Decision-making method and related device

Abstract

An embodiment of this application relates to the field of intelligent vehicles and provides a decision-making method and a related device. The method includes the steps of: acquiring first environmental information for a first lane, where a vehicle is traveling in the first lane; determining, based on the first environmental information, that a first TTCD cluster is distributed in the first lane, where the first TTCD cluster includes at least one TTCD; determining a distribution situation of the first TTCD cluster in the first lane, where the distribution situation indicates a relative positional relationship between the at least one TTCD and the first lane; and determining a driving strategy based on the distribution situation of the first TTCD cluster in the first lane. Based on this solution, a driving strategy can be more accurately and appropriately determined based on the distribution situation of the first TTCD cluster in the first lane, which can provide a plan for the vehicle to avoid obstacles, change lanes, or brake, thereby improving decision-making safety.

Description

[Technical Field]

[0001] [CROSS-REFERENCE TO RELATED APPLICATIONS] This application claims priority to Chinese Patent Application No. 202310026379.2, entitled "DECISION-MAKING METHOD AND RELATED APPARATUS," filed with the State Intellectual Property Office of China on January 9, 2023, which is incorporated herein by reference in its entirety. [Technical field] This application relates to the field of intelligent vehicles, and more particularly to decision-making methods and related apparatus. [Background technology]

[0002] As autonomous driving technology becomes more and more mature, it is increasingly widely applied to intelligent vehicles to assist or take over the driver's control of vehicle driving. However, in the process of controlling vehicle driving, it is inevitable to encounter some special road situations, such as construction on the road ahead or a traffic accident on the road ahead. In these cases, traffic cones are usually used to warn vehicles approaching the construction site or accident site and instruct the vehicles to detour to avoid accidents. This requires the autonomous driving system to accurately identify the scenario and develop a driving strategy to plan lane changes or avoid obstacles.

[0003] Due to the complex real-world road conditions and the limited sensing capabilities of automated driving systems, it is difficult to ensure the safety and robustness of driving strategies.

[0004] Therefore, how to ensure high safety and robustness of driving strategies determined by automated driving systems is an issue that needs to be solved urgently. Summary of the Invention

[0005] An embodiment of the present application provides a decision-making method and related apparatus for determining a vehicle driving strategy by determining the distribution of temporary traffic control devices (TTCDs) arranged in a first lane. This method can ensure high safety and robustness of the driving strategy determined by the automated driving system, that is, the driving strategy can be more accurately and appropriately formulated to provide a plan for the vehicle to bypass an obstacle, change lanes, or brake.

[0006] According to a first aspect, there is provided a decision-making method, the method including: acquiring first environmental information of a first lane, wherein a vehicle is traveling in the first lane; determining, based on the first environmental information, that a first TTCD cluster is distributed in the first lane, wherein the first TTCD cluster includes at least one TTCD; determining a distribution state of the first TTCD cluster in the first lane, wherein the distribution state indicates a relative positional relationship between the at least one TTCD and the first lane; and determining a driving strategy based on the distribution state of the first TTCD cluster in the first lane.

[0007] For example, the TTCD may be a traffic cone, a traffic tube, a traffic pillar, a water-filled traffic barrier, or the like.

[0008] For example, the first environmental information may be the environmental information around the vehicle provided in the above embodiments, and may be acquired by using an on-board sensor.

[0009] For example, a driving strategy may include obstacle avoidance, lane changes, or braking.

[0010] Based on this technical solution, the driving strategy can be determined more accurately and appropriately based on the distribution situation of the first TTCD cluster in the first lane, and can provide plans for the vehicle to avoid obstacles, change lanes, or brake, thereby improving the safety of decision-making.

[0011] Referring to the first aspect, in some implementation methods of the first aspect, when the distribution situation of a first TTCD cluster in a first lane is in a first state, the driving strategy is determined to be a first strategy, and the first strategy is to control the vehicle to bypass the first TTCD cluster at a first speed.

[0012] For example, the first speed is less than the current driving speed of the vehicle. In this way, the vehicle can slow down in advance in the process of bypassing the first TTCD cluster in the first lane to avoid a collision caused by the vehicle's inability to avoid due to a sudden change in the distribution situation of the first TTCD cluster or the road environment in the first lane.

[0013] Based on this technical solution, when the detection range of the sensor is limited, the vehicle can limit the vehicle's speed in advance in the process of bypassing the first TTCD cluster, so that the vehicle can avoid a collision caused by avoidance failure when the distribution situation of the first TTCD cluster suddenly changes, and in addition to improving the safety of decision-making, the robustness of decision-making is also improved.

[0014] Referring to the first aspect, in some implementations of the first aspect, the first state includes that the minimum distance between the first edge line of the first TTCD cluster and the road center line of the first lane is greater than or equal to a first threshold, and the first edge line is an edge line of the first TTCD cluster extending along the direction of the first lane.

[0015] For example, the type of the first lane may be estimated based on the number of lanes included in the current road, and the width of the first lane may be determined. The first threshold may then be adjusted in real time. For example, a four-lane road in each direction is known to be 2 × 7.5 m. In this case, the width of the first lane may be 3.25 m, and the corresponding first threshold may be 0.5 m. A six-lane road in each direction is known to be 2 × 11.25 m. In this case, the width of the first lane may be 3.75 m, and the corresponding first threshold may be 0.6 m. A eight-lane road in each direction is known to be 2 × 15 m. In this case, the width of the first lane may be 3.75 m, and the corresponding first threshold may be 0.6 m.

[0016] For example, based on the above example, the first threshold may be further determined with reference to the width of the vehicle.

[0017] Based on the above technical solutions, the first state is properly defined to ensure that the vehicle can safely bypass the first TTCD cluster in the first lane, thereby improving the feasibility of implementing the first strategy by the vehicle and improving the safety and robustness of decision-making.

[0018] Referring to the first aspect, in some implementation methods of the first aspect, before determining that the driving strategy is the first strategy, second environmental information is determined based on the first state, and the second environmental information includes at least one of the following: the length of the first edge line of the first TTCD cluster, the included angle between the first edge line of the first TTCD cluster and the road center line of the first lane, and the minimum distance between the vehicle and the first TTCD cluster, and the first speed is determined based on the second environmental information.

[0019] For example, a longer first edge line indicates a lower first speed, a larger included angle between the first edge line and the road centerline of the first lane indicates a lower first speed, and a smaller minimum distance between the vehicle and the first TTCD cluster indicates a lower first speed.

[0020] Based on the above technical solution, the vehicle speed at which the vehicle bypasses the first TTCD cluster can be appropriately controlled based on the acquired second environmental information to avoid excessively high vehicle speed in the process of the vehicle bypassing the obstacle, and improve the safety and robustness of decision-making.

[0021] Referring to the first aspect, in some implementation methods of the first aspect, when the distribution situation of the first TTCD cluster in the first lane is in a second state, third environmental information of an adjacent lane of the first lane is determined, the road conditions of the adjacent lane are determined based on the third environmental information, and the driving strategy is determined to be the second strategy or the third strategy based on the road conditions of the adjacent lane.

[0022] For example, the second state is all situations other than the first state, i.e., the second state indicates that the current vehicle cannot bypass the first TTCD cluster in the first lane.

[0023] Based on the above technical solution, in consideration of the case where the vehicle cannot bypass the first TTCD cluster in the first lane, a driving strategy other than bypassing the obstacle in the lane is determined by obtaining the road conditions of the adjacent lanes, which improves the flexibility and safety of decision-making.

[0024] Referring to the first aspect, in some implementations of the first aspect, the second condition includes that a minimum distance between a first edge line of the first TTCD cluster and a road centerline of the first lane is less than a first threshold.

[0025] Based on the above technical solutions, the second state is properly defined to ensure that the vehicle can avoid collision with the first TTCD cluster, thereby improving the safety of decision-making.

[0026] Referring to the first aspect, in some implementation methods of the first aspect, when the road conditions of the adjacent lane satisfy the first lane change condition, the driving strategy is determined to be a second strategy, and the second strategy is to control the vehicle to change to the adjacent lane for driving, or when the road conditions of the adjacent lane do not satisfy the first lane change condition, the driving strategy is determined to be a third strategy, and the third strategy is to control the vehicle to brake in the first lane.

[0027] For example, whether the road conditions of the adjacent lane satisfy the first lane change condition may be comprehensively determined based on the recognition results of a traffic sign recognition (TSR) system, road condition information of the adjacent lane collected by a sensor mounted on the vehicle, and the reliability of the corresponding information.

[0028] Based on the above technical solution, the environmental information of the first lane and adjacent lanes is fully collected to ensure the safety and rationality of vehicle decision-making and avoid the safety risks caused by lane changing when the vehicle does not meet the lane change conditions.

[0029] Referring to the first aspect, in some implementations of the first aspect, the first lane change condition includes that the vehicle is permitted to change between the first lane and an adjacent lane, the front of the adjacent lane is not occupied, and no other vehicle is traveling laterally behind the adjacent lane.

[0030] For example, if the road conditions of the adjacent lane satisfy the first lane change condition, it means that all of the above conditions included in the first lane change condition are satisfied. If any one of the first lane change conditions is not satisfied, it means that the road conditions of the adjacent lane do not satisfy the first lane change condition.

[0031] Based on the above technical solution, the traffic situation in front or behind the adjacent lane is fully acquired, and the traffic rule factors of the current road are also taken into consideration to determine whether the vehicle can properly and safely change lanes to avoid the first TTCD cluster, which avoids the safety risks caused by lane changes when the vehicle does not meet the lane change conditions, and further improves the safety of the driving strategy.

[0032] Referring to the first aspect, in some implementation methods of the first aspect, when the driving strategy is the third strategy, the braking strategy of the vehicle is determined based on the positional relationship between the first TTCD and the vehicle in the first TTCD cluster, and the first TTCD is the TTCD closest to the vehicle in the first TTCD cluster.

[0033] For example, an expected braking distance of the vehicle may be determined to determine an action to control the vehicle to brake. The braking distance may be less than the distance between the vehicle and the first TTCD.

[0034] Based on the above technical solutions, when the vehicle uses the third strategy, the vehicle can brake as early as possible to reduce the collision risk of the vehicle during the braking process, make decision-making more humanistic, and improve the user's driving experience.

[0035] Referring to the first embodiment, in some implementations of the first embodiment, the distribution of the first TTCD cluster in the first lane is identified based on a cluster fitting method.

[0036] For example, the clustering algorithm may be a K-means algorithm, a hierarchical clustering algorithm, or a Self-Organizing Feature Map (SOM) clustering algorithm.

[0037] Based on the above technical solution, the distribution situation of the first TTCD cluster in the first lane can be accurately identified, thereby ensuring the reliability and accuracy of decision-making.

[0038] According to a second aspect, a decision-making device is provided, the device including: an acquisition unit configured to acquire first environmental information of a first lane, wherein a vehicle travels in the first lane; and a decision unit configured to determine, based on the first environmental information, that a first TTCD cluster is distributed in the first lane, the first TTCD cluster including at least one TTCD; to determine a distribution status of the first TTCD cluster in the first lane, the distribution status indicating a relative positional relationship between the at least one TTCD and the first lane; and to determine a driving strategy based on the distribution status of the first TTCD cluster in the first lane.

[0039] Based on this technical solution, the driving strategy can be determined more accurately and appropriately based on the distribution situation of the first TTCD cluster in the first lane, and provide a plan for the vehicle to avoid obstacles, change lanes, or brake.

[0040] Referring to the second aspect, in some implementation schemes of the second aspect, the determination unit is specifically configured to determine that the driving strategy is a first strategy when the distribution situation of the first TTCD cluster in the first lane is in a first state, and the first strategy is to control the vehicle to bypass the first TTCD cluster at a first speed.

[0041] Based on this technical solution, when the detection range of the sensor is limited, the vehicle can limit the vehicle's speed in advance in the process of bypassing the first TTCD cluster, so that the vehicle can avoid a collision caused by avoidance failure when the distribution situation of the first TTCD cluster suddenly changes.

[0042] Referring to the second aspect, in some implementations of the second aspect, the first state includes that the minimum distance between the first edge line of the first TTCD cluster and the road center line of the first lane is greater than or equal to a first threshold, and that the first edge line is an edge line of the first TTCD cluster extending along the direction of the first lane.

[0043] Based on the above technical solutions, the first state is properly defined to ensure that the vehicle can safely bypass the first TTCD cluster in the first lane, thereby improving the feasibility of implementing the first strategy by the vehicle and improving the safety and robustness of decision-making.

[0044] Referring to the second aspect, in some implementation manners of the second aspect, before determining that the driving strategy is the first strategy, the determination unit is further configured to determine second environmental information based on the first state, where the second environmental information includes at least one of the following: the length of the first edge line of the first TTCD cluster, the included angle between the first edge line of the first TTCD cluster and the road center line of the first lane, and the minimum distance between the vehicle and the first TTCD cluster, and is further configured to determine a first speed based on the second environmental information.

[0045] Based on the above technical solution, the vehicle speed at which the vehicle bypasses the first TTCD cluster can be appropriately controlled based on the acquired second environmental information to avoid excessively high vehicle speed in the process of the vehicle bypassing the obstacle, and improve the safety and robustness of decision-making.

[0046] Referring to the second aspect, in some implementation methods of the second aspect, the determination unit is specifically configured to: determine third environmental information of an adjacent lane of the first lane when the distribution situation of the first TTCD cluster in the first lane is in a second state; determine the road situation of the adjacent lane based on the third environmental information; and determine that the driving strategy is the second strategy or the third strategy based on the road situation of the adjacent lane.

[0047] Based on the above technical solution, in consideration of the case where the vehicle cannot bypass the first TTCD cluster in the first lane, a driving strategy other than bypassing the obstacle in the lane is determined by obtaining the road conditions of the adjacent lanes, which improves the flexibility and safety of decision-making.

[0048] Referring to the second aspect, in some implementations of the second aspect, the second condition includes that the minimum distance between the first edge line of the first TTCD cluster and the road centerline of the first lane is less than a first threshold.

[0049] Based on the above technical solutions, the second state is properly defined to ensure that the vehicle can avoid collision with the first TTCD cluster, thereby improving the safety of decision-making.

[0050] Referring to the second aspect, in some implementation manners of the second aspect, the determination unit is specifically configured to determine that the driving strategy is a second strategy when the road conditions of the adjacent lane satisfy a first lane change condition, and the second strategy is to control the vehicle to change to the adjacent lane for driving, or to determine that the driving strategy is a third strategy when the road conditions of the adjacent lane do not satisfy the first lane change condition, and the third strategy is to control the vehicle to brake in the first lane.

[0051] Based on the above technical solution, the environmental information of the first lane and adjacent lanes is fully collected to ensure the safety and rationality of vehicle decision-making and avoid the safety risks caused by lane changing when the vehicle does not meet the lane change conditions.

[0052] Referring to the second aspect, in some implementations of the second aspect, the first lane change condition includes that the vehicle is permitted to change between the first lane and an adjacent lane, the front of the adjacent lane is not occupied, and no other vehicle is traveling laterally behind the adjacent lane.

[0053] Based on the above technical solution, the traffic situation in front or behind the adjacent lane is fully acquired, and the traffic rule factors of the current road are also taken into consideration to determine whether the vehicle can properly and safely change lanes to avoid the first TTCD cluster, which avoids the safety risks caused by lane changes when the vehicle does not meet the lane change conditions, and further improves the safety of the driving strategy.

[0054] Referring to the second aspect, in some implementation methods of the second aspect, when the driving strategy is the third strategy, the determination unit is further configured to determine a braking strategy for the vehicle based on a positional relationship between a first TTCD in the first TTCD cluster and the vehicle, and the first TTCD is the TTCD closest to the vehicle in the first TTCD cluster.

[0055] Based on the above technical solutions, when the vehicle uses the third strategy, the vehicle can brake as early as possible to reduce the collision risk of the vehicle during the braking process, make decision-making more humanistic, and improve the user's driving experience.

[0056] Referring to the second embodiment, in some implementations of the second embodiment, the distribution of the first TTCD cluster in the first lane is identified based on a cluster fitting method.

[0057] Based on the above technical solution, the distribution situation of the first TTCD cluster in the first lane can be accurately identified, thereby ensuring the reliability and accuracy of decision-making.

[0058] According to a third aspect, there is provided a decision-making apparatus including a processor and a memory, the processor being connected to the memory, the memory being configured to store program code, the processor being configured to invoke the program code to perform a method in any possible implementation manner of the design of the method of the first aspect.

[0059] According to a fourth aspect, there is provided a chip system, the chip system being applied to an electronic device, the chip system including one or more interface circuits and one or more processors, the interface circuits and the processors being interconnected through lines, the interface circuits being configured to receive signals from a memory of the electronic device and send signals to the processor, the signals including computer instructions stored in the memory, and when the processor executes the computer instructions, the electronic device performs a method in any possible implementation manner of the design of the method of the first aspect.

[0060] According to a fifth aspect, there is provided a computer readable storage medium storing a computer program or instructions for use in implementing the method of the first aspect in any possible implementation of the method design.

[0061] According to a sixth aspect, there is provided a computer program product, the computer program code or instructions being, when executed on a computer, capable of causing the computer to carry out the method of any possible implementation of the design of the method of the first aspect.

[0062] According to a seventh aspect, there is provided a vehicle, the vehicle comprising an apparatus according to any possible implementation of the second or third aspect. [Brief explanation of the drawings]

[0063] [Figure 1] 1 is a functional block diagram of a vehicle 100 according to an embodiment of the present application. [Figure 2] 1 illustrates an automated driving system 200 according to an embodiment of the present application that is applicable to an embodiment of the present application. [Figure 3] 1 is a schematic flowchart of a decision-making method according to an embodiment of the present application. [Figure 4] FIG. 2 is a diagram of the detection range of a sensing system according to an embodiment of the present application. [Figure 5(a)]FIG. 2 is a diagram of a first TTCD cluster distributed in a first state according to an embodiment of the present application. [Figure 5(b)] FIG. 2 is a diagram of a first TTCD cluster distributed in a first state according to an embodiment of the present application. [Figure 6(a)] FIG. 1 is a diagram of the expected effect of decision-making and post-processing according to an embodiment of the present application. [Figure 6(b)] FIG. 1 is a diagram of the expected effect of decision-making and post-processing according to an embodiment of the present application. [Figure 7] 1 is a schematic flowchart of another decision-making method according to an embodiment of the present application. [Figure 8] 1 is a schematic flowchart of another decision-making method according to an embodiment of the present application. [Figure 9] 9 is a block diagram of a decision-making device 900 according to an embodiment of the present application. [Figure 10] FIG. 1 is a block diagram of a decision-making device according to an embodiment of the present application. [Figure 11] 1 is a block diagram of a computer-readable storage medium according to an embodiment of the present application. DETAILED DESCRIPTION OF THE INVENTION

[0064] Below, the technical solutions in the embodiments of this application are described with reference to the accompanying drawings.

[0065] 1 is a functional block diagram of a vehicle 100 according to an embodiment of the present application. The vehicle 100 may include a sensing system 120, a display device 130, and a computing platform 150. The sensing system 120 may include several types of sensors that sense information about the surrounding environment of the vehicle 100. For example, the sensing system 120 may include a positioning system. The positioning system may be a global positioning system (GPS), or one or more of a BeiDou system or other positioning system, an inertial measurement unit (IMU), a lidar, a millimeter-wave radar, an ultrasonic radar, and a camera device.

[0066] Some or all of the functions of the vehicle 100 may be controlled by a computing platform 150. The computing platform 150 may include processors 151 to 15n (n is a positive integer). A processor is a circuit having signal processing capabilities. In one implementation, the processor may be a circuit having instruction reading and execution capabilities, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which may also be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor may implement a specific function based on the logical relationships of a hardware circuit. The logical relationships of the hardware circuit may be fixed or reconfigurable. For example, the processor may be a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field programmable gate array (FPGA). In a reconfigurable hardware circuit, the process of the processor loading a configuration document and implementing the hardware circuit configuration can be understood as the process of the processor loading instructions and implementing the functions of some or all of the above units. Furthermore, the processor may alternatively be a hardware circuit designed for artificial intelligence and can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), or a deep learning processing unit (DPU). Furthermore, the computing platform 150 may further include a memory. The memory is configured to store instructions.Some or all of the processors 151 to 15n may call instructions in the memory to implement the corresponding functions.

[0067] FIG. 2 illustrates an automated driving system 200 according to an embodiment of the present application that is applicable to the embodiment of the present application.

[0068] The autonomous driving system 200 includes a sensing system, a sensing and prediction module, a decision-making and planning module, a control module, and an actuator.

[0069] In some possible embodiments, the sensing system belongs to the sensing system 120 and is configured to collect environmental information around the vehicle, motion state information of the host vehicle, etc. The environmental information around the vehicle may include the road conditions ahead of the current driving lane, the road conditions of adjacent lanes, obstacle target information, etc., and may be collected by using a lidar. The motion state information of the host vehicle may include the vehicle speed, acceleration, turning angle, etc., and may be obtained by using sensors disposed on the chassis of the vehicle. The information is then transmitted to the sensing and prediction module.

[0070] In some possible embodiments, the obstacle may be a TTCD, and may also be a traffic cone, a traffic tube, a traffic pillar, a water-filled traffic barrier, or the like.

[0071] The sensing and prediction module may be the computing platform 150 provided in the above embodiment, and is configured to process the data information collected by the sensing system and use the related information, such as road and obstacle information obtained through the processing, as input for downstream modules. The processing result is transmitted to the decision-making and planning module.

[0072] The decision-making and planning module is configured to determine a driving decision based on relevant information included in the processing result, the driving decision including a predicted trajectory of the vehicle travel, and to transmit the driving decision to the control module.

[0073] The control module is configured to calculate a corresponding control value based on the operating decision and transmit the control value to the actuator.

[0074] The actuator is a vehicle steering wheel, a vehicle throttle, a brake device, etc., and controls the vehicle's driving state, such as lane change, acceleration or deceleration, based on a control value.

[0075] Based on the autonomous driving system 200, it can be ensured that the vehicle can drive safely and stably under ideal road conditions. However, in a real driving scenario, the road conditions are complicated, for example, the road ahead is under construction or there is a traffic accident on the road ahead. In these cases, TTCDs are usually deployed on the road to warn vehicles near the construction site or accident site and instruct the vehicles to take a detour to avoid the accident.

[0076] In existing decision-making methods, it is usually determined whether to control the vehicle to change lanes based only on the current lane environment conditions, and only one predicted driving path of the vehicle is provided, which ignores whether the current vehicle has a lane change condition at any time during the process of driving along the predicted path, that is, it ignores the risk of the vehicle driving along the predicted path.

[0077] In view of this, an embodiment of the present application provides a decision-making method for making driving decisions by analyzing the distribution of TTCDs placed on a road and the traffic conditions of adjacent lanes to determine how to control a vehicle.

[0078] FIG. 3 is a flowchart of a decision-making method according to an embodiment of this application.

[0079] S310: Obtain first environmental information for a first lane.

[0080] In some possible embodiments, the first environmental information may be environmental information around the vehicle provided in the above embodiments, and may be acquired by using the sensing system provided in the above embodiments.

[0081] S320: Based on the first environmental information, determine that a first TTCD cluster is distributed in a first lane, and the first TTCD cluster includes at least one TTCD.

[0082] S330: Determine a distribution of a first TTCD cluster in a first lane, where the distribution indicates a relative positional relationship between at least one TTCD and the first lane.

[0083] In some possible embodiments, the sensing and prediction module provided in the above embodiments may be used to analyze the first environmental information to determine the distribution of the first TTCD cluster in the first lane, including but not limited to the center point position and distribution of the TTCD in the first lane coordinate system.

[0084] In some possible embodiments, based on the first environmental information and a clustering algorithm, a clustering operation may be performed on the TTCDs to merge TTCDs of a specified type (such as traffic cones, traffic tubes, traffic pillars, water-filled traffic barriers, etc.) located in the first lane and remove irrelevant TTCDs, for example, TTCDs distributed outside the first lane, to determine a first TTCD cluster. Then, based on a fitting algorithm, for example, a least squares method or a Hough transform, the edge lines of the first TTCDs and the center point positions and distribution of the TTCDs in the first lane coordinate system may be determined.

[0085] In some possible embodiments, when the first TTCD cluster includes a plurality of TTCDs, the distribution status further includes the relative positional relationship between the plurality of TTCDs.

[0086] In some possible embodiments, the clustering algorithm may be a K-means algorithm, a hierarchical clustering algorithm, or a SOM clustering algorithm.

[0087] S340: Determine a driving strategy based on the distribution of the first TTCD cluster in the first lane.

[0088] In some possible embodiments, the driving strategy may include obstacle avoidance, lane changes, or braking.

[0089] Based on this technical solution, the driving strategy can be more accurately and appropriately determined based on the distribution situation of the first TTCD cluster in the first lane, and can be planned to avoid obstacles, change lanes, or brake, thereby improving the safety of decision-making.

[0090] In some possible embodiments, the distribution status may be represented by using the horizontal occupancy rate of the first TTCD cluster in the first lane, or by using the minimum distance between the first edge line of the first TTCD cluster and the road centerline of the first lane. The first edge line is the edge line of the first TTCD cluster extending along the direction of the first lane. In practice, the above two examples of determining the distribution status are essentially the same, i.e., determining the feasibility of vehicles to bypass the first TTCD cluster in the first lane.

[0091] FIG. 4 is a diagram of the detection range of a sensing system according to an embodiment of the present application.

[0092] In some possible embodiments, the detection range of the sensing system mounted on the vehicle is limited. For example, during a curve driving process, it is difficult for the sensing system to detect the change trend of the first TTCD cluster on the curve within a certain distance. As a result, the driving strategy determined by the vehicle before or during curve driving has a certain safety risk, i.e., there is a certain detection blind spot. For example, during the process of the vehicle bypassing the first TTCD cluster on the curve, a sudden change in the distribution situation of the first TTCD cluster is detected. If the vehicle speed is high, the vehicle will collide with the TTCD due to a failure to avoid collision. Based on this, when the distribution situation of the first TTCD cluster in the first lane is in a first state, a driving strategy may be determined to be a first strategy, where the vehicle bypasses the first TTCD cluster at a first speed.

[0093] The first speed may be less than the current traveling speed of the vehicle.

[0094] Based on this technical solution, when the detection range of the sensor is limited, the vehicle can limit the vehicle's speed in advance in the process of bypassing the first TTCD cluster, so that the vehicle can avoid a collision caused by avoidance failure when the distribution situation of the first TTCD cluster suddenly changes, improving the safety of decision-making and the robustness of decision-making.

[0095] 5(a) and 5(b) are diagrams of a first TTCD cluster distributed in a first state according to an embodiment of the present application.

[0096] In some possible embodiments, the first condition includes that the minimum distance between the first edge line of the first TTCD cluster and the road centerline of the first lane is greater than or equal to a first threshold, and that the first edge line is an edge line of the first TTCD cluster that extends along the direction of the first lane.

[0097] 5(a) and 5(b), it can be seen that one first TTCD cluster includes two first edge lines, i.e., first edge line 1 and first edge line 2 in FIGS. 5(a) and 5(b). However, the minimum distance between the first edge line of the first TTCD cluster and the road centerline of the first lane is naturally calculated based on the first edge line that is closest to the road centerline of the first lane.

[0098] For example, in Figure 5(a), the first edge line 1 is closer to the road centerline of the first lane than the first edge line 2. Therefore, the minimum distance between the first edge line of the first TTCD cluster and the road centerline of the first lane should be calculated based on the first edge line 1 relative to the road centerline of the first lane, and the minimum distance is L1.

[0099] For example, in Figure 5(b), the first edge line 2 is closer to the road centerline of the first lane than the first edge line 1. Therefore, the minimum distance between the first edge line of the first TTCD cluster and the road centerline of the first lane should be calculated based on the first edge line 2 relative to the road centerline of the first lane, and the minimum distance is L2.

[0100] It should be understood that when the first edge line of the first TTCD cluster intersects with the road centerline of the first lane, the minimum distance between the first edge line of the first TTCD cluster and the road centerline of the first lane is 0.

[0101] In some possible embodiments, the first threshold may be a preset appropriate value, for example, 0.5 m or 0.8 m, and should be specifically determined based on the width of the first lane.

[0102] In some possible embodiments, the type of the first lane may be estimated based on the number of lanes collected by the sensing system to determine the width of the first lane, and the first threshold may then be adjusted in real time. For example, a four-lane road in each direction is known to be 2 × 7.5 m. In this case, the width of the first lane may be 3.25 m, and the corresponding first threshold may be 0.5 m. A six-lane road in each direction is known to be 2 × 11.25 m. In this case, the width of the first lane may be 3.75 m, and the corresponding first threshold may be 0.6 m. A eight-lane road in each direction is known to be 2 × 15 m. In this case, the width of the first lane may be 3.75 m, and the corresponding first threshold may be 0.6 m.

[0103] In some possible embodiments, the first threshold value may be further determined with reference to the width of the host vehicle, which is not limited in this embodiment of the application.

[0104] Based on this technical solution, when the detection range of the sensor is limited, the vehicle can limit the vehicle's speed in advance in the process of bypassing the first TTCD cluster, so that the vehicle can avoid a collision caused by avoidance failure when the distribution situation of the first TTCD cluster suddenly changes.

[0105] In some possible embodiments, the first speed may be determined by using the following method: first, determining second environmental information based on the first state, and then determining the first speed based on the second environmental information.

[0106] In some possible embodiments, the second environmental information includes at least one of the following: a length of the first edge line of the first TTCD cluster, an included angle between the first edge line of the first TTCD cluster and the road centerline of the first lane, and a minimum distance between the vehicle and the first TTCD cluster.

[0107] In some possible embodiments, there is a correlation between each data included in the second environmental information and the first speed, for example, a longer first edge line indicates a lower first speed, a larger included angle between the first edge line and the road centerline of the first lane indicates a lower first speed, and a smaller minimum distance between the vehicle and the first TTCD cluster indicates a lower first speed.

[0108] Furthermore, the second environmental information may further include other types of information, such as the past change trends of TTCDs located on the road, i.e., the past change trends of the first edge line of the first TTCD cluster. Then, a predicted change trend of the first edge line of the first TTCD cluster is determined, and a distance between the first route and the first edge line is determined based on the predicted change trends of the first route and the first edge line to determine a first speed. A shorter distance between the first route and the first edge line indicates a lower first speed.

[0109] In some possible embodiments, the first speed may be further determined based on a first route included in the first strategy, for example, a smaller minimum distance between the first route and the first TTCD cluster indicates a lower first speed.

[0110] In some possible embodiments, the speed limit of the current road section is referenced to determine the first speed, so that in the process of the vehicle bypassing the first TTCD cluster in the first lane, the speed is not lower than the road speed limit.

[0111] Based on the above technical solution, the speed at which the vehicle bypasses the first TTCD cluster can be better determined, thereby further ensuring the safety of the vehicle bypassing the obstacle.

[0112] In some possible embodiments, the second environmental information may be used as an SV soft constraint and distributed to downstream decision-making and planning modules, which then make more accurate and appropriate driving decisions based on that information.

[0113] In some possible embodiments, when the distribution status of the first TTCD cluster in the first lane is in the second state, third environmental information of an adjacent lane of the first lane may be further determined, then the road conditions of the adjacent lane are determined based on the third environmental information, and finally, a driving strategy is determined based on the road conditions of the adjacent lane.

[0114] In some possible embodiments, the second state is any situation other than the first state. The second state indicates that the current vehicle cannot bypass the first TTCD cluster in the first lane. It can be seen that the second state includes the minimum distance between the first edge line of the first TTCD cluster and the road centerline of the first lane being less than a first threshold. For example, the first edge line intersects with the road centerline of the first lane. In this case, the minimum distance is equal to 0, which is less than the first threshold.

[0115] Based on the above technical solution, based on the distribution situation of the first TTCD cluster in the first lane, it is found that the vehicle cannot bypass the first TTCD cluster in the first lane, and a driving strategy other than the in-lane obstacle bypass is determined, which improves the flexibility and safety of decision-making.

[0116] In some possible embodiments, when the distribution of the first TTCD cluster is in a second state, whether the road conditions of the adjacent lanes satisfy the first lane change condition may be comprehensively determined based on the recognition results of the TSR system, the road condition information of the adjacent lanes collected by the sensors mounted on the vehicle, and the reliability of the corresponding information.

[0117] In some possible embodiments, the recognition results of the TSR system may include whether the lane boundary line between the first lane and the adjacent lane can be crossed, i.e., whether lane changing is permitted on the current road, etc. The road condition information of the adjacent lane may include whether a separation fence exists between the first lane and the adjacent lane, whether the front of the adjacent lane is occupied, whether another vehicle is traveling to the side or rear of the adjacent lane, etc.

[0118] Whether the adjacent lane ahead is occupied may be determined by whether the adjacent lane ahead is a congested road section, whether the adjacent lane ahead is a construction road section, or whether the adjacent lane ahead is occupied by another TTCD cluster.

[0119] The adjacent lane of the first lane should be understood to have the following meaning:

[0120] When the first lane is the right edge of the entire lane, the adjacent lane indicates the adjacent lane to the left of the first lane. Correspondingly, when the first TTCD cluster is distributed in the second state, the third environmental information indicates the environmental information of the adjacent lane to the left of the first lane.

[0121] When the first lane is the left edge of the entire lane, the adjacent lane indicates the adjacent lane to the right of the first lane. Correspondingly, when the first TTCD cluster is distributed in the second state, the third environmental information indicates the environmental information of the adjacent lane to the right of the first lane.

[0122] When the first lane is not the end of a full lane, the adjacent lanes indicate the adjacent lanes on both sides of the first lane. Correspondingly, when the first TTCD cluster is distributed in the second state, the third environmental information indicates the environmental information of the adjacent lanes on both sides of the first lane.

[0123] In some possible embodiments, when the road conditions of the adjacent lane satisfy the first lane change condition, the driving strategy is determined to be a second strategy, where the second strategy is for the vehicle to change into the adjacent lane for travel. When the road conditions of the adjacent lane do not satisfy the first lane change condition, the driving strategy is determined to be a third strategy, where the third strategy is for the vehicle to brake in the first lane.

[0124] In some possible embodiments, the first lane change condition may be determined by using the recognition result of the TSR system and road condition information of adjacent lanes provided in the above embodiments.

[0125] In some possible embodiments, the first lane change condition may include that the vehicle is permitted to change between the first lane and an adjacent lane, the adjacent lane ahead is not occupied, and no other vehicle is traveling laterally behind the adjacent lane.

[0126] It should be understood that the road conditions of the adjacent lane provided in the above embodiment satisfying the first lane change condition indicates that all of the above conditions included in the first lane change condition are satisfied. If any one of the first lane change conditions is not satisfied, this indicates that the first lane change condition is not satisfied.

[0127] Based on the above technical solution, the traffic situation in front or behind the adjacent lane is fully acquired, and the traffic rule factors of the current road are also taken into consideration to determine whether the vehicle can properly and safely change lanes to avoid the first TTCD cluster, which avoids the safety risks caused by lane changes when the vehicle does not meet the lane change conditions, and further improves the safety of the driving strategy.

[0128] In some possible embodiments, when the driving strategy is the third strategy, the decision-making and post-processing operations, i.e., The method may further include controlling the vehicle to brake based on a positional relationship between a first TTCD in the first TTCD cluster and the vehicle, the first TTCD being the TTCD closest to the vehicle in the first TTCD cluster.

[0129] In some possible embodiments, an expected braking distance of the vehicle may be determined to determine an action to control the vehicle to brake. The braking distance may be less than the distance between the vehicle and the first TTCD.

[0130] Based on the above technical solutions, when the vehicle uses the third strategy, the vehicle can brake as early as possible to reduce the collision risk of the vehicle during the braking process, make decision-making more humanistic, and improve the user's driving experience.

[0131] 6(a) and 6(b) are diagrams of the expected effect of post-decision processing according to an embodiment of the present application.

[0132] Figure 6(a) is a diagram of a parking location when decision-making and post-processing are not performed. Figure 6(b) is a diagram of a parking location when decision-making and post-processing are performed. The TTCDs in Figures 6(a) and 6(b) are traffic cones.

[0133] Referring to FIG. 6(a), it can be seen that the vehicle detects that the traffic cones 3 in the first TTCD cluster distributed in the first lane are already located on the road centerline of the first lane. Therefore, the driving decision is determined as the second decision or the third decision based on the above decision-making method. In this embodiment, it is assumed that the adjacent lane does not satisfy the first lane change condition. Therefore, the third decision needs to be used to control the vehicle to brake. In this case, the expected position where the vehicle will brake is determined based on the traffic cones 3, and finally, the vehicle brakes in front of the traffic cones 3. Although this method can ensure that the vehicle does not collide with the first TTCD cluster, if there are some unexpected cases in the traffic environment, the vehicle may collide with other traffic objects due to failure of avoidance, thereby posing a safety risk. Furthermore, such a braking method may be less humane and may not provide the user with sufficient reassurance. Therefore, the above decision-making and post-processing operations may be performed.

[0134] Referring to FIG. 6(b), it can be seen that the vehicle detects that the traffic cone 3 in the first TTCD cluster distributed in the first lane is already located on the road centerline of the first lane. Therefore, the driving decision is determined as the second decision or the third decision based on the above decision-making method. In this embodiment, it is assumed that the adjacent lane does not satisfy the first lane change condition. Therefore, the third decision needs to be used to control the vehicle to brake. Based on the above decision-making and post-processing operations, the expected position where the vehicle will brake is determined based on the traffic cone 1 closest to the vehicle, and finally, the vehicle brakes in front of the traffic cone 1. In this way, the vehicle can brake in advance to reduce the collision risk. Furthermore, such a braking method is humane and may provide the user with a sufficient sense of security, thereby improving the user's driving experience.

[0135] In some possible embodiments, after the driving strategy is determined, corresponding alarm information or handover request information may be generated, and the information may be reported to a human machine interface (HMI) of the assisted driving system to prompt the user to perform coordinated driving in a timely manner.

[0136] In some possible embodiments, the determined driving strategy may be further transmitted and displayed to the user through the HMI to prompt the user to confirm whether the current driving strategy is appropriate. If the current driving strategy is inappropriate, the user may receive a request to take over and control the vehicle's travel.

[0137] Based on the above technical solution, the decision-making results are transmitted and displayed to the user in real time, so that the user can obtain more decision-making information and be empowered to take over and control the vehicle, which improves the user's sense of security while ensuring the driving safety of the vehicle.

[0138] FIG. 7 is a schematic flowchart of another decision-making method according to an embodiment of the present application.

[0139] In some possible embodiments, the distribution situation of the first TTCD cluster in the first lane is used as an example. In practical applications, controlling the vehicle based on the above decision-making method may specifically include the following steps:

[0140] S710: A sensing system of the vehicle collects first environmental information and determines that a first TTCD cluster is distributed in front of the vehicle.

[0141] S720: The sensing and prediction module of the vehicle analyzes the distribution status of the first TTCD cluster in the first lane, and determines through the analysis that the distribution status of the first TTCD cluster is in a first state.

[0142] S730: The vehicle's sensing and prediction module further analyzes the second environmental information of the first lane.

[0143] The second environmental information includes at least one of the following: an included angle between a first edge line of the first lane and the road centerline, and a distance between the vehicle and a TTCD closest to the road centerline of the first lane. The second environmental information is then distributed to downstream decision-making and planning modules as SV soft constraints.

[0144] S740: The vehicle's decision-making and planning module determines, based on the first state and the second environmental information, that the driving strategy is a first strategy.

[0145] The first strategy is for the vehicle to bypass the first TTCD cluster at a first speed.

[0146] Furthermore, after the vehicle determines a first route to avoid obstacles, the decision-making and planning module may also add the positional relationship between the first route and the first edge line of the first TTCD cluster to the second environmental information, so that the first decision-making made by the vehicle becomes safer and more reasonable.

[0147] S750: The control module of the vehicle controls the actuators of the vehicle to perform the corresponding action according to the first strategy.

[0148] Based on the above technical solution, when it is determined that the vehicle can bypass the first TTCD cluster in the first lane, it ensures that the vehicle will not collide with the first TTCD, and appropriate deceleration is further implemented to avoid collision risks such as failure to avoid the emergency situation in the first lane.

[0149] FIG. 8 is a schematic flowchart of another decision-making method according to an embodiment of the present application.

[0150] In some possible embodiments, the distribution situation of the first TTCD cluster in the first lane is used as an example in the second state. In practical applications, controlling the vehicle based on the above decision-making method may specifically include the following steps:

[0151] S810: A sensing system of the vehicle collects first environmental information and determines that a first TTCD cluster is distributed in front of the vehicle.

[0152] S820: The sensing and prediction module of the vehicle analyzes the distribution status of the first TTCD cluster in the first lane, and determines through the analysis that the distribution status of the first TTCD cluster is in a second state.

[0153] The distribution status of the first TTCD cluster being in the second state means that the vehicle cannot bypass the first TTCD cluster in the first lane.

[0154] S830: The vehicle's sensing system collects third environmental information of a lane adjacent to the first lane.

[0155] In some possible embodiments, after S820 is executed, the sensing and prediction module may generate first instruction information, which instructs the upstream sensing system to perform the action in S830.

[0156] S840: The vehicle's sensing and prediction module determines whether the road conditions of the adjacent lane satisfy a first lane change condition.

[0157] If the first lane change condition is met, S850 is executed, or if the first lane change condition is not met, S860 is executed.

[0158] The first lane change condition includes that the vehicle is permitted to change between the first lane and an adjacent lane, that the front of the adjacent lane is not occupied, that no other vehicle is traveling to the side or rear of the adjacent lane, etc.

[0159] S850: The vehicle's decision-making and planning module determines that the driving strategy is a second strategy, and the second strategy is to control the vehicle to change into an adjacent lane for travel.

[0160] S860: The vehicle's decision-making and planning module determines that the driving strategy is a third strategy, and the third strategy is to control the vehicle to brake in the first lane.

[0161] When S860 is executed, S865 may be further executed.

[0162] S865: The vehicle's decision-making and planning module performs decision-making and post-processing operations so that the vehicle completes braking in advance.

[0163] S870: The control module of the vehicle controls the actuators of the vehicle to perform the corresponding action according to the first strategy.

[0164] Based on the above technical solution, after the vehicle can no longer bypass the first TTCD cluster in the first lane, the vehicle can avoid a collision between the vehicle and the first TTCD cluster by changing lanes or braking. Furthermore, it effectively ensures that the vehicle will not collide with objects such as other vehicles in adjacent lanes. Furthermore, in the braking process, the vehicle can brake in advance, which results in more human-like decision-making and improves the user's driving experience.

[0165] Furthermore, embodiments of the present application further provide an apparatus configured to implement any one of the above methods. For example, a braking apparatus is provided. The apparatus includes a unit (or means) configured to implement any one of the above braking methods.

[0166] 9 is a block diagram of a decision-making device 900 according to an embodiment of the present application. As shown in FIG. 9, the device 900 includes: an acquisition unit 910 configured to acquire first environmental information of a first lane, where the vehicle travels in the first lane; and The system includes a determination unit 920 configured to determine, based on first environmental information, that a first TTCD cluster is distributed in a first lane, the first TTCD cluster including at least one TTCD; to determine a distribution status of the first TTCD cluster in the first lane, the distribution status indicating a relative positional relationship between the at least one TTCD and the first lane; and to determine a driving strategy based on the distribution status of the first TTCD cluster in the first lane.

[0167] In some possible embodiments, the determination unit 920 is specifically configured to determine that when the distribution situation of the first TTCD cluster in the first lane is in a first state, the driving strategy is a first strategy, and the first strategy is to control the vehicle to bypass the first TTCD cluster at a first speed.

[0168] In some possible embodiments, the first condition includes that the minimum distance between the first edge line of the first TTCD cluster and the road centerline of the first lane is greater than or equal to a first threshold, and that the first edge line is an edge line of the first TTCD cluster that extends along the direction of the first lane.

[0169] In some possible embodiments, before determining that the driving strategy is the first strategy, the determination unit 920 is further configured to determine second environmental information based on the first state, the second environmental information including at least one of the following: the length of the first edge line of the first TTCD cluster, the included angle between the first edge line of the first TTCD cluster and the road center line of the first lane, and the minimum distance between the vehicle and the first TTCD cluster, and is further configured to determine a first speed based on the second environmental information.

[0170] In some possible embodiments, the determination unit 920 is specifically configured to: determine third environmental information of an adjacent lane of the first lane when the distribution status of the first TTCD cluster in the first lane is in a second state; determine the road status of the adjacent lane based on the third environmental information; and determine that the driving strategy is the second strategy or the third strategy based on the road status of the adjacent lane.

[0171] In some possible embodiments, the second condition includes a minimum distance between a first edge line of the first TTCD cluster and a road centerline of the first lane being less than a first threshold.

[0172] In some possible embodiments, the determination unit 920 is specifically configured to determine that the driving strategy is a second strategy when the road conditions of the adjacent lane satisfy a first lane change condition, the second strategy being to control the vehicle to change into the adjacent lane for driving, or to determine that the driving strategy is a third strategy when the road conditions of the adjacent lane do not satisfy the first lane change condition, the third strategy being to control the vehicle to brake in the first lane.

[0173] In some possible embodiments, the first lane change condition includes that the vehicle is permitted to change between the first lane and an adjacent lane, the adjacent lane ahead is not occupied, and no other vehicle is traveling laterally behind the adjacent lane.

[0174] In some possible embodiments, when the driving strategy is the third strategy, the determination unit 920 is further configured to determine a braking strategy for the vehicle based on a positional relationship between a first TTCD in the first TTCD cluster and the vehicle, the first TTCD being the TTCD closest to the vehicle in the first TTCD cluster.

[0175] In some possible embodiments, the distribution of the first TTCD cluster in the first lane is identified based on a cluster fitting method.

[0176] 10 is a block diagram of yet another decision-making apparatus according to an embodiment of the present application. The computer device 1000 shown in FIG. 10 includes a memory 1010, a processor 1020, and a bus 1040. Optionally, the computer device 1000 further includes a communication interface 1030. The memory 1010, the processor 1020, and the communication interface 1030 are interconnected through the bus 1040.

[0177] The memory 1010 may be a read only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1010 may store a program. When the program stored in the memory 1010 is executed by the processor 1020, the processor 1020 is configured to perform steps of a neural network model training method in an embodiment of this application. Specifically, the processor 1020 may perform the method shown in FIG. 3.

[0178] The processor 1020 may be a general-purpose central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), a graphics processing unit (GPU), or one or more integrated circuits, and is configured to execute associated programs to implement the decision-making methods provided in the method embodiments of this application.

[0179] The processor 1020 may alternatively be an integrated circuit chip and have signal processing capabilities. In the implementation process, the steps of the decision-making method provided in this application may be completed by using integrated logic circuits of hardware in the processor 1020 or instructions in software form.

[0180] The processor 1020 may alternatively be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, which may implement or perform the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor, or the processor may be any conventional processor, etc. The steps of the methods disclosed with reference to the embodiments of this application may be directly performed and achieved by using a hardware decoding processor, or may be performed and achieved by using a combination of hardware modules and software modules in the decoding processor. The software modules may be located in a storage medium well-established in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, or a register. The storage medium is located in the memory 1010. The processor 1020 reads the information in the memory 1010 and, in combination with the hardware of the processor 1020, completes the functions that need to be performed by the units included in the apparatus shown in FIG. 9, or performs the method shown in FIG. 3 in the method embodiment of this application.

[0181] The communication interface 1030 uses a transceiver device, such as, but not limited to, a transceiver, to facilitate communication between the apparatus 1000 and other devices or communication networks. For example, training data may be obtained through the communication interface 1030.

[0182] Bus 1040 may include a path for transmitting information between components of device 1000 (eg, memory 1010, processor 1020, and communication interface 1030).

[0183] It should be understood that only a memory, a processor, and a communication interface are shown in the above device 1000. However, in a specific implementation process, those skilled in the art should understand that the device 1000 may further include other components required for normal execution. Furthermore, based on specific requirements, those skilled in the art should understand that the device 1000 may further include hardware components for implementing other additional functions. Furthermore, those skilled in the art should understand that the device 1000 may alternatively include only devices required to implement the embodiments of this application, but may not necessarily include all devices shown in FIG. 10.

[0184] It may be understood that the memory in the embodiments of this application may be volatile memory or nonvolatile memory, or may include volatile memory and nonvolatile memory. Nonvolatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may be random access memory (RAM) used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) may be used, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchlink dynamic random access memory (SLDRAM), and direct rambus random access memory (DR RAM).

[0185] 11 is a block diagram of a computer-readable storage medium according to an embodiment of the present application. The computer-readable storage medium 1100 shown in FIG. 11 stores computer instructions 1110. When the computer instructions 1110 are executed by a processor, the method shown in FIG. 3 may be realized.

[0186] In some possible embodiments, computer-readable storage medium 1100 may be any available medium accessible by a computer, or a data storage device that integrates one or more available media, such as a server or data center. The available medium may be a magnetic medium (e.g., a floppy disk, hard disk, or magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state drive.

[0187] Those skilled in the art may recognize that, in combination with the examples described in the embodiments disclosed in this specification, the units and algorithm steps may be realized by electronic hardware or a combination of computer software and electronic hardware. Whether a function is performed by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to realize the described functions for each specific application, but such implementation methods should not be considered to go beyond the scope of this application.

[0188] For the purpose of convenient and concise description, those skilled in the art can clearly understand that the detailed operation processes of the above systems, devices and units may refer to the corresponding processes in the above method embodiments, and the details will not be described again in this specification.

[0189] In some embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other ways. For example, the described device embodiments are merely examples. For example, the division into units is merely a logical division of function, and other divisions may be used in actual implementations. For example, multiple units or components may be combined or integrated into other systems, or some features may be omitted or not implemented. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be realized through some interfaces. Indirect couplings or communication connections between devices or units may be realized in electronic, mechanical, or other forms.

[0190] The units described as separate parts may or may not be physically separate, and the parts shown as units may or may not be physical units, and may be located in one place or distributed across multiple network units. Some or all of the units may be selected based on actual requirements to achieve the objectives of the solutions of the embodiments.

[0191] Furthermore, the functional units in the embodiments of this application may be integrated into one processing unit, each of the units may exist physically alone, or two or more units may be integrated into one unit.

[0192] When a function is realized in the form of a software functional unit and sold or used as an independent product, the function may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application may essentially, or a portion of the technical solution or a portion of the technical solution may be realized in the form of a software product. A computer software product is stored in a storage medium and includes some instructions for instructing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method described in the embodiments of this application. The above storage medium includes any medium capable of storing program code, such as a USB flash drive, a removable hard disk, a read-only memory (ROM), a random access memory, a magnetic disk, or an optical disk.

[0193] The above description is merely a specific implementation of this application and is not intended to limit the scope of protection of this application. Any variations or replacements that can be easily conceived by those skilled in the art within the technical scope disclosed in this application shall fall within the scope of protection of this application. Therefore, the scope of protection of this application shall be subject to the scope of protection of the claims.

Claims

1. 1. A decision-making method applied to a vehicle, comprising: acquiring first environmental information of a first lane, the vehicle traveling in the first lane; determining, based on the first environmental information, that a first temporary traffic control device (TTCD) cluster is distributed in the first lane, the first TTCD cluster including at least one TTCD; determining a distribution of the first TTCD cluster in the first lane, the distribution indicating a relative positional relationship between the at least one TTCD and the first lane; determining a driving strategy based on the distribution of the first TTCD cluster in the first lane; A method comprising:

2. The step of determining a driving strategy based on the distribution status of the first TTCD cluster in the first lane includes:

2. The method of claim 1, comprising: determining that the driving strategy is a first strategy when the distribution situation of the first TTCD cluster in the first lane is in a first state, the first strategy being to control the vehicle to bypass the first TTCD cluster at a first speed.

3. The first state is 3. The method of claim 2, comprising: a minimum distance between a first edge line of the first TTCD cluster and a road centerline of the first lane being equal to or greater than a first threshold; and the first edge line being an edge line of the first TTCD cluster extending along the direction of the first lane.

4. before determining that the driving strategy is a first strategy, determining second environmental information based on the first state, the second environmental information including at least one of the following: a length of a first edge line of the first TTCD cluster, an included angle between the first edge line of the first TTCD cluster and a road centerline of the first lane, and a minimum distance between the vehicle and the first TTCD cluster; determining the first speed based on the second environmental information; The method of claim 2 or 3, further comprising:

5. The step of determining a driving strategy based on the distribution status of the first TTCD cluster in the first lane includes: When the distribution state of the first TTCD cluster in the first lane is in a second state, determining third environmental information of an adjacent lane of the first lane; determining a road condition of the adjacent lane based on the third environmental information; determining, based on the road conditions of the adjacent lane, that the driving strategy is a second strategy or a third strategy; The method of claim 1 , further comprising:

6. The second state is The method of claim 5 , further comprising: a minimum distance between a first edge line of the first TTCD cluster and a road centerline of the first lane being less than a first threshold.

7. The step of determining that the driving strategy is a second strategy or a third strategy based on the road condition of the adjacent lane includes: determining that the driving strategy is the second strategy when the road conditions of the adjacent lane satisfy a first lane change condition, the second strategy being to control the vehicle to change into the adjacent lane for travel; or determining that the driving strategy is the third strategy when the road conditions of the adjacent lane do not satisfy the first lane change condition, the third strategy being to control the vehicle to brake in the first lane; 7. The method of claim 5 or 6, comprising:

8. 8. The method of claim 7, wherein the first lane change condition includes the vehicle being permitted to change between the first lane and the adjacent lane, the adjacent lane being unoccupied ahead, and no other vehicle traveling laterally behind the adjacent lane.

9. When the driving strategy is the third strategy, The method of claim 7 or 8, further comprising: determining a braking strategy for the vehicle based on a positional relationship between a first TTCD in the first TTCD cluster and the vehicle, the first TTCD being the closest TTCD to the vehicle in the first TTCD cluster.

10. The method of claim 1 , wherein the distribution of the first TTCD cluster in the first lane is identified based on a cluster fitting method.

11. 1. A decision-making device for use in a vehicle, comprising: an acquisition unit configured to acquire first environmental information of a first lane, the vehicle traveling in the first lane; and a determining unit configured to determine, based on the first environmental information, that a first temporary traffic control device (TTCD) cluster is distributed in the first lane, the first TTCD cluster including at least one TTCD; to determine a distribution state of the first TTCD cluster in the first lane, the distribution state indicating a relative positional relationship between the at least one TTCD and the first lane; and to determine a driving strategy based on the distribution state of the first TTCD cluster in the first lane; An apparatus comprising:

12. The decision unit: The device of claim 11, wherein the device is specifically configured to determine that the driving strategy is a first strategy when the distribution situation of the first TTCD cluster in the first lane is in a first state, and the first strategy is to control the vehicle to bypass the first TTCD cluster at a first speed.

13. The first state is 13. The device of claim 12, wherein the minimum distance between a first edge line of the first TTCD cluster and a road centerline of the first lane is equal to or greater than a first threshold, and the first edge line is an edge line of the first TTCD cluster that extends along the direction of the first lane.

14. Before determining that the driving strategy is the first strategy, the determining unit: and further configured to determine second environmental information based on the first state, the second environmental information including at least one of the following: a length of a first edge line of the first TTCD cluster, an included angle between the first edge line of the first TTCD cluster and a road centerline of the first lane, and a minimum distance between the vehicle and the first TTCD cluster; 14. The apparatus of claim 12 or 13, further configured to determine the first speed based on the second environmental information.

15. The decision unit: When the distribution state of the first TTCD cluster in the first lane is in a second state, determining third environmental information of an adjacent lane of the first lane; determining a road condition of the adjacent lane based on the third environmental information; The device of claim 11 , specifically configured to determine that the driving strategy is a second strategy or a third strategy based on the road conditions of the adjacent lane.

16. The second state is The apparatus of claim 15 , further comprising: a minimum distance between a first edge line of the first TTCD cluster and a road centerline of the first lane being less than a first threshold.

17. The decision unit: Specifically configured to determine that the driving strategy is the second strategy when the road conditions of the adjacent lane satisfy a first lane change condition, and the second strategy is to control the vehicle to change into the adjacent lane for driving; or 17. The device of claim 15 or 16, wherein the device is specifically configured to determine that the driving strategy is the third strategy when the road conditions of the adjacent lane do not satisfy the first lane change condition, and the third strategy is to control the vehicle to brake in the first lane.

18. 18. The apparatus of claim 17, wherein the first lane change condition includes the vehicle being permitted to change between the first lane and the adjacent lane, the adjacent lane being unoccupied ahead, and no other vehicle traveling laterally behind the adjacent lane.

19. When the driving strategy is the third strategy, the determining unit:

19. The device of claim 17 or 18, further configured to determine a braking strategy for the vehicle based on a positional relationship between a first TTCD in the first TTCD cluster and the vehicle, the first TTCD being the closest TTCD to the vehicle in the first TTCD cluster.

20. 20. The apparatus of claim 11, wherein the distribution of the first TTCD cluster in the first lane is identified based on a cluster fitting method.

21. A decision-making device including a processor and a memory, 11. A decision-making device, wherein the processor is connected to the memory, the memory being configured to store program code, and the processor is configured to call the program code to perform the method of any one of claims 1 to 10.

22. 1. A chip system for use in an electronic device, comprising: The chip system includes one or more interface circuits and one or more processors, the interface circuits and the processors are interconnected through lines, the interface circuits are configured to receive signals from a memory of the electronic device and send the signals to the processor, the signals include computer instructions stored in the memory, and when the processor executes the computer instructions, the electronic device performs the method of any one of claims 1 to 10.

23. 1. A computer-readable storage medium, comprising:

11. A computer readable storage medium storing a computer program, the computer program being executed by a processor to implement the method of any one of claims 1 to 10.

24. 1. A computer program product comprising: A computer program product comprising computer program codes or instructions that, when executed on a computer, enable the computer to carry out the method of any one of claims 1 to 10.

25. A vehicle including an apparatus according to any one of claims 11 to 21.

Images