Method and device for generating avoidance path

Abstract

The invention discloses a method and a device for generating an avoidance path, and relates to the technical field of intelligent driving, and the method comprises the steps: when an avoidance request initiated by a to-be-avoided vehicle is received, based on vehicle sensing data and to-be-avoided vehicle information carried by the avoidance request, determining the avoidance path of the to-be-avoided vehicle; determining a current traffic scene of a target vehicle in driving, determining a current traffic state of the target vehicle based on the vehicle sensing data, and if the current avoiding scene is a scene in which the target vehicle needs to avoid the to-be-avoided vehicle, adopting a preset path planning strategy to plan the to-be-avoided vehicle based on the current road scene of the target vehicle and the current traffic state. According to the vehicle avoidance path generation method and device, the technical problem that the vehicle avoidance efficiency is low due to the fact that the avoidance path cannot be accurately generated in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a method and device for generating an avoidance path. Background Art

[0002] With the rapid development of road traffic, the total number of existing cars has increased, and the road environment has become more complex, which not only increases the risk of traffic accidents, but also brings huge challenges to the rapid travel of vehicles to be avoided (i.e. emergency vehicles, such as ambulances and fire trucks). Every time a vehicle to be avoided performs a task, it must race against time. If other vehicles cannot avoid it in time, it may cause property damage or even threaten life safety. With the development of vehicle networking technology, autonomous driving has proposed vehicle-road collaborative autonomous driving based on single-vehicle intelligence. Through the deep integration of "people, vehicles, roads and clouds", it can achieve collaborative perception, collaborative decision-making planning and collaborative control with autonomous driving vehicles, which not only improves the safety of autonomous driving, but also overcomes the problem of avoiding vehicles to be avoided in various complex traffic environments.

[0003] In an intelligent connected environment based on C-V2X (Cellular Vehicle-to-Everything, a cellular-based vehicle wireless communication technology), related technologies mainly dispatch traffic resources through an intelligent transportation system to ensure that vehicles to be avoided have priority. Specific methods include: reserving lanes in advance, closing roads or switching traffic lights, etc., so as to plan the optimal driving path for the vehicles to be avoided and ensure that the vehicles to be avoided can reach their destination safely and efficiently.

[0004] However, the above method is mainly aimed at the scenario where all the vehicles around the vehicle to be avoided are intelligent networked vehicles, and does not consider the mixed vehicle scenario where the surrounding vehicles are intelligent networked vehicles and human-driven vehicles.

[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0006] The embodiment of the present invention provides a method and device for generating an avoidance path, so as to at least solve the technical problem in the related art that the avoidance path cannot be accurately generated, resulting in low vehicle avoidance efficiency.

[0007] According to one aspect of an embodiment of the present invention, a method for generating an avoidance path is provided, comprising: upon receiving an avoidance request initiated by a vehicle to be avoided, determining a current traffic scene of a driving target vehicle based on vehicle sensor data and information about the vehicle to be avoided carried in the avoidance request, wherein the vehicle sensor data is data information collected by sensors in the target vehicle; the current traffic scene includes at least: a current avoidance scene, a current road scene; the information about the vehicle to be avoided is information about a vehicle that meets preset conditions; based on the vehicle sensor data, determining a current traffic state of the target vehicle; if the current avoidance scene is a scene that requires the target vehicle to avoid the vehicle to be avoided, using a preset path planning strategy to generate an avoidance path for the target vehicle based on the current road scene and the current traffic state in which the target vehicle is located.

[0008] Furthermore, the vehicle sensor data includes at least: vehicle quantity information, vehicle speed information, vehicle braking information, and vehicle operation information. Before determining the current traffic status of the target vehicle based on the vehicle sensor data, it also includes: determining the number of vehicles in the current lane and the neighboring lane where the target vehicle is located based on the vehicle quantity information, wherein the neighboring lane is a lane connected to the current lane; determining the average speed of the leading vehicle based on the vehicle speed information, wherein the leading vehicle is a vehicle traveling in front of the target vehicle; determining the number of brakes of the leading vehicle within a first preset time based on the vehicle braking information; and determining the operating status and lane of the leading vehicle based on the vehicle operation information.

[0009] Furthermore, based on the vehicle sensor data, the step of determining the current traffic state of the target vehicle includes: when the number of vehicles is less than a preset number of vehicles, determining that the current traffic state is a first state; when the number of vehicles is greater than or equal to the preset number of vehicles and the average speed of the leading vehicle is greater than a preset speed threshold, determining that the current traffic state is a second state, wherein the congestion level of the target vehicle traveling in the second state is higher than the congestion level of traveling in the first state; when the number of vehicles is greater than or equal to the preset number of vehicles, the average speed of the leading vehicle is less than or equal to the preset speed threshold, the number of braking times is greater than a preset braking threshold, the operating state is a lane changing state, and the lane in which the vehicle is located is a variable lane, determining that the current traffic state is a third state, wherein the congestion level of the target vehicle traveling in the third state is higher than the congestion level of traveling in the second state.

[0010] Furthermore, before adopting a preset path planning strategy and generating an avoidance path for the target vehicle based on the current road scene and the current traffic status in which the target vehicle is located, it also includes: determining, based on the vehicle sensor data, a first-class lane in which no vehicle to be avoided is driven within a second preset time; determining, based on the navigation path, a driving direction of the target vehicle, and determining a lane with a lane direction indication consistent with the driving direction as a second-class lane; determining a set of neighbor lanes connected to the current lane of the target vehicle, and screening neighbor lanes whose lane lines indicating a lane change direction are dotted lines from the set of neighbor lanes, and determining the neighbor lanes as third-class lanes, wherein the lane change direction is the direction in which the target vehicle changes lanes; determining, based on the vehicle sensor data, the number of lane changes made by the target vehicle in each lane, and determining the lane with the least number of lane changes as a fourth-class lane.

[0011] Furthermore, a preset path planning strategy is adopted to generate an avoidance path for the target vehicle based on the current road scene and the current traffic state in which the target vehicle is located, including: based on the first type of lane, the second type of lane, the third type of lane and the fourth type of lane, a lane selection strategy is adopted to determine whether the target vehicle corresponds to a target lane; if the target vehicle corresponds to the target lane, based on the vehicle sensor data, whether the target vehicle meets the lane change condition during the process of driving to the target lane, wherein the lane change condition refers to the condition of having a lateral and longitudinal safety distance and a preset lane change space; if the target vehicle meets the lane change condition during the process of driving to the target lane, the target vehicle is controlled to driving to the target lane; if the target vehicle does not meet the lane change condition during its driving to the target lane, controlling the target vehicle to broadcast a cooperative lane change request, or controlling the target vehicle to determine an avoidance path for the target vehicle based on the current traffic status; if the target vehicle does not correspond to the target lane, determining whether the target vehicle corresponds to other driving lanes, and if the target vehicle corresponds to other driving lanes, controlling the target vehicle to drive to the other driving lanes; if the target vehicle does not correspond to other driving lanes, determining the avoidance method of the target vehicle based on the lane width of the current lane, and controlling the target vehicle to avoid based on the avoidance method.

[0012] Furthermore, the current traffic state includes: a first state, a second state, and a third state, and the step of controlling the target vehicle to determine the avoidance path of the target vehicle based on the current traffic state includes: when the current traffic state is the first state, controlling the target vehicle to leave the current lane until the lane change condition is met; when the current traffic state is the second state, determining a departure method based on the direction of the target lane, and controlling the target vehicle to leave the vehicle to be avoided in the departure method; when the current traffic state is the third state, controlling the target vehicle to park sideways.

[0013] Furthermore, after determining the current traffic scenario of the target vehicle in driving, it also includes: if the current avoidance scenario is a scenario that requires the target vehicle to cooperate with other vehicles to avoid, determining whether the target vehicle needs to change lanes to avoid, wherein the other vehicles are vehicles that need to directly avoid the vehicle to be avoided; when the target vehicle needs to change lanes to avoid, controlling the target vehicle to broadcast a lane change avoidance cooperation request, and when receiving a response request from the other vehicle, controlling the target vehicle to change lanes to avoid; when the response request from the other vehicle is not received, controlling the target vehicle to change lanes to avoid with a preset lane change strategy based on the vehicle sensor data.

[0014] Furthermore, after determining whether the target vehicle needs to change lanes to avoid, it also includes: if the target vehicle does not need to change lanes to avoid, determining whether the target vehicle has received a cooperative lane change request sent by the other vehicle; if the cooperative lane change request sent by the other vehicle is received, controlling the target vehicle to cooperate with the other vehicle to avoid; if the cooperative lane change request sent by the other vehicle is not received, determining whether to perform cooperative avoidance based on the vehicle sensor data and the information of the vehicle to be avoided.

[0015] Furthermore, after generating the avoidance path of the target vehicle, it also includes: judging whether the target vehicle successfully avoids the vehicle to be avoided, and updating the traffic status of the target vehicle when the target vehicle successfully avoids the vehicle to be avoided; obtaining the traffic restoration demand, and regenerating the path planning result based on the traffic restoration demand, the updated traffic status and the navigation path of the target vehicle.

[0016] According to another aspect of an embodiment of the present invention, a device for generating an avoidance path is also provided, including: a first determination unit, for determining, upon receiving an avoidance request initiated by a vehicle to be avoided, a current traffic scene of a driving target vehicle based on vehicle sensor data and information about the vehicle to be avoided carried in the avoidance request, wherein the vehicle sensor data is data information collected by sensors in the target vehicle; the current traffic scene includes at least: a current avoidance scene, a current road scene; the information about the vehicle to be avoided is information about a vehicle that meets preset conditions; a second determination unit, for determining a current traffic state of the target vehicle based on the vehicle sensor data; and a first generation unit, for generating an avoidance path for the target vehicle based on the current road scene and the current traffic state of the target vehicle, if the current avoidance scene is a scene in which the target vehicle is required to avoid the vehicle to be avoided.

[0017] Furthermore, the generating device includes: a first determination module, used to determine the number of vehicles in the current lane and the neighboring lane where the target vehicle is located based on the vehicle number information before determining the current traffic state of the target vehicle based on the vehicle sensor data, wherein the neighboring lane is a lane connected to the current lane; a second determination module, used to determine the average speed of the leading vehicle based on the vehicle speed information, wherein the leading vehicle is a vehicle traveling in front of the target vehicle; a third determination module, used to determine the number of brakes of the leading vehicle within a first preset time; and a fourth determination module, used to determine the operating state and lane of the leading vehicle based on the vehicle operating information.

[0018] Further, the second determination unit includes: a fifth determination module, which is used to determine that the current traffic state is a first state when the number of vehicles is less than a preset number of vehicles; a sixth determination module, which is used to determine that the current traffic state is a second state when the number of vehicles is greater than or equal to the preset number of vehicles and the average speed of the preceding vehicle is greater than a preset speed threshold, wherein the congestion level of the target vehicle traveling in the second state is higher than the congestion level of the target vehicle traveling in the first state; and a seventh determination module, which is used to determine that the current traffic state is a third state when the number of vehicles is greater than or equal to the preset number of vehicles, the average speed of the preceding vehicle is less than or equal to the preset speed threshold, the number of braking times is greater than a preset braking threshold, the operating state is a lane changing state, and the lane is a variable lane, wherein the congestion level of the target vehicle traveling in the third state is higher than the congestion level of the target vehicle traveling in the second state.

[0019] Furthermore, the generating device also includes: an eighth determination module, which is used to determine, based on the vehicle sensor data, a first-class lane in which no vehicle to be avoided is driven within a second preset time before generating the avoidance path of the target vehicle by adopting a preset path planning strategy based on the current road scene and the current traffic status in which the target vehicle is located; a ninth determination module, which is used to determine the driving direction of the target vehicle based on the navigation path, and determine the lane with a lane direction indication consistent with the driving direction as a second-class lane; a tenth determination module, which is used to determine a set of neighbor lanes connected to the current lane of the target vehicle, and filter out neighbor lanes whose lane lines indicating the lane change direction are dotted lines from the set of neighbor lanes, and determine the neighbor lanes as third-class lanes, wherein the lane change direction is the direction in which the target vehicle changes lanes; an eleventh determination module, which is used to determine the number of lane changes made by the target vehicle in each lane based on the vehicle sensor data, and determine the lane with the least number of lane changes as a fourth-class lane.

[0020] Furthermore, the second determination unit includes: a first judgment module, which is used to determine whether the target vehicle corresponds to a target lane by adopting a lane selection strategy based on the first type of lane, the second type of lane, the third type of lane and the fourth type of lane; a twelfth determination module, which is used to determine whether the target vehicle meets the lane change condition in the process of driving to the target lane based on the vehicle sensor data when the target vehicle corresponds to the target lane, wherein the lane change condition refers to the condition of having a lateral and longitudinal safety distance and a preset lane change space; a first control module, which is used to control the target vehicle to drive to the target lane when the target vehicle meets the lane change condition in the process of driving to the target lane; and a second control module, which is used to control the target vehicle to drive to the target lane when the target vehicle meets the lane change condition; If the lane change condition is not met during driving to the target lane, the target vehicle is controlled to broadcast a collaborative lane change request, or the target vehicle is controlled to determine an avoidance path for the target vehicle based on the current traffic status; a third control module is used to determine whether the target vehicle corresponds to other driving lanes if the target vehicle does not have the corresponding target lane, and control the target vehicle to drive to the other driving lane if the target vehicle corresponds to the other driving lane; a fourth control module is used to determine the avoidance method of the target vehicle based on the lane width of the current lane if the target vehicle does not have the corresponding other driving lane, and control the target vehicle to avoid based on the avoidance method.

[0021] Furthermore, the second determination unit also includes: a fifth control module, which is used to control the target vehicle to leave the current lane until the lane change condition is met when the current traffic state is the first state; a sixth control module, which is used to determine the departure method based on the direction of the target lane when the current traffic state is the second state, and control the target vehicle to leave the vehicle to be avoided in the departure method when the current traffic state is the third state; and a seventh control module, which is used to control the target vehicle to park sideways when the current traffic state is the third state.

[0022] Furthermore, the generating device also includes: a second judgment module, which is used to determine whether the target vehicle needs to change lanes to avoid after determining the current traffic scene of the driving target vehicle, if the current avoidance scene is a scene that requires the target vehicle to cooperate with other vehicles to avoid, wherein the other vehicles are vehicles that need to directly avoid the vehicle to be avoided; an eighth control module, which is used to control the target vehicle to broadcast a lane change avoidance cooperation request when the target vehicle needs to change lanes to avoid, and control the target vehicle to change lanes to avoid when a response request from the other vehicle is received; a ninth control module, which is used to control the target vehicle to change lanes to avoid based on the vehicle sensor data when the response request from the other vehicle is not received.

[0023] Furthermore, the generating device also includes: a third judgment module, which is used to judge whether the target vehicle receives the cooperative lane change request sent by the other vehicle after judging whether the target vehicle needs to change lanes to avoid, if the target vehicle does not need to change lanes to avoid; a tenth control module, which is used to control the target vehicle to cooperate with the other vehicle to avoid, if the cooperative lane change request sent by the other vehicle is received; and a fourth judgment module, which is used to judge whether to perform cooperative avoidance based on the vehicle sensor data and the information of the vehicle to be avoided, if the cooperative lane change request sent by the other vehicle is not received.

[0024] Furthermore, the generating device also includes: a first updating module, which is used to determine whether the target vehicle successfully avoids the vehicle to be avoided after generating the avoidance path of the target vehicle, and to update the traffic status of the target vehicle when the target vehicle successfully avoids the vehicle to be avoided; a first generating module, which is used to obtain the traffic restoration demand, and regenerate the path planning result based on the traffic restoration demand, the updated traffic status and the navigation path of the target vehicle.

[0025] In the present invention, when an avoidance request initiated by a vehicle to be avoided is received, the current traffic scenario of the driving target vehicle is determined based on vehicle sensor data and the information of the vehicle to be avoided carried in the avoidance request, and the current traffic status of the target vehicle is determined based on the vehicle sensor data. If the current avoidance scenario is a scenario in which the target vehicle needs to avoid the vehicle to be avoided, a preset path planning strategy is adopted to generate an avoidance path for the target vehicle based on the current road scenario and the current traffic status of the target vehicle, thereby solving the technical problem in the related art that the avoidance path cannot be accurately generated, resulting in low vehicle avoidance efficiency.

[0026] In the present invention, after the target vehicle in driving receives the avoidance request initiated by the vehicle to be avoided, the current traffic scene where the target vehicle is located can be determined based on the vehicle sensing data collected by its sensor and the information of the vehicle to be avoided carried in the avoidance request, and then the current traffic state where the target vehicle is located can be determined based on the vehicle sensing data. If the target vehicle is required to avoid the scene of the vehicle to be avoided, the avoidance path of the target vehicle can be generated based on the current road scene and the current traffic state where the target vehicle is located. In this way, an accurate avoidance path can be generated, and the vehicle avoidance action can be efficiently completed according to the avoidance path, thereby achieving the technical effect of improving the avoidance efficiency of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0028] Figure 1 is a flow chart of an optional method for generating an avoidance path according to an embodiment of the present invention;

[0029] Figure 2 is a schematic diagram of an optional lane change avoidance path generation according to an embodiment of the present invention;

[0030] Figure 3 is a schematic diagram of an optional mixed traffic flow avoidance process according to an embodiment of the present invention;

[0031] Figure 4 is a schematic diagram of an optional road traffic restoration process according to an embodiment of the present invention;

[0032] Figure 5 is a schematic diagram of an optional avoidance working principle according to an embodiment of the present invention;

[0033] Figure 6 is a schematic diagram of an optional avoidance path generation device according to an embodiment of the present invention;

[0034] Figure 7 The present invention is a hardware structure block diagram of an electronic device (or mobile device) for generating an avoidance path according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 described embodiments 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 creative work should fall within the scope of protection of the present invention.

[0036] It should be noted that the terms "first", "second", etc. 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 data used in this way can be interchanged 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 device 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 inherent to these processes, methods, products or devices.

[0037] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) collected and involved in the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with the relevant laws, regulations and standards of the relevant regions, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set between the system and the relevant users or organizations. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0038] In the present invention, a C-V2X-based emergency vehicle avoidance method in mixed traffic flow is proposed. By acquiring the information of the vehicle to be avoided and the vehicle sensor data, the traffic state of the target vehicle can be obtained, and the road scene of the target vehicle can be judged. Then, an avoidance path can be generated according to the road scene of the target vehicle and the traffic state of the target vehicle. The present invention is not only applicable to the scenario where the target vehicle is surrounded by all intelligent networked autonomous driving vehicles, but also to the scenario where the target vehicle is surrounded by a mixed traffic flow consisting of intelligent networked autonomous driving vehicles and human-driven vehicles. The emergency vehicle avoidance method in mixed traffic flow can not only improve the traffic efficiency of the vehicles to be avoided in mixed traffic scenarios, but also quickly restore road traffic after the vehicles to be avoided successfully pass, thereby improving the traffic efficiency and safety of the target vehicles and the road as a whole.

[0039] The present invention is described in detail below in conjunction with various embodiments.

[0040] Embodiment 1

[0041] According to an embodiment of the present invention, an embodiment of a method for generating an avoidance path is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0042] Figure 1 is a flow chart of an optional method for generating an avoidance path according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0043] Step S101, upon receiving an avoidance request initiated by a vehicle to be avoided, determining the current traffic scene of the target vehicle in driving based on vehicle sensor data and the vehicle to be avoided information carried in the avoidance request, wherein the vehicle sensor data is data information collected by sensors in the target vehicle; the current traffic scene includes at least: a current avoidance scene, a current road scene; and the vehicle to be avoided information is information of vehicles that meet preset conditions.

[0044] Optionally, the vehicle to be avoided (such as an ambulance, fire truck, police car, etc.) can send an avoidance request to surrounding vehicles or a roadside unit RSU (Road Side Unit, a communication device installed next to the road) through an on-board unit OBU (On Board Unit, a communication device installed on the vehicle). The avoidance request carries information about the vehicle to be avoided (the information about the vehicle to be avoided is information about an emergency vehicle that meets preset conditions (i.e., is performing an emergency task (such as firefighting and rescue, etc.)), including but not limited to: the body size, position, speed, driving path, etc. of the vehicle to be avoided).

[0045] In this embodiment, the target vehicle (i.e., the vehicle itself) in driving can receive an avoidance request sent by the vehicle to be avoided through the on-board unit OBU or an avoidance request sent by the roadside unit RSU through the on-board unit OBU, and then determine the current traffic scene in which the target vehicle is located based on the vehicle sensor data (i.e., the data information collected by the sensors (such as cameras, radars, etc.) in the target vehicle) and the information of the vehicle to be avoided in the avoidance request sent by the vehicle to be avoided.

[0046] In this embodiment, the current traffic scene includes at least: a current avoidance scene and a current road scene, wherein the current avoidance scene may include a direct avoidance scene and a coordinated avoidance scene, and the current road scene may include a multi-lane road scene and a single-lane road scene, etc.

[0047] In this embodiment, the vehicle sensor data includes but is not limited to: vehicle quantity information, vehicle speed information, vehicle braking information, vehicle operation information, lane information, surrounding environment information, etc.

[0048] Step S102, determining the current traffic state of the target vehicle based on the vehicle sensor data.

[0049] Optionally, the vehicle sensor data can be data collected by various sensors on the target vehicle to reflect the vehicle status and surrounding environment. The current traffic status of the target vehicle (i.e., the current road traffic operation status, such as smooth, slow, congested, etc.) can be determined based on the data information collected by the sensors in the target vehicle (such as vehicle quantity information, vehicle speed information, vehicle braking information, vehicle operation information, etc.).

[0050] In some optional embodiments, the traffic state of the vehicle, such as free flow, stable flow or congested flow, can be obtained through big data calculation based on various types of collected sensor data (i.e., vehicle sensor data).

[0051] Step S103, if the current avoidance scenario is a scenario where the target vehicle needs to avoid the vehicle to be avoided, a preset path planning strategy is adopted to generate an avoidance path for the target vehicle based on the current road scenario and current traffic conditions where the target vehicle is located.

[0052] Optionally, when the current avoidance scenario is a scenario in which the target vehicle needs to avoid the vehicle to be avoided (i.e., a direct avoidance scenario), a preset path planning strategy can be adopted (i.e., a pre-set path planning strategy, such as first determining the target lane, then determining whether the lane change conditions are met, and then planning an avoidance path based on the target lane and the lane change conditions), and then generating an avoidance path for the target vehicle based on the current road scene and current traffic conditions in which the target vehicle is located.

[0053] In this embodiment, the target lane is the final lane that the target vehicle needs to travel in order to avoid the vehicle to be avoided, and the lane change condition is the conditions and standards that need to be met when changing lanes in the process of avoiding the vehicle to be avoided, which can ensure the safety and compliance of the lane change behavior.

[0054] In summary, the current traffic scenario of the target vehicle can be determined based on the avoidance request initiated by the vehicle to be avoided and the sensor data information of the target vehicle. Then, the current traffic status of the target vehicle can be determined based on the sensor data of the target vehicle. When the current avoidance scenario requires the target vehicle to avoid the vehicle to be avoided, a preset path planning strategy is adopted, and an avoidance path for the target vehicle can be generated based on the current road scenario and the current traffic status of the target vehicle. This enables the target vehicle to efficiently avoid the vehicle to be avoided, thereby solving the technical problem in the related technology that the avoidance path cannot be accurately generated, resulting in low vehicle avoidance efficiency.

[0055] In order to determine the traffic status of the vehicle in real time, it is necessary to first determine the information of other vehicles around the vehicle. In the method for generating the avoidance path provided in Example 1 of the present application, based on the vehicle quantity information, the number of vehicles in the current lane and the neighboring lane where the target vehicle is located is determined, wherein the neighboring lane is a lane connected to the current lane; based on the vehicle speed information, the average speed of the leading vehicle is determined, wherein the leading vehicle is the vehicle traveling in front of the target vehicle; based on the vehicle braking information, the number of brakes of the leading vehicle within the first preset time is determined; based on the vehicle operation information, the operation status and lane of the leading vehicle are determined.

[0056] Optionally, the sensor in the target vehicle can collect information (such as the number of vehicles, vehicle position, vehicle speed, vehicle running status, etc.) of other vehicles within its sensing range (i.e., the range in which the sensor can collect data). Then, it can be judged whether there are other vehicles within the sensing range and whether there are other vehicles in the lane (i.e., the current lane where the target vehicle is located) and the lane next to it (i.e., the neighbor lane) within the sensing range according to the collected data, specifically: the number of vehicles in the current lane where the target vehicle is located and the number of vehicles in the neighbor lane connected to the current lane can be determined according to the number of vehicles, so as to judge whether there are other vehicles around the target vehicle according to the number of vehicles. In addition, the average speed of the vehicle in front of the target vehicle (i.e., the vehicle traveling in front of the target vehicle) can be determined according to the vehicle speed information collected by the sensor in the target vehicle, such as, the vehicle sensor continuously collects the vehicle speed within a period of time (such as 20s), and then calculates the average speed of the vehicle in front of the vehicle within the 20s, so as to judge whether the speed of the vehicle in front of the target vehicle exceeds the preset speed threshold (such as 30km / h) according to the average speed. The number of braking times of the preceding vehicle within the first preset time (pre-set collection time, such as 20s) can also be determined based on the vehicle braking information, so that it can be judged whether the braking frequency of the preceding vehicle of the target vehicle exceeds the preset braking threshold (such as the preceding vehicle braking twice within 20s) based on the number of braking times. The running state of the preceding vehicle (such as the straight-ahead state (i.e., the vehicle does not turn on any turn signal), the lane change state (i.e., the vehicle turns on the left turn signal or the right turn signal) and the lane it is in can also be determined based on the vehicle running information, so that it can be judged whether the preceding vehicle of the target vehicle has the intention to change lanes and has been in the lane change area). In this way, the current traffic state of the target vehicle can be quickly determined based on the other vehicle information obtained by the above calculation (including: the number of vehicles within the perception range, the average speed, braking times, running state and lane of the preceding vehicle).

[0057] In order to accurately determine the current traffic state, in the avoidance path generation method provided in Example 1 of the present application, when the number of vehicles is less than a preset number of vehicles, the current traffic state is determined to be a first state; when the number of vehicles is greater than or equal to the preset number of vehicles and the average speed of the preceding vehicle is greater than a preset speed threshold, the current traffic state is determined to be a second state, wherein the congestion level of the target vehicle in the second state is higher than the congestion level of the target vehicle in the first state; when the number of vehicles is greater than or equal to the preset number of vehicles, the average speed of the preceding vehicle is less than or equal to the preset speed threshold, the number of braking times is greater than the preset braking threshold, the operating state is a lane changing state, and the lane is a variable lane, the current traffic state is determined to be a third state, wherein the congestion level of the target vehicle in the third state is higher than the congestion level of the target vehicle in the second state.

[0058] Optionally, the preset number of vehicles is a pre-set number of vehicles (such as 1 vehicle). When the number of vehicles collected by the sensor of the target vehicle is less than the preset number of vehicles, it indicates that the current traffic condition is that the vehicle can travel freely and smoothly, and the current traffic state can be determined as the first state (i.e., free state); when the number of vehicles collected by the sensor in the target vehicle is greater than or equal to the preset number of vehicles, and the average speed of the preceding vehicle is greater than a preset speed threshold (such as 30 km / h (kilometers per hour, i.e., speed unit)), it indicates that the current traffic condition is that the vehicle needs to travel smoothly, and the current traffic state can be determined as the second state (i.e., stable state); when the number of vehicles is greater than or equal to the preset number of vehicles, the average speed of the preceding vehicle is less than or equal to the preset speed threshold, the number of braking times is greater than the preset braking threshold (such as 2 times), the operating state is the lane change state (i.e., the turn signal is turned on), and the lane is a variable lane (i.e., the lane boundary line is a dotted line), it indicates that the current traffic condition is in a congested state, the vehicle needs to travel slowly, and the current traffic state can be determined as the third state (i.e., congested state).

[0059] In this embodiment, the first state can be a state in which there are no other vehicles within the range collected by the target vehicle sensor, the second state can be a state in which there are other vehicles within the range collected by the target vehicle sensor, but the average speed of other vehicles within 20 seconds is greater than 30 km / h, and the third state can be a state in which there are other vehicles within the range collected by the target vehicle sensor, but the average speed of other vehicles within 20 seconds is less than 30 km / h, and the number of brakes in front of the target vehicle is greater than 2 times within 20 seconds, and the front vehicle has the intention to change lanes (i.e., the turn signal is turned on) and is in the area where the lane can be changed.

[0060] In this embodiment, the target vehicle is driven in a second state at a higher congestion level than in the first state, and the target vehicle is driven in a third state at a higher congestion level than in the second state, that is, the target vehicle can drive freely in the free state, the stable state requires steady driving, and the congested state requires slow driving.

[0061] In order to accurately determine the target lane, in the method for generating an avoidance path provided in Example 1 of the present application, based on the vehicle sensor data, a first-class lane in which no vehicle to be avoided is driven within a second preset time is determined; based on the navigation path, the driving direction of the target vehicle is determined, and the lane with a lane direction indication consistent with the driving direction is determined as a second-class lane; a set of neighbor lanes connected to the current lane of the target vehicle is determined, and the neighbor lanes with lane lines indicated by lane change directions as dotted lines are screened from the set of neighbor lanes, and the neighbor lanes are determined as third-class lanes, wherein the lane change direction is the direction in which the target vehicle changes lanes; based on the vehicle sensor data, the number of lane changes made by the target vehicle in each lane is determined, and the lane with the least number of lane changes is determined as a fourth-class lane.

[0062] Optionally, vehicle information (such as vehicle type information, vehicle quantity information, etc.) and lane information (such as lane line information, lane quantity information, etc.) can be obtained based on the sensor data of the target vehicle, and the subsequent driving path and driving direction of the target vehicle can also be obtained based on the vehicle navigation data.

[0063] In this embodiment, it is possible to determine whether there are other vehicles to be avoided in the lane (i.e., other vehicles other than the avoiding vehicle that currently initiates an avoidance request to the target vehicle, such as ambulances, police cars, fire trucks, large vehicles, bicycles, vehicles transporting dangerous goods, etc.) based on the vehicle type information on other lanes or based on whether an avoidance request from a vehicle to be avoided in other lanes is received. If there is no vehicle to be avoided in the lane within a second preset time (e.g., 10 seconds), the lane is determined to be a first-class lane.

[0064] In this embodiment, according to the subsequent driving path and driving direction of the target vehicle, the lane with a lane direction indication consistent with the subsequent driving direction of the target vehicle can be determined as the second-class lane (that is, if the vehicle is about to enter the intersection, the second-class lane (that is, the lane for changing lanes) must be consistent with the subsequent driving direction of the vehicle).

[0065] In this embodiment, all neighbor lanes connected to the current lane of the target vehicle can be obtained based on the lane line information, and the neighbor lane whose lane line indicating the lane change direction of the target vehicle is a dotted line is screened out from all the neighbor lanes, and the neighbor lane is determined as a third-category lane (that is, the boundary line of the lane change direction of the third-category lane needs to be a dotted line).

[0066] In this embodiment, based on the lane in which the target vehicle is located and the lane number information, the number of lane changes made by the target vehicle in each lane can be calculated, and the lane with the least number of lane changes can be determined as the fourth-category lane (i.e., the lane with the least number of lane changes is determined as the fourth-category lane).

[0067] In order to improve the accuracy of determining the avoidance path of the target vehicle, in the avoidance path generation method provided in the first embodiment of the present application, based on the first type of lane, the second type of lane, the third type of lane and the fourth type of lane, a lane selection strategy is adopted to determine whether the target vehicle corresponds to a target lane; if the target vehicle corresponds to a target lane, based on the vehicle sensor data, whether the target vehicle meets the lane change condition during the process of driving to the target lane, wherein the lane change condition refers to the condition of having a lateral and longitudinal safety distance and a preset lane change space; if the target vehicle meets the lane change condition during the process of driving to the target lane, the target vehicle is controlled to drive to the target lane; if the target vehicle does not meet the lane change condition during the process of driving to the target lane, the target vehicle is controlled to broadcast a collaborative lane change request, or the target vehicle is controlled to determine the avoidance path of the target vehicle based on the current traffic status; if the target vehicle does not correspond to a target lane, it is determined whether the target vehicle corresponds to other driving lanes, and if the target vehicle corresponds to other driving lanes, the target vehicle is controlled to drive to other driving lanes; if the target vehicle does not correspond to other driving lanes, the avoidance method of the target vehicle is determined based on the lane width of the current lane, and the target vehicle is controlled to avoid based on the avoidance method.

[0068] Optionally, a lane selection strategy is adopted (i.e., the target lane needs to belong to the first class lane, the second class lane, the third class lane and the fourth class lane at the same time. If it cannot belong to the first class lane, the second class lane, the third class lane and the fourth class lane at the same time, then the target lane is selected according to the selection strategy that the priority of the first class lane is greater than the priority of the second class lane, the priority of the second class lane is greater than the priority of the third class lane, and the priority of the third class lane is greater than the priority of the fourth class lane) and based on the lane selection strategy, it is determined whether the target vehicle corresponds to the target lane.

[0069] In this embodiment, when there is a target lane corresponding to the target vehicle, it is determined based on the target vehicle sensor data whether the target vehicle meets the lane change conditions (such as lateral and longitudinal safety distances (i.e., the longitudinal safety distance from the vehicle in front and the lateral safety distance from the adjacent vehicles (including vehicles in and between lanes)) and the preset lane change space (such as the free area of ​​the target lane that can at least accommodate the target vehicle)) during the process of driving to the target lane.

[0070] In this embodiment, when there is a target lane corresponding to the target vehicle, if the target vehicle meets the lane changing conditions during the process of driving to the target lane, the target vehicle can be controlled to drive to the target lane; if the target vehicle does not meet the lane changing conditions during the process of driving to the target lane, the target vehicle can be controlled to broadcast a collaborative lane change request, and the vehicles in the target lane can provide lane changing conditions for the target vehicle based on the request, or the target vehicle can be controlled to determine the avoidance path of the target vehicle according to the current traffic conditions.

[0071] In this embodiment, when the target vehicle does not have a corresponding target lane, it is determined whether the target vehicle corresponds to other driving lanes, and when the target vehicle corresponds to other driving lanes, the target vehicle is controlled to first drive to other driving lanes for avoidance, and then returns to the vehicle navigation path after the avoidance vehicle passes. When the target vehicle does not have a corresponding other driving lane, according to the lane width of the current lane, if the lane width of the lane is narrow (i.e., it cannot accommodate the target vehicle and the vehicle to be avoided to pass at the same time), then according to the running state and running speed of the vehicle in front of the target vehicle, the current speed of the target vehicle is increased to drive away from the vehicle to be avoided until the lane change conditions are met. If the lane width of the lane is wide (i.e., it can accommodate the target vehicle and the vehicle to be avoided to pass at the same time), the target vehicle can be controlled to move laterally away from the vehicle to be avoided to provide passage space for the target vehicle to be avoided.

[0072] In order to further improve the accuracy of determining the avoidance path of the target vehicle, in the avoidance path generation method provided in Example 1 of the present application, when the current traffic state is the first state, the target vehicle is controlled to leave the current lane until the lane changing conditions are met; when the current traffic state is the second state, the departure method is determined based on the direction of the target lane, and the target vehicle is controlled to drive away from the vehicle to be avoided in the departure method; when the current traffic state is the third state, the target vehicle is controlled to park sideways.

[0073] Optionally, if the current traffic state is the first state, it indicates that the current traffic condition is relatively smooth, and the target vehicle can be controlled to leave the current lane until the target lane has the conditions for the target vehicle to change lanes. For example, when entering an intersection, the target vehicle can be controlled to enter the next lane of the intersection and then change lanes to avoid. If the current traffic state is the second state, it indicates that the current traffic condition is in a state of slight congestion. Based on the direction of the target lane, the target vehicle can be controlled to move laterally away from the vehicle to be avoided in the direction close to the target lane while ensuring a safe distance. If the current traffic state is the third state, it indicates that the current traffic condition is in a state of severe congestion, and the target vehicle can be controlled to park sideways. In this way, emergency vehicles can be quickly avoided according to the real-time traffic state of the target vehicle.

[0074] Figure 2 is a schematic diagram of an optional lane change avoidance path generation according to an embodiment of the present invention, such as Figure 2As shown, first, after receiving the avoidance request of the emergency vehicle (i.e., the vehicle to be avoided), it is determined whether the vehicle (i.e., the target vehicle) is a direct avoidance vehicle. If the vehicle is not a direct avoidance vehicle, the vehicle is controlled to cooperate with other vehicles (i.e., other vehicles) to avoid or restore traffic flow; if the vehicle is a direct avoidance vehicle, then it is determined whether there is a target lane. If there is a target lane, it is determined whether there is a lane change condition. If there is a lane change condition, the vehicle is controlled to change lanes to avoid. If there is no lane change condition, it is then determined whether the traffic state is in free flow (i.e., the first state). If the traffic state is in free flow, the vehicle can be controlled to accelerate and leave until the lane change condition is met. If the traffic state is not in free flow, it is determined whether the traffic state is in Stable flow (i.e. the second state). If the traffic state is in a stable flow, the vehicle can move laterally away from the emergency vehicle in the direction of the target lane while maintaining lateral safety. If the traffic state is not in a stable flow (i.e. in a congested flow (i.e. the third state)), the vehicle can be controlled to park sideways. If there is no target lane, then determine whether there are other lanes. If there are other lanes, control the vehicle to change lanes to the other lane closest to the current lane. If there are no other lanes, determine whether the current lane is a narrow road. If it is a narrow road, control the vehicle to accelerate and leave until the conditions for changing lanes are met. If it is not a narrow road, the vehicle can move laterally away from the emergency vehicle in the direction of the target lane while maintaining lateral safety.

[0075] In order to improve the accuracy of cooperating with other vehicles to avoid, in the avoidance path generation method provided in the first embodiment of the present application, if the current avoidance scenario is a scenario that requires the target vehicle to cooperate with other vehicles to avoid, it is determined whether the target vehicle needs to change lanes to avoid, wherein the other vehicles are vehicles that need to directly avoid the vehicle to be avoided; if the target vehicle needs to change lanes to avoid, the target vehicle is controlled to broadcast a lane change avoidance cooperation request, and if a response request from other vehicles is received, the target vehicle is controlled to change lanes to avoid; if no response request from other vehicles is received, the target vehicle is controlled to change lanes to avoid based on vehicle sensor data using a preset lane change strategy.

[0076] Optionally, if the current avoidance scenario is a scenario that requires the target vehicle to cooperate with other vehicles (i.e., the vehicle that directly avoids the vehicle to be avoided), it can be determined whether the target vehicle needs to change lanes to avoid. For example, other vehicles need to change lanes to the lane where the target vehicle is located in order to avoid the target vehicle, then the target vehicle needs to change lanes to another lane to cooperate with the avoidance. If the target vehicle needs to change lanes to avoid, the target vehicle can be controlled to broadcast a lane change avoidance cooperation request through the on-board unit OBU.

[0077] In this embodiment, other vehicles may include human-driven vehicles and autonomous driving vehicles. Human-driven vehicles cannot broadcast lane change avoidance cooperation requests and return response requests. Autonomous driving vehicles can receive lane change avoidance cooperation requests broadcast by the target vehicle through their own on-board units and return response requests. If the target vehicle receives the response requests of other vehicles, the target vehicle can be controlled to cooperate with lane change avoidance. If the target vehicle does not receive the response requests of other vehicles, the target vehicle can be controlled to change lanes with a preset lane change strategy through the target vehicle sensor data (such as a single-vehicle intelligent lane change method (that is, the target vehicle autonomously completes lane change decisions and executions, without relying on communication between vehicles)).

[0078] For example, the number, position, and speed of vehicles in adjacent lanes can be obtained based on the target vehicle's sensor data, and then based on the number, position, and speed of vehicles in adjacent lanes, the target vehicle can be controlled to change lanes to the adjacent lane while maintaining a safe distance.

[0079] In order to improve the accuracy of cooperating with other vehicles to avoid, in the avoidance path generation method provided in Example 1 of the present application, when the target vehicle does not need to change lanes to avoid, it is determined whether the target vehicle has received a cooperative lane change request sent by other vehicles; when a cooperative lane change request is received from other vehicles, the target vehicle is controlled to cooperate with other vehicles to avoid; when no cooperative lane change request is received from other vehicles, it is determined whether to perform cooperative avoidance based on vehicle sensor data and information of the vehicle to be avoided.

[0080] Optionally, when the target vehicle does not need to change lanes to avoid, it can be determined whether the target vehicle has received a cooperative lane change request sent by other vehicles. If the target vehicle has received a cooperative lane change request sent by other vehicles, the target vehicle can be controlled to cooperate with other vehicles to avoid. If the target vehicle has not received a cooperative lane change request sent by other vehicles, it can be determined whether to perform cooperative avoidance based on vehicle sensor data (such as the number of lanes, vehicle lane change intention, etc.) and information about the vehicle to be avoided (such as location, driving path, etc.).

[0081] Exemplarily, the vehicle to be avoided is in the neighboring lane on the left side of the target vehicle, and the vehicle to be avoided needs the vehicle in front to give way. The vehicle in front of the vehicle to be avoided is a human-driven vehicle. The human-driven vehicle knows through the vehicle's side-view mirrors and rearview mirror that the vehicle in front of the vehicle to be avoided is and needs to give way, that is, turns on the right turn signal to change lanes. The target vehicle's sensor data detects that the vehicle in front of the vehicle to be avoided has turned on the right turn signal, and determines the vehicle's intention to change lanes (that is, it has the intention to change lanes to the right). At this time, it is necessary to control the target vehicle to not turn left, and provide the vehicle in front of the vehicle to be avoided in the neighboring lane on the left with sufficient lane changing space to cooperate in avoidance.

[0082] Figure 3is a schematic diagram of an optional mixed traffic flow avoidance process according to an embodiment of the present invention, in which the vehicle (i.e., the target vehicle) cooperates with other vehicles, such as Figure 3 As shown, after receiving the avoidance request from the emergency vehicle (i.e. the vehicle to be avoided), it is determined whether the vehicle needs to change lanes to avoid the emergency vehicle. If the vehicle needs to change lanes to avoid the emergency vehicle, it is controlled to broadcast the collaborative lane change avoidance request, and then it is determined whether the vehicle has received feedback agreeing to the collaborative lane change. If the feedback agreeing to the collaborative lane change is received, the vehicle can be controlled to change lanes quickly to avoid the emergency vehicle. If the feedback agreeing to the collaborative lane change is not received, the vehicle can be controlled to change lanes to avoid the emergency vehicle according to the single-vehicle intelligent lane change method. If the vehicle does not need to change lanes to avoid the emergency vehicle, it is determined whether the vehicle has received a collaborative lane change request from other vehicles. If the collaborative lane change request is received from other vehicles, the vehicle is controlled to cooperate with other vehicles (i.e. other vehicles) to avoid the emergency vehicle. If the collaborative lane change request is not received from other vehicles, the emergency vehicle status and the real-time vehicle perception results are used to actively determine whether there is a need for collaboration.

[0083] In order to restore road traffic, in the avoidance path generation method provided in Example 1 of the present application, it is determined whether the target vehicle successfully avoids the vehicle to be avoided, and when the target vehicle successfully avoids the vehicle to be avoided, the traffic status of the target vehicle is updated; the traffic restoration demand is obtained, and the path planning result is regenerated based on the traffic restoration demand, the updated traffic status and the navigation path of the target vehicle.

[0084] Optionally, it is determined whether the target vehicle has successfully avoided the vehicle to be avoided (if the target vehicle has been controlled to perform a corresponding avoidance action (such as changing lanes, decelerating, braking, etc.) and the position of the vehicle to be avoided is in front of the target vehicle, it is determined that the vehicle to be avoided has been successfully avoided). When the target vehicle successfully avoids the vehicle to be avoided, the surrounding environment is monitored in real time by vehicle sensors to obtain vehicle sensor data, and the traffic status of the target vehicle is updated based on the vehicle sensor data.

[0085] In this embodiment, after the vehicle to be avoided has successfully passed, if the lane where the target vehicle is located is in a congested state, it can be determined whether the target vehicle is in the target lane. If the target vehicle is in the target lane, it can be determined whether there are other target lanes. If there are other target lanes, the target vehicle is controlled to change lanes to other target lanes. If there are no other target lanes, the vehicle navigation path is updated and the path planning result is regenerated. If the target vehicle is not in the target lane, the congestion coefficient of the target lane (i.e., an indicator used to measure the degree of road congestion, such as using the TTI (Travel Time Index) method to calculate the congestion coefficient) is calculated, and the lane is changed to other uncongested lanes. If the adjacent lane of the target vehicle is in a congested state, the target vehicle can be controlled to cooperate with the adjacent lane to restore traffic.

[0086] Figure 4 is a schematic diagram of an optional road traffic restoration process according to an embodiment of the present invention, such as Figure 4 As shown, after the emergency vehicle (i.e., the vehicle to be avoided) has passed, determine whether the lane where the vehicle (i.e., the target vehicle) is located is congested. If the lane where the vehicle is located is congested, then determine whether the vehicle is in the target lane. If the vehicle is in the target lane, determine whether there are other target lanes. If there are other target lanes, control the vehicle to change lanes to other target lanes. If there are no other target lanes, determine whether to update the navigation path planning. If the vehicle is not in the target lane, calculate the congestion coefficient of the target lane, and then control the vehicle to change lanes to a non-congested lane. If the lane where the vehicle is located is not congested, determine whether the adjacent lane of the vehicle is congested. If the adjacent lane of the vehicle is congested, the vehicle can be controlled to cooperate with the adjacent lane to restore traffic.

[0087] Figure 5 is a schematic diagram of an optional avoidance working principle according to an embodiment of the present invention, such as Figure 5 As shown, based on the emergency vehicle (i.e., the vehicle to be avoided) information, the own vehicle (i.e., the target vehicle) OBU information, and map information, the scene in which the own vehicle (i.e., the target vehicle) is located can be obtained. By performing perception fusion on the own vehicle perception information, the other vehicle OBU information, the own vehicle OBU information, etc., the current traffic status of the own vehicle can be obtained, and a lane change avoidance path planning can be generated based on the scene in which the own vehicle is located and the current traffic status of the own vehicle.

[0088] In an optional embodiment, the following may be used: Figure 5 The avoidance working principle shown implements the method of generating the avoidance path.

[0089] In an embodiment of the present invention, the scene in which the target vehicle is located is determined through vehicle sensor data and the avoidance request sent by the vehicle to be avoided, and the traffic status of the target vehicle is obtained based on the vehicle sensor data. Then, the avoidance path of the target vehicle is planned based on the scene in which the target vehicle is located, the traffic status of the target vehicle, the target vehicle sensor data, the avoidance request information sent by the vehicle to be avoided, and the collaborative lane change request information. After the vehicle to be avoided passes, the vehicle driving path is updated in combination with the surrounding traffic status, the road traffic is restored, and the road traffic efficiency is improved.

[0090] The following is a detailed description in conjunction with another embodiment.

[0091] Embodiment 2

[0092] The avoidance path generation device provided in this embodiment includes multiple implementation units, each implementation unit corresponds to each implementation step in the above-mentioned embodiment 1.

[0093] Figure 6 is a schematic diagram of an optional avoidance path generation device according to an embodiment of the present invention, such as Figure 6 As shown, the avoidance path generating device may include: a first determining unit 60 , a second determining unit 61 , and a first generating unit 62 .

[0094] The first determination unit 60 is used to determine the current traffic scene of the target vehicle in driving based on the vehicle sensor data and the information of the vehicle to be avoided carried in the avoidance request when receiving the avoidance request initiated by the vehicle to be avoided, wherein the vehicle sensor data is data information collected by the sensor in the target vehicle; the current traffic scene at least includes: the current avoidance scene and the current road scene; the information of the vehicle to be avoided is the information of the vehicle that meets the preset conditions;

[0095] A second determination unit 61 is used to determine the current traffic state of the target vehicle based on the vehicle sensor data;

[0096] The first generating unit 62 is used to generate an avoidance path for the target vehicle based on the current road scene and current traffic status of the target vehicle by adopting a preset path planning strategy if the current avoidance scene is a scene where the target vehicle needs to avoid the vehicle to be avoided.

[0097] The above-mentioned avoidance path generation device can determine the current traffic scene of the driving target vehicle based on the vehicle sensor data and the information of the vehicle to be avoided carried in the avoidance request when the avoidance request is received by the first determination unit 60, and determine the current traffic state of the target vehicle based on the vehicle sensor data through the second determination unit 61, and if the current avoidance scene is a scene that requires the target vehicle to avoid the vehicle to be avoided, the preset path planning strategy is adopted to generate an avoidance path for the target vehicle based on the current road scene and the current traffic state of the target vehicle.

[0098] Optionally, the generating device includes: a first determination module, used to determine the number of vehicles in the current lane and the neighboring lane where the target vehicle is located based on the vehicle quantity information before determining the current traffic status of the target vehicle based on the vehicle sensor data, wherein the neighboring lane is a lane connected to the current lane; a second determination module, used to determine the average speed of the leading vehicle based on the vehicle speed information, wherein the leading vehicle is the vehicle traveling in front of the target vehicle; a third determination module, used to determine the number of brakes of the leading vehicle within a first preset time; and a fourth determination module, used to determine the operating status and lane of the leading vehicle based on the vehicle operating information.

[0099] Optionally, the second determination unit includes a fifth determination module, which is used to determine that the current traffic state is a first state when the number of vehicles is less than a preset number of vehicles; a sixth determination module, which is used to determine that the current traffic state is a second state when the number of vehicles is greater than or equal to the preset number of vehicles and the average speed of the preceding vehicle is greater than a preset speed threshold, wherein the congestion level of the target vehicle traveling in the second state is higher than the congestion level of the target vehicle traveling in the first state; and a seventh determination module, which is used to determine that the current traffic state is a third state when the number of vehicles is greater than or equal to the preset number of vehicles, the average speed of the preceding vehicle is less than or equal to the preset speed threshold, the number of braking times is greater than the preset braking threshold, the operating state is a lane changing state, and the lane is a variable lane, wherein the congestion level of the target vehicle traveling in the third state is higher than the congestion level of the target vehicle traveling in the second state.

[0100] Optionally, the generating device also includes: an eighth determination module, which is used to determine, based on the vehicle sensor data, a first-class lane in which no vehicle to be avoided is driven within a second preset time before generating an avoidance path for the target vehicle based on the current road scene and current traffic conditions of the target vehicle using a preset path planning strategy; a ninth determination module, which is used to determine the driving direction of the target vehicle based on the navigation path, and determine the lane with a lane direction indication consistent with the driving direction as a second-class lane; a tenth determination module, which is used to determine a set of neighbor lanes connected to the current lane of the target vehicle, and filter out neighbor lanes whose lane lines indicating the lane change direction are dotted lines from the set of neighbor lanes, and determine the neighbor lanes as third-class lanes, wherein the lane change direction is the direction in which the target vehicle changes lanes; an eleventh determination module, which is used to determine the number of lane changes made by the target vehicle in each lane based on the vehicle sensor data, and determine the lane with the least number of lane changes as a fourth-class lane.

[0101] Optionally, the second determination unit includes: a first judgment module, which is used to determine whether the target vehicle corresponds to a target lane by adopting a lane selection strategy based on the first type of lane, the second type of lane, the third type of lane and the fourth type of lane; a twelfth determination module, which is used to determine whether the target vehicle meets the lane changing condition in the process of driving to the target lane based on the vehicle sensor data when the target vehicle corresponds to the target lane, wherein the lane changing condition refers to the condition of having a lateral and longitudinal safety distance and a preset lane changing space; a first control module, which is used to control the target vehicle to drive to the target lane when the lane changing condition is met in the process of the target vehicle driving to the target lane; and a second control module, which is used to If the target vehicle does not meet the lane change conditions when driving to the target lane, the target vehicle is controlled to broadcast a collaborative lane change request, or the target vehicle is controlled to determine the avoidance path of the target vehicle based on the current traffic status; a third control module is used to determine whether the target vehicle corresponds to other driving lanes when the target vehicle does not have a corresponding target lane, and control the target vehicle to drive to other driving lanes when the target vehicle corresponds to other driving lanes; a fourth control module is used to determine the avoidance method of the target vehicle based on the lane width of the current lane when the target vehicle does not have a corresponding other driving lane, and control the target vehicle to avoid based on the avoidance method.

[0102] Optionally, the second determination unit also includes: a fifth control module, which is used to control the target vehicle to leave the current lane until the lane change conditions are met when the current traffic state is the first state; a sixth control module, which is used to determine the departure method based on the direction of the target lane when the current traffic state is the second state, and control the target vehicle to drive away from the vehicle to be avoided in the departure method; and a seventh control module, which is used to control the target vehicle to park sideways when the current traffic state is the third state.

[0103] Optionally, the generating device also includes: a second judgment module, which is used to determine whether the target vehicle needs to change lanes to avoid after determining the current traffic scene of the driving target vehicle, if the current avoidance scene is a scene that requires the target vehicle to cooperate with other vehicles to avoid, wherein the other vehicles are vehicles that need to directly avoid the vehicle to be avoided; an eighth control module, which is used to control the target vehicle to broadcast a lane change avoidance cooperation request when the target vehicle needs to change lanes to avoid, and to control the target vehicle to change lanes to avoid when receiving a response request from other vehicles; a ninth control module, which is used to control the target vehicle to change lanes to avoid based on vehicle sensor data when no response request from other vehicles is received.

[0104] Optionally, the generating device also includes: a third judgment module, which is used to judge whether the target vehicle needs to change lanes to avoid, after judging whether the target vehicle needs to change lanes to avoid, if the target vehicle does not need to change lanes to avoid, whether the target vehicle receives a cooperative lane change request sent by other vehicles; a tenth control module, which is used to control the target vehicle to cooperate with other vehicles to avoid when a cooperative lane change request sent by other vehicles is received; and a fourth judgment module, which is used to judge whether to perform cooperative avoidance based on vehicle sensor data and information of vehicles to be avoided when no cooperative lane change request sent by other vehicles is received.

[0105] Optionally, the generating device also includes: a first updating module, which is used to determine whether the target vehicle successfully avoids the vehicle to be avoided after generating the avoidance path of the target vehicle, and to update the traffic status of the target vehicle when the target vehicle successfully avoids the vehicle to be avoided; a first generating module, which is used to obtain the traffic restoration demand, and regenerate the path planning result based on the traffic restoration demand, the updated traffic status and the navigation path of the target vehicle.

[0106] The above-mentioned avoidance path generation device may also include a processor and a memory. The above-mentioned first determination unit 60, the second determination unit 61, the first generation unit 62, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0107] The processor includes a kernel, and the kernel retrieves the corresponding program unit from the memory. One or more kernels may be provided, and the avoidance path is generated based on all the processed data by adjusting kernel parameters.

[0108] The above-mentioned memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0109] According to another aspect of an embodiment of the present invention, a computer program product is also provided, including a non-volatile computer-readable storage medium, the non-volatile computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, any one of the above-mentioned methods for generating an avoidance path is implemented.

[0110] When the computer program product is executed on a data processing device, it is suitable for executing a program that is initialized with the following method steps: when an avoidance request initiated by a vehicle to be avoided is received, based on the vehicle sensor data and the information of the vehicle to be avoided carried in the avoidance request, the current traffic scene of the driving target vehicle is determined, and based on the vehicle sensor data, the current traffic state of the target vehicle is determined; if the current avoidance scene is a scene that requires the target vehicle to avoid the vehicle to be avoided, a preset path planning strategy is used to generate an avoidance path for the target vehicle based on the current road scene and the current traffic state of the target vehicle.

[0111] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement the above-mentioned method for generating an avoidance path.

[0112] Figure 7 FIG. 1 is a hardware structure block diagram of an electronic device (or mobile device) for generating an avoidance path according to an embodiment of the present invention. Figure 7 As shown, the electronic device may include one or more processors (e.g., Figure 7 The processor 702a, processor 702b, ..., processor 702n, etc., which may include but are not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 704 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a keyboard, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 7 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 7 More or fewer components as shown, or with Figure 7 Different configurations are shown.

[0113] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0114] The embodiments or examples of the present disclosure are not exhaustive, but are only illustrative of some embodiments or examples, and are not intended to be specific limitations on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment or example can be implemented as an independent example, and the steps can be combined arbitrarily. For example, the scheme after removing some steps in a certain embodiment or example can also be implemented as an independent example, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be combined arbitrarily; in addition, the various embodiments or examples can be combined arbitrarily, for example, some or all steps of different embodiments or examples can be combined arbitrarily, and a certain embodiment or example can be combined arbitrarily with the optional methods or optional examples of other embodiments or examples.

[0115] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0116] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0117] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0118] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0119] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0120] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for generating an avoidance path, characterized in that: include: In the case of receiving an avoidance request initiated by a vehicle to be avoided, determining the current traffic scene of the target vehicle in driving based on vehicle sensor data and the vehicle to be avoided information carried in the avoidance request, wherein the vehicle sensor data is data information collected by a sensor in the target vehicle; the current traffic scene at least includes: a current avoidance scene and a current road scene; the vehicle to be avoided information is information of a vehicle that meets preset conditions; Determining the current traffic state of the target vehicle based on the vehicle sensor data; If the current avoidance scenario is a scenario that requires the target vehicle to avoid the vehicle to be avoided, a preset path planning strategy is adopted to generate an avoidance path for the target vehicle based on the current road scenario and the current traffic status where the target vehicle is located.

2. The method for generating an avoidance path according to claim 1, characterized in that: The vehicle sensor data at least includes: vehicle quantity information, vehicle speed information, vehicle braking information, and vehicle operation information. Before determining the current traffic state of the target vehicle based on the vehicle sensor data, the following is also included: Based on the vehicle quantity information, determine the number of vehicles in the current lane and the neighboring lane where the target vehicle is located, wherein the neighboring lane is a lane connected to the current lane; Determining an average speed of a preceding vehicle based on the vehicle speed information, wherein the preceding vehicle is a vehicle traveling in front of the target vehicle; Based on the vehicle braking information, determining the number of braking times of the preceding vehicle within a first preset time; Based on the vehicle operation information, the operation status and lane of the preceding vehicle are determined.

3. The method for generating an avoidance path according to claim 2, characterized in that: The step of determining the current traffic state of the target vehicle based on the vehicle sensor data comprises: When the number of vehicles is less than a preset number of vehicles, determining that the current traffic state is a first state; When the number of vehicles is greater than or equal to the preset number of vehicles and the average speed of the preceding vehicle is greater than a preset speed threshold, determining that the current traffic state is a second state, wherein the congestion degree of the target vehicle traveling in the second state is higher than the congestion degree of the target vehicle traveling in the first state; When the number of vehicles is greater than or equal to the preset number of vehicles, the average speed of the leading vehicle is less than or equal to a preset speed threshold, the number of braking times is greater than a preset braking threshold, the operating state is a lane changing state, and the lane is a variable lane, the current traffic state is determined to be a third state, wherein the congestion level of the target vehicle in the third state is higher than the congestion level of the target vehicle in the second state.

4. The method for generating an avoidance path according to claim 1, characterized in that: Before generating an avoidance path for the target vehicle based on the current road scene and the current traffic state of the target vehicle by adopting a preset path planning strategy, the method further includes: Based on the vehicle sensor data, determine that no first-class lane for vehicles to be avoided is driven within a second preset time; Determine the driving direction of the target vehicle based on the navigation path, and determine the lane with the lane direction indication consistent with the driving direction as the second type lane; Determine a set of neighbor lanes connected to the current lane of the target vehicle, and select neighbor lanes whose lane lines indicating lane change directions are dashed lines from the set of neighbor lanes, and determine the neighbor lanes as third-category lanes, wherein the lane change direction is the direction in which the target vehicle changes lanes; Based on the vehicle sensor data, the number of lane changes of the target vehicle in each lane is determined, and the lane with the least number of lane changes is determined as the fourth type lane.

5. The method for generating an avoidance path according to claim 4, characterized in that: The step of using a preset path planning strategy to generate an avoidance path for the target vehicle based on the current road scene and the current traffic state where the target vehicle is located includes: Based on the first lane, the second lane, the third lane, and the fourth lane, a lane selection strategy is adopted to determine whether the target vehicle corresponds to a target lane; In the case where the target vehicle corresponds to the target lane, determining whether the target vehicle meets a lane change condition in the process of driving to the target lane based on the vehicle sensor data, wherein the lane change condition refers to a condition of having a lateral and longitudinal safety distance and a preset lane change space; When the target vehicle meets the lane change condition during driving to the target lane, controlling the target vehicle to drive to the target lane; When the target vehicle does not meet the lane change condition during driving to the target lane, control the target vehicle to broadcast a cooperative lane change request, or control the target vehicle to determine an avoidance path for the target vehicle based on the current traffic status; In the case that the target vehicle does not correspond to the target lane, determining whether the target vehicle corresponds to other driving lanes, and in the case that the target vehicle corresponds to the other driving lanes, controlling the target vehicle to drive to the other driving lanes; In the case that the target vehicle does not have the corresponding other driving lane, the avoidance method of the target vehicle is determined based on the lane width of the current lane, and the target vehicle is controlled to avoid the lane based on the avoidance method.

6. The method for generating an avoidance path according to claim 5, characterized in that: The current traffic state includes: a first state, a second state, and a third state. The step of controlling the target vehicle to determine an avoidance path of the target vehicle based on the current traffic state includes: When the current traffic state is the first state, controlling the target vehicle to leave the current lane until the lane change condition is met; When the current traffic state is the second state, determining a driving-away method based on the direction of the target lane, and controlling the target vehicle to drive away from the vehicle to be avoided in the driving-away method; When the current traffic state is the third state, the target vehicle is controlled to park sideways.

7. The method for generating an avoidance path according to claim 1, characterized in that: After determining the current traffic scene of the target vehicle in driving, it also includes: If the current avoidance scenario is a scenario that requires the target vehicle to cooperate with other vehicles to avoid, determining whether the target vehicle needs to change lanes to avoid, wherein the other vehicles are vehicles that need to directly avoid the vehicle to be avoided; When the target vehicle needs to change lanes to avoid, control the target vehicle to broadcast a lane change cooperation request, and when receiving a response request from the other vehicle, control the target vehicle to change lanes to avoid; In the case where the response request from the other vehicle is not received, the target vehicle is controlled to change lanes to avoid the vehicle according to a preset lane change strategy based on the vehicle sensor data.

8. The method for generating an avoidance path according to claim 7, characterized in that: After determining whether the target vehicle needs to change lanes to avoid, the method further includes: In a case where the target vehicle does not need to change lanes to avoid, determining whether the target vehicle has received a cooperative lane change request sent by the other vehicle; When receiving the cooperative lane change request sent by the other vehicle, controlling the target vehicle to cooperate with the other vehicle to avoid; In the case where the cooperative lane change request sent by the other vehicle is not received, it is determined whether to perform cooperative avoidance based on the vehicle sensor data and the information of the vehicle to be avoided.

9. The method for generating an avoidance path according to claim 1, characterized in that: After generating the avoidance path of the target vehicle, the method further includes: Determining whether the target vehicle successfully avoids the vehicle to be avoided, and updating the traffic state of the target vehicle if the target vehicle successfully avoids the vehicle to be avoided; A traffic restoration requirement is obtained, and a path planning result is regenerated based on the traffic restoration requirement, the updated traffic status, and the navigation path of the target vehicle.

10. A device for generating an avoidance path, characterized in that: include: A first determination unit is used to determine the current traffic scene of the target vehicle in driving based on vehicle sensor data and information of the vehicle to be avoided carried in the avoidance request when receiving an avoidance request initiated by the vehicle to be avoided, wherein the vehicle sensor data is data information collected by a sensor in the target vehicle; the current traffic scene at least includes: a current avoidance scene and a current road scene; the vehicle information to be avoided is information of a vehicle that meets preset conditions; A second determination unit, configured to determine a current traffic state of the target vehicle based on the vehicle sensor data; The first generating unit is used to generate an avoidance path for the target vehicle based on the current road scene and the current traffic status of the target vehicle by adopting a preset path planning strategy if the current avoidance scene is a scene that requires the target vehicle to avoid the vehicle to be avoided.

Images