.

[0083] In some embodiments, in order to balance safety and traffic efficiency, driving decisions are made and driving decision results are obtained. This can be implemented as follows: when it is determined that continuing to overtake poses a collision risk and it is not safe to return to the original lane, the driving decision result is determined based on the motion state of the risk obstacle.

[0084] In this embodiment, a comprehensive assessment is made of the collision risk with the obstacle and the possibility of returning to the original lane, which is equivalent to achieving a safety detection for continuing the overtaking behavior. After obtaining the safety detection result, a driving decision is further made based on the movement state of the obstacle, which can accurately and reasonably obtain the driving decision result, effectively improving overtaking safety while also improving traffic efficiency.

[0085] In some embodiments, it is determined that it is safe to return to the original lane if the distance between the front side of the driver vehicle and the rear side of the target obstacle is greater than a first threshold and the distance between the rear side of the driver vehicle and the front side of the target obstacle is greater than a second threshold.

[0086] In practice, as shown in formula (1), the relative speed between the main vehicle and the target obstacle is the target obstacle speed (geo_car_v) minus the main vehicle speed (obs_v). The calculation methods for the first threshold d1 and the second threshold d2 are shown in formulas (2) and (3):

[0087] relative_v=ego_car_v-obs_v; (1)

[0088] d1=max(0,relative_v*t); (2)

[0089] d2=max(0,-relative_v*t); (3)

[0090] Where t is the duration. Based on the above formulas (1)-(3), the safe distance required for the main vehicle to return to the original lane can be obtained, namely d1 and d2 mentioned above.

[0091] In some embodiments, a distance range can be determined based on a first threshold d1 and a second threshold d2, which is the shaded area shown in Figure 3(a). When the main vehicle enters the shaded area (i.e., the distance between the front of the main vehicle and the rear of the target obstacle is not greater than the first threshold, and the distance between the rear of the main vehicle and the front of the target obstacle is not greater than the second threshold), the main vehicle is too close to the target obstacle, and it is determined that the main vehicle cannot safely return to its original lane; as shown in Figure 3(b), when the main vehicle is outside the shaded area (i.e., the distance between the front of the main vehicle and the rear of the target obstacle is greater than the first threshold, and the distance between the rear of the main vehicle and the front of the target obstacle is greater than the second threshold), it is determined that it can safely return to the main lane.

[0092] In summary, in this embodiment of the present disclosure, considering the situation where a risky obstacle is encountered while already in the overtaking state, a safety detection is performed to abandon the overtaking and return to the original lane. The detection based on the first threshold and the second threshold effectively improves the safety of returning to the original lane after abandoning the overtaking process.

[0093] In some embodiments, as shown in Figure 4(a), when the lane in which the main vehicle is located and the lane used for overtaking (hereinafter referred to as the overtaking lane) travel in the same direction, the risk obstacle can be a vehicle in front of the overtaking lane (vehicle 2 in Figure 4(a)) or a vehicle behind the main vehicle in the overtaking lane (vehicle 3 in Figure 4(b)). In practice, the risk obstacle can be determined based on the situation of the main vehicle (vehicle 1) encroaching on the overtaking lane. When the main vehicle encroaches on the overtaking lane beyond the encroachment threshold, vehicle 2 is considered a risk obstacle; when the main vehicle encroaches on the overtaking lane without exceeding the encroachment threshold, vehicle 3 can be considered a risk obstacle.

[0094] In some embodiments, when the driving lane of the main vehicle is traveling in the opposite direction to the lane used for overtaking (hereinafter referred to as the overtaking lane), the risk obstacle can be a vehicle traveling in the opposite direction in the overtaking lane (vehicle 4 in Figure 4(c)) or a vehicle behind the main vehicle in the overtaking lane (vehicle 5 in Figure 4(d)). In practice, the risk obstacle is determined based on the extent to which the main vehicle intrudes into the overtaking lane. When the main vehicle intrudes into the overtaking lane beyond the intrusion threshold, vehicle 4 is considered a risk obstacle; when the main vehicle intrudes into the overtaking lane without exceeding the intrusion threshold, vehicle 5 can be considered a risk obstacle.

[0095] For any risky obstacle, the collision time with the obstacle can be used to determine whether continuing to overtake poses a collision risk. For example, if the collision time with the obstacle is less than a first duration threshold, continuing to overtake is determined to pose a collision risk; if the collision time with the obstacle is not less than the first duration threshold, continuing to overtake is determined not to pose a collision risk.

[0096] The first duration threshold can be determined based on vehicle speed, the distance between the two vehicles, and road conditions. This embodiment does not limit its specific value. To ensure driving safety as much as possible, the first duration threshold can be set to a relatively large value.

[0097] In some embodiments, when encountering an oncoming vehicle during overtaking, collision time detection is performed with the oncoming vehicle. If the collision time with the oncoming vehicle is less than a first duration threshold, it is determined that there is a risk of collision if overtaking continues. If the collision time with the oncoming vehicle is not less than the first duration threshold, it is determined that there is no risk of collision if overtaking continues.

[0098] In some embodiments, when the main vehicle is traveling in the same direction as the risk obstacle, for example, if the risk obstacle is a vehicle ahead in an adjacent lane, the scenario diagram is as follows: Figure 5 As shown, when encountering sudden deceleration or braking by the vehicle ahead during overtaking, a collision time detection is performed. If the collision time with the vehicle ahead is less than a first time threshold, it is determined that continuing to overtake poses a collision risk; if the collision time with the vehicle ahead is not less than the first time threshold, it is determined that continuing to overtake poses no collision risk.

[0099] In this embodiment of the disclosure, collision risk can be accurately assessed based on collision time, so as to ensure driving safety.

[0100] In some embodiments, determining the driving decision based on the motion state of the risk obstacle can be implemented as follows: determining the time required for a collision with the risk obstacle based on the motion state of the risk obstacle; if the time is greater than a second time threshold, determining to accelerate and continue overtaking; if the time is not greater than the second time threshold, determining to decelerate and abandon overtaking.

[0101] In some embodiments, the second duration threshold may be determined based on vehicle speed, the distance between the two vehicles, and road conditions. This disclosure does not limit its specific value. To maximize driving safety, the second duration threshold may be set to a relatively large value.

[0102] In some embodiments, when the obstacle is an oncoming vehicle, collision time detection is performed. If the collision time with the oncoming vehicle exceeds a second duration threshold, it is determined that overtaking can be accelerated to improve traffic efficiency while ensuring safety. When accelerating to overtake, the overtaking route and speed are replanned to facilitate a safe overtaking maneuver. If the collision time with the oncoming vehicle does not exceed the second duration threshold, it is determined that continuing to overtake poses a collision risk. Therefore, the vehicle speed is reduced and a route back to the original lane is planned to ensure driving safety.

[0103] In some embodiments, when the main vehicle is traveling in the same direction as a potential obstacle, the potential obstacle is assumed to be a vehicle ahead in an adjacent lane. If, during overtaking, the vehicle ahead suddenly decelerates or brakes, a collision time detection is performed. If the collision time with the vehicle ahead exceeds a second time threshold, it is determined that continuing to overtake poses no collision risk, the vehicle speed is increased, and the overtaking route is replanned. If the collision time with the vehicle ahead does not exceed the second time threshold, it is determined that continuing to overtake poses a collision risk, the vehicle speed is reduced, and a route back to the original lane or following the vehicle ahead is planned to ensure driving safety.

[0104] In summary, in this embodiment of the present disclosure, a second duration threshold is set as a safety indicator to avoid collisions with risky obstacles during overtaking as much as possible. By comparing the collision time and the second duration threshold, driving decisions can be made accurately and reasonably, effectively improving the safety of the overtaking process while also taking into account traffic efficiency.

[0105] In some embodiments, making a driving decision and obtaining a driving decision result can also be implemented as follows: if it is determined that continuing to overtake poses a collision risk and it is safe to return to the original lane, decide to abandon overtaking; if it is determined that it is safe to continue overtaking, decide to continue overtaking.

[0106] In summary, when encountering a risky obstacle during overtaking, a safety check of returning to the original lane should be performed. If it is determined that it is safe to return to the original lane, the overtaking safety check can continue. If it is determined that continuing to overtake poses a collision risk, a route to return to the original lane should be planned, and a safety check of returning to the original lane should be performed in real time until the vehicle returns to the original lane and continues to follow the target obstacle. If it is determined that it is safe to return to the original lane and there is no collision risk of continuing to overtake, the overtaking route can be replanned, and driving decisions should be made in real time based on the surrounding situation until the overtaking is successful.

[0107] In summary, in this embodiment of the present disclosure, overtaking is carried out when it is determined that it is safe to continue overtaking; when overtaking is not possible, the main vehicle is ensured to return to its original lane, thereby improving both overtaking safety and traffic efficiency.

[0108] To further ensure driving safety, in this embodiment of the present disclosure, after making a driving decision, the system can return to the current state in real time during the execution of the driving decision until the vehicle successfully overtakes or returns to the original lane.

[0109] In some embodiments, the operation of making driving decisions in a loop can be terminated when there is an obstacle in front of the main vehicle that meets the overtaking conditions or when the target obstacle does not meet the overtaking conditions.

[0110] In summary, in this embodiment of the present disclosure, real-time detection allows for flexible driving decisions based on actual conditions, ensuring driving safety.

[0111] To facilitate a systematic understanding of the autonomous driving method provided in the embodiments of this disclosure, taking a risk obstacle as an oncoming vehicle, the lane where the driver is located as lane 1, the lane where the oncoming vehicle is located as lane 2, and lane 1 and lane 2 traveling in opposite directions as an example, the overall flowchart for overtaking is as follows: Figure 6 As shown:

[0112] S601, a target obstacle in front of the main vehicle that meets the conditions for overtaking has been detected;

[0113] S602, Overtaking safety is checked based on oncoming traffic in lane 2 and oncoming traffic in lane 1;

[0114] S603, If the check passes, proceed to step S604; if the check fails, return to step S601.

[0115] S604, planning overtaking routes and speeds;

[0116] S605, overtaking based on overtaking path and speed;

[0117] S606 If an oncoming vehicle appears in lane 2 during overtaking, a safety check will be performed to abandon the overtaking maneuver, i.e., to check whether it is safe to return to the original lane.

[0118] If you choose not to overtake safely and can safely return to your original lane, proceed to S608 or S609; if you fail the safety check, proceed to S612.

[0119] S608, stop overtaking, return to the original lane and continue following the target obstacle;

[0120] S609, if the distance of the main vehicle intruding into lane 2 is less than the threshold T, execute S610; if the distance of the intrusion into lane 2 is not less than the threshold T, execute S611.

[0121] S610, conduct a safety check, checking on oncoming and rear-approaching vehicles in lane 2; if the safety check passes, proceed to S604; if the safety check fails, proceed to S614.

[0122] It should be noted that step S610 may also omit the safety check of vehicles approaching from behind.

[0123] S611, Conduct a safety check to inspect vehicles traveling in the opposite direction in lane 2; if the safety check passes, proceed to S604; if the safety check fails, proceed to S614.

[0124] S612, determine TTC based on the speed of the oncoming vehicle and the distance to the oncoming vehicle;

[0125] S613, if TTC is less than the threshold t, execute S614; if TTC is not less than the threshold t, execute S615.

[0126] S614, reduce speed, wait for the opportunity to return to lane 1, and continue to follow the target obstacle vehicle;

[0127] S615, increase vehicle speed, plan overtaking route and overtaking speed, return to execute S605.

[0128] It should be noted that during the execution of S614 and S615, driving decisions can still be made based on the surrounding environment to ensure driving safety.

[0129] To facilitate a systematic understanding of the autonomous driving method provided in this disclosure, taking the obstacle as the vehicle ahead, the lane where the driver is located as lane 1, and the lane where the vehicle ahead is located as lane 2 as an example, and assuming that lane 1 and lane 2 travel in the same direction, the overall flowchart for overtaking is as follows: Figure 7 As shown:

[0130] S701, detected a target obstacle in front of the main vehicle that meets the conditions for overtaking;

[0131] S702, based on the vehicles in front of lane 2 and the vehicles behind lane 1, perform a safety check, and execute S703;

[0132] S703, If the check passes, proceed to step S704; if the check fails, return to step S701.

[0133] S704, planning overtaking routes and speeds;

[0134] S705, overtaking based on overtaking path and overtaking speed;

[0135] S706 If, during overtaking, a vehicle in lane 2 slows down or brakes, a safety check is performed to abandon the overtaking maneuver, i.e., to check whether it is safe to return to the original lane 1.

[0136] S707 If the overtaking safety check is passed, proceed to S708 or S709; if the overtaking safety check is failed, proceed to S711 or S712.

[0137] S708, stop overtaking and follow the target obstacle;

[0138] S709, if the distance of the intrusion into lane 2 is less than the threshold T, execute S710; if the distance of the intrusion into lane 2 is not less than the threshold T, execute S709.

[0139] S710, check the vehicles in front and behind in lane 2. If the safety check is passed, proceed to S704 to overtake; if the safety check is failed, proceed to S713.

[0140] S711, give up overtaking and follow the vehicle in front in lane 2;

[0141] S712, check the vehicle in front of lane 2. If the safety check passes, proceed to S704; if the safety check fails, proceed to S711.

[0142] S713, reduce speed and follow the target obstacle in return lane 1.

[0143] Similarly, during the process of slowing down to return to the original lane and accelerating to overtake, driving decisions are made cyclically based on the surrounding environment to improve driving safety.

[0144] Based on the same technical concept, and according to a second aspect of this disclosure, an autonomous driving device is provided, the structural diagram of which is shown below. Figure 8 As shown, it includes:

[0145] The detection module 801 is used to check the overtaking safety when a target obstacle that meets the overtaking conditions is detected.

[0146] The overtaking module 802 is used to overtake a target obstacle when the inspection result indicates that it is safe to overtake.

[0147] The decision module 803 is used to make driving decisions when encountering risky obstacles that hinder overtaking during the overtaking process, and to obtain driving decision results, including continuing to overtake or giving up overtaking.

[0148] The execution module 804 is used to perform autonomous driving operations based on the driving decision results.

[0149] In some embodiments, Figure 8 On the basis of, such as Figure 9 As shown, the decision module 803 includes: a first decision unit 8031, used to determine the driving decision result based on the motion state of the risk obstacle when it is determined that there is a risk of collision if overtaking is continued and it is not safe to return to the original lane.

[0150] In some embodiments, the first decision unit 8031 ​​is configured to: determine the duration required to collide with the risk obstacle based on the motion state of the risk obstacle; determine to accelerate and continue overtaking if the duration is greater than a second duration threshold; and determine to decelerate and abandon overtaking if the duration is not greater than the second duration threshold.

[0151] In some embodiments, the decision module 803 further includes:

[0152] The second decision unit 8032 is used to determine whether to abandon overtaking if it is determined that continuing to overtake poses a collision risk and that it is safe to return to the original lane.

[0153] The third decision unit 8033 is used to determine whether to continue overtaking if it is safe to do so.

[0154] In some embodiments, such as Figure 9 As shown, the autonomous driving device also includes:

[0155] The first safety inspection module 901 is used to determine that it is safe to return to the original lane when the distance between the front side of the main vehicle and the rear side of the target obstacle is greater than a first threshold and the distance between the rear side of the main vehicle and the front side of the target obstacle is greater than a second threshold.

[0156] The second safety inspection module 902 is used to determine the collision time with the risky obstacle; if the collision time with the risky obstacle is less than the first duration threshold, it is determined that there is a risk of collision if overtaking is continued.

[0157] In some embodiments, the decision module 803 is also used to perform driving decision operations based on the current state in real time until the vehicle successfully overtakes or returns to the original lane.

[0158] In some embodiments, the overtaking condition includes that the target obstacle continuously meets at least one of the following conditions for a specified duration:

[0159] The target obstacle is located in an overtaking section of the road;

[0160] The target obstacle's speed is below the speed threshold and below the maximum speed limit for the road segment.

[0161] The target obstacle showed no intention of changing direction;

[0162] The target obstacle travels along the boundary of its lane;

[0163] The distance between the target obstacle and the preset road segment exceeds the distance threshold;

[0164] The distance between the target obstacle and the main vehicle is greater than the safe distance.

[0165] In some embodiments, the above-mentioned autonomous driving device further includes:

[0166] The disguised intent determination module 903 is used to determine the angle between the direction of movement of the target obstacle and the center line of the lane it is in; if the angle is less than the angle threshold, it is determined that the target obstacle has no intention to change direction.

[0167] In some embodiments, the above-mentioned autonomous driving device further includes:

[0168] The boundary driving determination module 904 is used to determine the distance between the centerline of the target obstacle and the centerline of the lane it is in; if the distance is greater than the preset distance, it determines that the target obstacle is driving along the boundary of the lane it is in.

[0169] In some embodiments, the autonomous driving method proposed in this disclosure can be a vehicle equipped with autonomous driving capabilities. Target obstacles are selected based on overtaking conditions, and the safety of the overtaking process is ensured through an overtaking safety check. During the overtaking process, the vehicle can perceive risky obstacles and make autonomous decisions, ensuring safety throughout the entire process from before to after the overtaking maneuver.

[0170] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0171] Figure 10 A schematic block diagram of an example electronic device 1000 that can be used to implement embodiments of the present disclosure is shown. The electronic device 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 assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0172] like Figure 10 As shown, the electronic device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a random access memory (RAM) 1003. The RAM 1003 may also store various programs and data required for the operation of the electronic device 1000. The computing unit 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0173] Multiple components in electronic device 1000 are connected to I / O interface 1005, including: input unit 1006, such as keyboard, mouse, etc.; output unit 1007, such as various types of displays, speakers, etc.; storage unit 1008, such as disk, optical disk, etc.; and communication unit 1009, such as network card, modem, wireless transceiver, etc. Communication unit 1009 allows electronic device 1000 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0174] The computing unit 1001 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose 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 computing unit 1001 executes the autonomous driving method described above. In some embodiments, the autonomous driving method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1008. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 1000 via ROM 1002 and / or communication unit 1009. When the computer program is loaded into RAM 1003 and executed by the computing unit 1001, one or more steps of the autonomous driving method can be performed. Alternatively, in other embodiments, the computing unit 1001 can be configured to execute the autonomous driving method by any other suitable means (e.g., by means of firmware).

[0175] Based on the aforementioned electronic devices, this disclosure also provides an autonomous driving vehicle, which may include electronic devices, and may further include communication components, a display screen for implementing a human-machine interface, and information collection devices for collecting information about the surrounding environment, etc., wherein the communication components, display screen, information collection devices, and electronic devices are communicatively connected. The electronic devices included in the autonomous driving vehicle can execute the autonomous driving method provided in the embodiments of this disclosure.

[0176] According to embodiments of this disclosure, the electronic device can be integrated with the communication component, display screen, and information acquisition device, or it can be separately configured with the communication component, display screen, and information acquisition device.

[0177] Various embodiments of the systems and techniques described above 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), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0178] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This 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 when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0179] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0180] To provide automated driving with the user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide automated driving 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 sound input, voice input, or tactile input).

[0181] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact autonomously with the implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0182] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically communicate via a network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0183] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0184] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. An autonomous driving method, comprising: If a target obstacle that meets the overtaking conditions is detected, the overtaking safety is checked. If the inspection results indicate that it is safe to overtake, then overtake the target obstacle. When encountering a risky obstacle that hinders overtaking during the overtaking process, a driving decision is made and a driving decision result is obtained, which includes continuing to overtake or abandoning the overtaking; Based on the driving decision results, execute autonomous driving operations; based on the situation of the main vehicle intruding into the overtaking lane and the intrusion threshold, determine the risk obstacles in the overtaking lane; Specifically, if the main vehicle intrudes into the overtaking lane beyond the intrusion threshold, the vehicle in front of the main vehicle in the overtaking lane is considered a risk obstacle; if the main vehicle intrudes into the overtaking lane less than the intrusion threshold, the vehicle behind the main vehicle in the overtaking lane is considered a risk obstacle.

2. The method according to claim 1, wherein, The process of making driving decisions and obtaining driving decision results includes: If it is determined that continuing to overtake poses a collision risk, and it is determined based on the current vehicle speed that it is not safe to return to the original lane, the vehicle returns to the motion state based on the aforementioned risk obstacle, and determines the driving decision result.

3. The method according to claim 2, wherein, The process of determining the driving decision based on the motion state of the risk obstacle includes: Based on the motion state of the risk obstacle, determine the time required for a collision with the risk obstacle; If the duration exceeds the second duration threshold, determine to accelerate and continue overtaking; If the duration is not greater than the second duration threshold, determine to reduce speed and abandon overtaking.

4. The method according to claim 1, wherein, The process of making driving decisions and obtaining driving decision results includes: If it is determined that continuing to overtake poses a collision risk and it is safe to return to the original lane, then the decision is made to abandon the overtaking maneuver. If it is determined that it is safe to continue overtaking, then it is decided to continue overtaking.

5. The method according to any one of claims 2-4, further comprising determining whether it is safe to return to the original lane based on the following method: If the distance between the front of the main vehicle and the rear of the target obstacle is greater than a first threshold, and the distance between the rear of the main vehicle and the front of the target obstacle is greater than a second threshold, it is determined that it is safe to return to the original lane. in, The first threshold and the second threshold are determined based on the current vehicle speed.

6. The method according to any one of claims 2-4, further comprising determining a collision risk based on the following method: Determine the collision time with the aforementioned risky obstacle; If the collision time with the risky obstacle is less than a first duration threshold, it is determined that continuing to overtake poses a collision risk.

7. The method according to any one of claims 1-3, after making a driving decision and obtaining the driving decision result, further comprising: The system returns to the current state in real time to perform the driving decision-making operation until it successfully overtakes or returns to the original lane.

8. The method according to any one of claims 1-3, wherein, The overtaking conditions include that the target obstacle continuously meets at least one of the following conditions for a specified period of time: The target obstacle is located in an overtaking section of the road; The speed of the target obstacle is lower than the speed threshold and lower than the maximum speed limit of the road segment. The target obstacle showed no intention of changing direction; The target obstacle travels along the boundary of its lane; The distance between the target obstacle and the preset road section exceeds a distance threshold; The distance between the target obstacle and the main vehicle is greater than the safe distance.

9. The method of claim 8, further comprising determining, based on the following method, that the target obstacle has no intention to change direction: Determine the angle between the direction of movement of the target obstacle and the centerline of the lane it is in; If the included angle is less than the included angle threshold, it is determined that the target obstacle has no intention of changing direction.

10. The method of claim 8, further comprising determining, based on the following method, that the target obstacle travels along the boundary of the lane in which it is located; Determine the distance between the centerline of the target obstacle and the centerline of the lane in which it is located; If the distance is greater than the preset distance, it is determined that the target obstacle is traveling along the boundary of the lane it is in.

11. An autonomous driving device, comprising: The detection module is used to check the overtaking safety when a target obstacle that meets the overtaking conditions is detected. The overtaking module is used to overtake the target obstacle when the inspection result indicates that it is safe to overtake. The decision-making module is used to make driving decisions when encountering risky obstacles that hinder overtaking during the overtaking process, and to obtain driving decision results, including continuing to overtake or abandoning overtaking; An execution module is used to perform autonomous driving operations based on the driving decision results; Based on the situation of the main vehicle intruding into the overtaking lane and the intrusion threshold, the risky obstacles in the overtaking lane are identified; The decision module is used for: If the intrusion of the main vehicle into the overtaking lane exceeds the intrusion threshold, the vehicle in front of the main vehicle in the overtaking lane is considered a risk obstacle; if the intrusion of the main vehicle into the overtaking lane does not exceed the intrusion threshold, the vehicle behind the main vehicle in the overtaking lane is considered a risk obstacle.

12. The apparatus according to claim 11, wherein, The decision-making module includes: The first decision-making unit is used to determine the driving decision result when it is determined that there is a risk of collision if the vehicle continues to overtake, and it is determined that it is not safe to return to the original lane based on the current speed of the main vehicle.

13. The apparatus according to claim 12, wherein, The first decision unit is used for: Based on the motion state of the risk obstacle, determine the time required for a collision with the risk obstacle; If the duration exceeds the second duration threshold, determine to accelerate and continue overtaking; If the duration is not greater than the second duration threshold, determine to reduce speed and abandon overtaking.

14. The apparatus according to claim 11, wherein, The decision-making module includes: The second decision-making unit is used to decide to abandon overtaking if it is determined that continuing to overtake poses a collision risk and that it is safe to return to the original lane. The third decision-making unit is used to determine whether to continue overtaking if it is safe to do so.

15. The apparatus according to any one of claims 12-14, further comprising: The first safety check module is used to determine that it is safe to return to the original lane when the distance between the front side of the main vehicle and the rear side of the target obstacle is greater than a first threshold and the distance between the rear side of the main vehicle and the front side of the target obstacle is greater than a second threshold. The first threshold and the second threshold are determined based on the current vehicle speed.

16. The apparatus according to any one of claims 12-14, further comprising: The second safety inspection module is used to determine the collision time with the risky obstacle; If the collision time with the risky obstacle is less than a first duration threshold, it is determined that continuing to overtake poses a collision risk.

17. The apparatus according to any one of claims 12-14, wherein the decision module is further configured to return to the operation of making driving decisions in real time based on the current state until overtaking is successful or the vehicle returns to its original lane.

18. The apparatus according to any one of claims 11-14, wherein, The overtaking conditions include that the target obstacle continuously meets at least one of the following conditions for a specified period of time: The target obstacle is located in an overtaking section of the road; The speed of the target obstacle is lower than the speed threshold and lower than the maximum speed limit of the road segment. The target obstacle showed no intention of changing direction; The target obstacle travels along the boundary of its lane; The distance between the target obstacle and the preset road section exceeds a distance threshold; The distance between the target obstacle and the main vehicle is greater than the safe distance.

19. The apparatus of claim 18, further comprising: A disguised intent determination module is used to determine the angle between the movement direction of the target obstacle and the centerline of the lane in which it is located; If the included angle is less than the included angle threshold, it is determined that the target obstacle has no intention of changing direction.

20. The apparatus of claim 18, further comprising: The boundary driving determination module is used to determine the distance between the centerline of the target obstacle and the centerline of the lane in which it is located; If the distance is greater than the preset distance, it is determined that the target obstacle is traveling along the boundary of the lane it is in.

21. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method of any one of claims 1-10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-10.

23. A computer program product comprising a computer program that, when executed by a processor, implements the method of any one of claims 1-10.

24. A vehicle comprising the electronic equipment as claimed in claim 21.

Images