Vehicle driving strategy determination method, vehicle mixed traffic control method and unmanned vehicle

Abstract

The present application provides a method for determining a vehicle driving strategy, a method for controlling mixed traffic of vehicles, and an unmanned vehicle, and relates to the fields of unmanned driving, automatic driving, and unmanned vehicles. The method for determining a vehicle driving strategy includes: generating at least one collision plan and at least one risk avoidance plan when a target vehicle has a risk of collision with surrounding objects, wherein a collision plan refers to a collision response method adopted by the target vehicle when a collision cannot be avoided, and a risk avoidance plan refers to an evasive response method adopted by the target vehicle to avoid a collision; calculating the collision cost of each collision plan and the risk cost of each risk avoidance plan; and determining a target driving strategy from the at least one collision plan and the at least one risk avoidance plan based on the collision cost of each collision plan and the risk cost of each risk avoidance plan.

Description

Technical Field

[0001] The present application relates to the technical fields of unmanned driving, automatic driving, and unmanned vehicles, and specifically to a method for determining a vehicle driving strategy, a method for controlling mixed vehicle traffic, and an unmanned vehicle. Background Art

[0002] The vehicle may pose safety risks to the surrounding environment and itself, or even directly cause a safety accident due to its own reasons or software or hardware failures.

[0003] In traditional solutions, when a vehicle may collide with the surrounding environment, the vehicle's behavior is usually optimized based on the potential losses caused by the collision to reduce collision damage. Summary of the Invention

[0004] In view of this, embodiments of the present application provide a vehicle driving strategy determination method, a vehicle mixed traffic control method, and an unmanned vehicle.

[0005] In a first aspect, an embodiment of the present application provides a method for determining a vehicle driving strategy, comprising: generating at least one collision plan and at least one risk avoidance plan when there is a risk of collision between a target vehicle and surrounding objects, the collision plan referring to a collision response method taken when the target vehicle cannot avoid a collision, and the risk avoidance plan referring to an avoidance response method taken by the target vehicle to avoid a collision; calculating the collision cost of each collision plan, and calculating the risk cost of each risk avoidance plan; and determining a target driving strategy from at least one collision plan and at least one risk avoidance plan based on the collision cost of each collision plan and the risk cost of each risk avoidance plan.

[0006] In combination with the first aspect, in certain implementations of the first aspect, when there is a risk of collision between the target vehicle and surrounding objects, at least one collision plan and at least one risk avoidance plan are generated, including: when it is determined that there is a risk of collision between the target vehicle and surrounding objects, at least one risk avoidance plan is generated; based on the at least one risk avoidance plan, a corresponding collision plan is generated.

[0007] In combination with the first aspect, in certain implementations of the first aspect, at least one risk avoidance plan is generated, including: obtaining motion information of the target vehicle and status data of surrounding objects; generating a candidate risk avoidance sequence based on the motion information of the target vehicle and the status data of surrounding objects, the candidate risk avoidance sequence including a combination of one or more actions of steering, braking and accelerating; performing a feasibility check on each candidate risk avoidance sequence, and determining the candidate risk avoidance sequence that passes the feasibility check as the risk avoidance plan.

[0008] In combination with the first aspect, in certain implementations of the first aspect, a corresponding collision plan is generated based on at least one avoidance plan, including: for each avoidance plan, predicting the execution process of the avoidance plan; if the avoidance plan fails to be executed, determining the potential collision object and / or potential collision position after the avoidance plan is executed, and the execution failure indicates that the target vehicle cannot avoid collision with surrounding objects; based on the potential collision object and / or potential collision position after the avoidance plan is executed, generating a collision plan corresponding to the avoidance plan, and the associated information of the collision plan includes the collision object and / or collision position.

[0009] In combination with the first aspect, in certain implementations of the first aspect, the collision scheme corresponding to the avoidance scheme includes a collision posture optimization instruction and / or a collision energy distribution strategy; based on the potential collision object and / or potential collision position after the execution of the avoidance scheme, a collision scheme corresponding to the avoidance scheme is generated, including: based on the type of the potential collision object and / or the potential collision position, generating a collision posture optimization instruction, the collision posture optimization instruction is used to indicate collision position optimization and / or collision angle optimization; and / or, based on the distribution of the potential collision position and the buffer zone of the target vehicle, generating a collision energy distribution strategy, the collision energy distribution strategy includes a distribution rule for dispersing the impact energy generated by the collision to the buffer zone according to a preset proportion.

[0010] In conjunction with the first aspect, in certain implementations of the first aspect, when there is a risk of collision between the target vehicle and surrounding objects, before generating at least one collision solution and at least one risk avoidance solution, the method further includes:

[0011] Obtain motion information of a target vehicle and state data of surrounding objects; based on the motion information of the target vehicle, generate at least one predicted trajectory of the target vehicle within a future target time; if, based on the state data of the surrounding objects, it is determined that the predicted trajectory of the target vehicle overlaps with the surrounding objects, then determine that there is a risk of collision between the target vehicle and the surrounding objects; wherein the motion information includes at least one of posture, velocity, acceleration, kinematic parameters, and dynamic parameters; and the state data includes at least one of position, velocity, size, and direction of motion.

[0012] In combination with the first aspect, in certain implementations of the first aspect, if it is determined that there is overlap between the predicted trajectory of the target vehicle and the surrounding objects based on the status data of the surrounding objects, the method includes: calculating the spatiotemporal overlap probability between the predicted trajectory of the target vehicle and the surrounding objects based on the status data of the surrounding objects; if the spatiotemporal overlap probability is greater than a preset probability threshold, determining that there is overlap between the predicted trajectory of the target vehicle and the surrounding objects.

[0013] In combination with the first aspect, in certain implementations of the first aspect, the collision cost of each collision scenario is calculated, including: for each collision scenario, using at least one cost calculation function in a collision cost model, the collision cost of the collision scenario is calculated based on the costs corresponding to the collision objects and / or collision positions associated with the collision scenario, as well as the cost corresponding to the target vehicle; wherein the cost of the collision object is determined based on the type of the collision object or the value of the collision object.

[0014] In combination with the first aspect, in certain implementations of the first aspect, the risk cost of each hedging plan is calculated, including: for each hedging plan, based on the type of hedging action, the status data of surrounding objects, the motion information of the target vehicle, and at least one of the environmental parameters, the risk cost of the hedging plan is calculated through at least one cost calculation function in the risk cost model, wherein the risk cost is the expected cost of the probability of a risk event occurring during the execution of the hedging plan.

[0015] In combination with the first aspect, in certain implementations of the first aspect, the motion information of the target vehicle includes dynamic parameters, which include load and / or center of gravity height, and the environmental parameters of the target vehicle include road adhesion coefficient and / or visibility.

[0016] In combination with the first aspect, in certain implementations of the first aspect, based on the collision costs of each collision scenario and the risk costs of each avoidance scenario, a target driving strategy is determined from at least one collision scenario and at least one avoidance scenario, including: comparing the numerical values ​​of the collision cost of the collision scenario and the risk cost of the avoidance scenario, and selecting the scenario with the smallest numerical value as the target driving strategy; or, selecting a set of scenarios that meet a safety threshold from the collision scenarios and the avoidance scenarios, and selecting the scenario with the lowest cost from the set of scenarios as the target driving strategy.

[0017] In the second aspect, an embodiment of the present application provides a vehicle mixed traffic control method, including: when there is a risk of collision between an unmanned vehicle and a manned vehicle, determining a target driving strategy corresponding to the unmanned vehicle, wherein the target driving strategy is obtained based on the method described in the first aspect; and controlling the driving of the unmanned vehicle based on the target driving strategy.

[0018] On the third aspect, an embodiment of the present application provides a vehicle driving strategy determination device, including: a generation module, used to generate at least one collision plan and at least one risk avoidance plan when there is a risk of collision between the target vehicle and surrounding objects. The collision plan refers to the collision response method taken when the target vehicle cannot avoid collision, and the risk avoidance plan refers to the avoidance response method taken by the target vehicle to avoid collision; a calculation module, used to calculate the collision cost of each collision plan, and calculate the risk cost of each risk avoidance plan; a first determination module, used to determine the target driving strategy from at least one collision plan and at least one risk avoidance plan based on the collision cost of each collision plan and the risk cost of each risk avoidance plan.

[0019] In the fourth aspect, an embodiment of the present application provides a vehicle mixed traffic control device, including: a second determination module, used to determine the target driving strategy corresponding to the unmanned vehicle when there is a risk of collision between the unmanned vehicle and a manned vehicle, wherein the target driving strategy is obtained based on the method described in the first aspect; a control module, used to control the driving of the unmanned vehicle based on the target driving strategy.

[0020] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program for executing the method described in the first aspect and / or the second aspect.

[0021] In a sixth aspect, an embodiment of the present application provides an unmanned vehicle, which includes: a processor; a memory for storing processor-executable instructions; and the processor is used to execute the method described in the first aspect and / or the second aspect.

[0022] In a seventh aspect, an embodiment of the present application provides a computer program product, which includes instructions that, when executed on an unmanned vehicle, enable the unmanned vehicle to implement the method described in the first aspect and / or the second aspect.

[0023] In this application, at least one collision scenario and at least one avoidance scenario are generated simultaneously, providing multiple possibilities for selecting the optimal driving strategy. Next, the collision cost of each collision scenario and the risk cost of each avoidance scenario are calculated, visually and quantitatively demonstrating the potential losses and risks of different scenarios. Finally, based on cost comparison and comprehensive trade-offs, the target driving strategy is determined from the collision and avoidance scenarios, fully considering the balance between safety and driving efficiency, enabling flexible selection of the most appropriate driving method in complex traffic environments.

[0024] Overall, this application realizes forward-looking decision-making on vehicle driving strategies, which not only helps to reduce the losses caused by collisions, but also effectively avoids unnecessary risks, improves the vehicle's response capabilities when facing collision risks, and enhances driving safety. At the same time, it also significantly improves the rationality and scientificity of vehicle driving strategies, effectively reducing the probability of safety accidents and various possible losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above and other purposes, features, and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0026] Figure 1 The figure is a flow chart of a method for determining a vehicle driving strategy provided in one embodiment of the present application.

[0027] Figure 2 The figure shows a flow chart of generating at least one collision solution and at least one risk avoidance solution provided by an embodiment of the present application.

[0028] Figure 3 Shown is a flow chart of a vehicle driving strategy determination method provided by another embodiment of the present application.

[0029] Figure 4 Shown is a flow chart of determining a target driving strategy provided by an embodiment of the present application.

[0030] Figure 5 The figure is a flow chart of a vehicle mixed traffic control method provided by an embodiment of the present application.

[0031] Figure 6 Shown is a structural diagram of a vehicle driving strategy determination device provided in one embodiment of the present application.

[0032] Figure 7 Shown is a schematic structural diagram of a vehicle mixed traffic control device provided in one embodiment of the present application.

[0033] Figure 8 Shown is a schematic structural diagram of an unmanned vehicle provided in one embodiment of the present application. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0035] Figure 1 FIG. 1 is a flow chart of a method for determining a vehicle driving strategy according to an embodiment of the present application. Figure 1 As shown, the method includes the following steps.

[0036] Step S110 : When there is a risk of collision between the target vehicle and surrounding objects, at least one collision plan and at least one risk avoidance plan are generated.

[0037] Surrounding objects refer to other traffic participants within a certain range around the target vehicle. For example, surrounding objects include other vehicles, pedestrians, obstacles, etc.

[0038] Optionally, the target vehicle needs to use various sensors, such as cameras and lidar, to perceive information about the surrounding environment in real time, including the position, speed, acceleration, type, etc. of surrounding objects. Based on the perceived information about surrounding objects, the collision risk between the target vehicle and surrounding objects is assessed. For example, when the motion trajectory, speed, and other factors of the target vehicle and surrounding objects interact, which may lead to a collision, it is considered that there is a collision risk. In one implementation method, the possibility and severity of the collision can be calculated based on factors such as the relative speed, distance, and respective acceleration of the two vehicles. If the calculation result exceeds a certain threshold, it is considered that there is a collision risk.

[0039] Furthermore, when it is determined that there is a collision risk, at least one collision plan and at least one avoidance plan are generated. Specifically, a collision plan refers to a collision response method adopted when the target vehicle cannot avoid a collision. When generating a collision plan, factors such as the vehicle's own physical characteristics and passenger safety need to be considered. An avoidance plan refers to an evasive response method adopted by the target vehicle to avoid a collision. Exemplarily, avoidance plans include emergency braking, emergency lane changes, accelerated avoidance, etc. For example, the posture of the target vehicle can be controlled so that the collision point is as close as possible to the stronger part of the vehicle structure to avoid serious impact on key parts such as the cockpit; or the collision angle can be adjusted so that the collision energy is more reasonably dispersed.

[0040] Step S120 , calculating the collision cost of each collision solution and the risk cost of each risk avoidance solution.

[0041] Collision costs are a quantified representation of the various losses and costs incurred when a target vehicle collides according to a specific collision scenario. For example, these losses include the extent of damage to the vehicle itself, potential injuries to passengers, damage to surrounding objects, and potential traffic disruptions.

[0042] Risk cost is a quantitative representation of the risk and potential losses faced by the target vehicle when executing a specific avoidance strategy. While the goal of an avoidance strategy is to avoid a collision, there may be certain uncertainties and other risks involved during its execution. For example, the avoidance maneuver may result in loss of vehicle control or the risk of a new collision with other nearby objects. These factors, taken together, constitute the risk cost of the avoidance strategy.

[0043] Optionally, before calculating collision and risk costs, a corresponding cost calculation model can be established. The collision cost model comprehensively considers factors such as the vehicle's physical structure, materials, and the location of key components to assess vehicle damage costs. Passenger injury costs are assessed based on human physiological characteristics and the protective effectiveness of safety features such as seat belts. Historical traffic accident data can also be used to analyze the impact of different types of collisions on traffic disruptions, thereby establishing a mathematical model that comprehensively reflects collision losses.

[0044] The risk cost model requires analyzing factors such as the difficulty of executing an avoidance maneuver, the complexity of the surrounding traffic environment, and traffic regulations. For example, when making an emergency lane change, it's important to consider the impact of lane change distance, vehicle speed, and the distance to the vehicle behind on lane change safety, thereby establishing a model that accurately measures avoidance risk.

[0045] The vehicle then uses its own sensors and information from its surroundings to obtain the parameters needed to calculate collision and risk costs. These parameters are then substituted into the corresponding cost calculation model to calculate the collision cost for each collision scenario and the risk cost for each avoidance scenario.

[0046] Step S130 : determining a target driving strategy from at least one collision solution and at least one avoidance solution based on the collision costs of each collision solution and the risk costs of each avoidance solution.

[0047] In this embodiment, the target driving strategy refers to the optimal driving strategy selected from collision scenarios and risk avoidance scenarios after comprehensively considering collision costs and risk costs. It aims to balance safety and driving efficiency so that the target vehicle can drive in the most reasonable manner under the current traffic environment, thereby minimizing the losses caused by collisions and effectively avoiding unnecessary risks.

[0048] In this embodiment, at least one collision scenario and at least one avoidance scenario are generated simultaneously, providing multiple possibilities for selecting the optimal driving strategy. Next, the collision cost of each collision scenario and the risk cost of each avoidance scenario are calculated, quantifying and visually demonstrating the potential losses and risks of different scenarios. Finally, based on cost comparisons and comprehensive trade-offs, the target driving strategy is determined from the collision and avoidance scenarios, fully considering the balance between safety and driving efficiency, enabling flexible selection of the most appropriate driving method in complex traffic environments.

[0049] Overall, this application realizes forward-looking decision-making on vehicle driving strategies, which not only helps to reduce the losses caused by collisions, but also effectively avoids unnecessary risks, improves the vehicle's response capabilities when facing collision risks, and enhances driving safety. At the same time, it also significantly improves the rationality and scientificity of vehicle driving strategies, effectively reducing the probability of safety accidents and various possible losses.

[0050] Figure 2 The figure shows a flow chart of generating at least one collision solution and at least one risk avoidance solution provided by an embodiment of the present application. Figure 1 Based on the embodiment shown, Figure 2 The embodiment shown is described below in detail. Figure 2 The embodiment shown and Figure 1 The differences and similarities between the illustrated embodiments are not described in detail.

[0051] like Figure 2 As shown, in this embodiment, when there is a risk of collision between the target vehicle and surrounding objects, generating at least one collision solution and at least one risk avoidance solution includes the following steps.

[0052] Step S210: When it is determined that there is a collision risk between the target vehicle and surrounding objects, at least one risk avoidance plan is generated.

[0053] Optionally, once a collision risk is determined, at least one avoidance plan is generated based on the current traffic conditions and vehicle driving status. For example, if the vehicle ahead suddenly stops, and the target vehicle is close to the leading vehicle and traveling at a high speed, emergency braking may be selected as the avoidance plan. If an obstacle suddenly appears to the side of the target vehicle and the vehicle behind it is far away, an emergency lane change may be selected to avoid the obstacle.

[0054] Specifically, in one implementation, the motion information of the target vehicle and the status data of the surrounding objects are obtained; based on the motion information of the target vehicle and the status data of the surrounding objects, a candidate avoidance sequence is generated; a feasibility check is performed on each candidate avoidance sequence, and the candidate avoidance sequence that passes the feasibility check is determined as the avoidance solution.

[0055] For example, motion information includes information related to the vehicle's driving state, such as the target vehicle's speed, acceleration, driving direction, and wheel angle. State data includes parameters describing the state of surrounding objects, such as their position, speed, size, and type.

[0056] Optionally, the target vehicle obtains its own motion information and status data of surrounding objects in real time through sensors such as cameras and wheel speed sensors. Then, based on the collected motion information and status data, a pre-designed risk avoidance strategy algorithm is used to generate candidate risk avoidance sequences containing different combination actions. Among them, the candidate risk avoidance sequence includes a combination of one or more actions of steering, braking and acceleration, such as steering first and then braking, accelerating only, etc. Finally, the candidate risk avoidance sequence is verified through a series of rules and conditions to determine whether it can be executed safely and effectively in the current environment to avoid collisions without affecting the normal driving of the vehicle. It can be understood that only candidate risk avoidance sequences that pass these verifications can be determined as the final risk avoidance plan.

[0057] This solution first generates candidate avoidance sequences containing a variety of action combinations, increasing the diversity and flexibility of avoidance strategies and better adapting to complex and changing traffic scenarios. It then rigorously verifies the feasibility of each candidate avoidance sequence to identify safe, reliable, and feasible avoidance solutions. This effectively reduces the risk of avoidance failure or secondary accidents, and improves the vehicle's ability to respond to collision risks.

[0058] For example, assume a target vehicle is traveling at 50 km / h on a city road. The vehicle ahead suddenly stops, and the target vehicle is close to the vehicle ahead, posing a collision risk. At this point, the target vehicle obtains information such as its own speed and acceleration, as well as the position and speed of the vehicle ahead. Based on this information, multiple candidate avoidance sequences are generated, such as:

[0059] Sequence 1: Brake first, then change lanes to the left if the braking distance is insufficient.

[0060] Sequence 2: Make an emergency lane change to the right to avoid the collision.

[0061] Sequence 3: Accelerate to overtake and avoid the suddenly stopped vehicle in front.

[0062] Next, sequence 1 is verified: the braking distance is calculated based on the target vehicle's speed and braking performance. If the calculated braking distance is greater than the actual distance to the vehicle ahead, the lane change is considered feasible. The left lane is checked for sufficient space and clear of other vehicles. The lane change is also considered to comply with local traffic regulations.

[0063] Verify sequence 2: Check whether there are any obstacles or vehicles in the right lane, whether the safe distance requirements for lane change are met, and whether the driving trajectory after lane change will cause a collision with other objects on the right.

[0064] Verify sequence 3: whether accelerating to overtake complies with the traffic rules of the current road section (such as whether overtaking is allowed), whether there is enough space to pass safely after acceleration without colliding with oncoming vehicles, etc.

[0065] Ultimately, only candidate avoidance sequences that pass all checks will be determined as avoidance plans. For example, if Sequence 1 meets the braking distance and lane change requirements under the current environment, and the left lane change is legal and safe, it will be determined as the avoidance plan and executed.

[0066] Step S220: Generate a corresponding collision plan based on at least one risk avoidance plan.

[0067] Optionally, for each avoidance plan, consider various failure scenarios that may be encountered during its actual execution. For example, the avoidance plan is to change lanes to the left, but other vehicles or obstacles may suddenly appear in the left lane, making the lane change impossible to complete; or the avoidance plan is emergency braking, but the braking distance may be insufficient due to factors such as slippery road conditions, and the collision cannot be avoided. Then, based on the failure of the avoidance plan, determine the possible collision scenarios. For example, if the left lane change avoidance fails, a side collision with a vehicle that suddenly appears on the left may occur; if the emergency braking fails, a rear-end collision with the vehicle in front may occur. Finally, generate a corresponding collision plan for the determined collision scenario. In the collision plan, it is necessary to consider how to protect the safety of the occupants in the car, minimize vehicle damage, and reduce the impact on other traffic participants when a collision occurs.

[0068] More specifically, based on at least one risk avoidance plan, a corresponding collision plan is generated, including: for each risk avoidance plan, predicting the execution process of the risk avoidance plan; if the risk avoidance plan fails to be executed, determining the potential collision object and / or potential collision position after the risk avoidance plan is executed; based on the potential collision object and / or potential collision position after the risk avoidance plan is executed, generating a collision plan corresponding to the risk avoidance plan.

[0069] Failure indicates that the target vehicle is unable to avoid a collision with a surrounding object. Potential collision objects are surrounding objects that the target vehicle could collide with if the avoidance plan fails. Potential collision locations are locations where the target vehicle could collide if the avoidance plan fails.

[0070] Optionally, the execution process of the risk avoidance plan is predicted by sensors and related algorithms. Taking emergency lane change as an example, the sensor will monitor information such as vehicle speed and steering wheel angle, and the related algorithm will predict the vehicle's lane change trajectory and the time required. If the risk avoidance plan fails to be executed, the potential collision object and position are determined based on the prediction results. For example, when changing lanes, the vehicle behind the side enters the blind spot, the potential collision object is the vehicle, and the potential collision position is behind the target vehicle. Finally, a collision plan is generated based on the potential collision object and position, and the associated information of the collision plan includes the collision object and / or collision position. Exemplarily, the collision plan includes adjusting the vehicle posture, controlling the vehicle so that its side protection structure contacts the obstacle; or reducing the vehicle speed to reduce the collision speed and impact force.

[0071] This solution effectively improves vehicle safety in complex traffic environments and reduces accident losses by predicting the risk avoidance process and planning collision response strategies in advance.

[0072] Furthermore, the collision solution corresponding to the avoidance solution includes collision posture optimization instructions and / or a collision energy allocation strategy. Based on the potential collision object and / or potential collision position after the avoidance solution is executed, a collision solution corresponding to the avoidance solution is generated, including: generating collision posture optimization instructions based on the type of potential collision object and / or potential collision position; and / or generating a collision energy allocation strategy based on the potential collision position and the distribution of the target vehicle's buffer zone.

[0073] The collision posture optimization command is used to instruct the optimization of the collision position and / or collision angle, adjusting the vehicle's posture during a collision. The goal is to ensure that the target vehicle contacts the collision object in a relatively safe manner through reasonable posture adjustment, thereby reducing injuries to occupants and damage to the vehicle. The collision energy distribution strategy includes a distribution rule that distributes the impact energy generated by the collision to the buffer zone according to a preset ratio. The goal is to reduce the impact force locally through reasonable energy distribution, thereby reducing damage.

[0074] Optionally, when generating collision posture optimization instructions, the system determines the potential collision targets and locations after a failed avoidance plan is executed, including information such as their type, size, and location, as well as their distribution around the target vehicle. For example, if the target is a pedestrian, the system attempts to adjust the vehicle's posture so that the side of the vehicle contacts the pedestrian, reducing the possibility of a direct impact with a critical pedestrian area. For vehicles, the system attempts to ensure that the two vehicles contact at a relatively low speed and at a small angle to avoid a head-on collision. For example, if the collision occurs on the side of the vehicle, the system adjusts the vehicle's posture so that the side guard structure contacts the collision target. If the collision occurs head-on, the system attempts to adjust the vehicle's posture so that buffer zones, such as the engine compartment, can effectively absorb energy in a head-on collision.

[0075] Optionally, when generating a collision energy distribution strategy, the specific location of the collision is determined, such as the left front portion of the vehicle. It is understood that different buffer zones have different energy absorption capacities and structural characteristics. This is further considered based on the distribution of buffer zones, such as the front, rear, and side locations of the vehicle. Finally, based on the collision location, the impact energy is rationally distributed to each buffer zone. For example, through the vehicle's structural design and material properties, some energy can be directed to the frame's longitudinal and transverse beams, allowing them to share the impact force and avoid localized excessive energy absorption that could lead to severe deformation or damage.

[0076] When risk avoidance fails, this solution provides a final protective barrier for the vehicle by optimizing the collision posture and energy distribution strategy, effectively reducing the damage caused by the collision and protecting the personal and property safety of the occupants in the vehicle and surrounding traffic participants.

[0077] In general, the schemes of step S210 and step S220 in this embodiment first generate at least one risk avoidance plan when there is a risk of collision between the target vehicle and surrounding objects. Based on the generated risk avoidance plan, a corresponding collision plan is further generated to prepare for possible collisions, thus forming a comprehensive risk response system.

[0078] Figure 3 The figure shows a flow chart of a method for determining a vehicle driving strategy provided by another embodiment of the present application. Figure 1 Based on the embodiment shown, Figure 3 The embodiment shown is described below in detail. Figure 3 The embodiment shown and Figure 1 The differences and similarities between the illustrated embodiments are not described in detail.

[0079] like Figure 3 As shown, in this embodiment, when there is a risk of collision between the target vehicle and surrounding objects, before generating at least one collision plan and at least one risk avoidance plan, the following steps are also included.

[0080] Step S310: Acquire the motion information of the target vehicle and the status data of the surrounding objects.

[0081] Optionally, the motion information of the target vehicle includes at least one of the following information: the target vehicle's posture, velocity, acceleration, kinematic parameters, dynamic parameters, etc. The state data of the surrounding objects includes at least one of the following data: the position, velocity, size, motion direction, etc. of the surrounding objects.

[0082] For example, information about the target vehicle and surrounding objects can be collected through sensors (such as millimeter-wave radar, lidar, and cameras).

[0083] Step S320: generating at least one predicted trajectory of the target vehicle within a future target time based on the motion information of the target vehicle.

[0084] Predicting a trajectory refers to predicting the path that a target vehicle may travel within a future target time based on its motion information, and usually includes position information at multiple time points.

[0085] Optionally, the acquired motion information (such as position, velocity, acceleration, etc.) is used as input and combined with the dynamic model or kinematic model of the target vehicle to predict at least one predicted trajectory within the future target time for subsequent collision risk assessment.

[0086] In step S330 , if it is determined based on the state data of the surrounding objects that the predicted trajectory of the target vehicle overlaps with the surrounding objects, it is determined that there is a collision risk between the target vehicle and the surrounding objects.

[0087] Specifically, the motion information includes at least one of posture, velocity, acceleration, kinematic parameters and dynamic parameters; the state data includes at least one of position, velocity, size and motion direction.

[0088] Overlap refers to the situation where the predicted trajectory of the target vehicle and the possible future positions of surrounding objects intersect or overlap in space.

[0089] Optionally, based on the state data of surrounding objects, the possible location ranges of these objects within a future target time are predicted. These location ranges are compared with the predicted trajectory of the target vehicle to determine whether there is spatial overlap. In one implementation, if there is overlap, a collision risk is determined between the target vehicle and the surrounding objects.

[0090] In this solution, by acquiring the motion information and status data of the target vehicle and surrounding objects in real time, the predicted trajectory of the target vehicle is generated, and it is determined whether there is a risk of collision between it and the surrounding objects, thereby identifying potential dangers in advance, effectively enhancing the vehicle's active safety performance, and improving the vehicle's risk perception and response capabilities in complex traffic environments.

[0091] In another implementation, if it is determined that there is an overlap between the predicted trajectory of the target vehicle and the surrounding objects based on the status data of the surrounding objects, it includes: calculating the spatiotemporal overlap probability between the predicted trajectory of the target vehicle and the surrounding objects based on the status data of the surrounding objects; if the spatiotemporal overlap probability is greater than a preset probability threshold, it is determined that there is an overlap between the predicted trajectory of the target vehicle and the surrounding objects.

[0092] Specifically, the spatiotemporal overlap probability refers to the likelihood that the target vehicle's predicted trajectory will overlap with surrounding objects within a specific future time period and spatial region. The preset probability threshold is a pre-set probability value used to determine whether the spatiotemporal overlap probability meets the threshold sufficient to determine a collision risk.

[0093] Optionally, the system calculates the possible position distribution of surrounding objects within a target future time based on their motion states. Combined with the target vehicle's predicted trajectory, the probability of overlap between the two within the same spatial region at the same time is calculated. If the calculated spatiotemporal overlap probability exceeds a preset probability threshold, the predicted trajectory of the target vehicle is considered to overlap with the surrounding objects, indicating a collision risk.

[0094] For example, let's say there's a pedestrian crossing the road in front of a target vehicle. Based on the pedestrian's position, speed, and direction of movement, as well as the target vehicle's speed and predicted trajectory, the system calculates a 70% probability of spatiotemporal overlap between the target vehicle and the pedestrian in the crossing area within the next two seconds. If the preset probability threshold is 50%, a collision risk is determined.

[0095] In this scheme, the calculation of spatiotemporal overlap probability takes into account both time and space factors, making risk assessment more comprehensive and accurate. Secondly, the preset probability threshold provides a clear risk determination standard, improving the consistency and stability of the assessment. Finally, this scheme can identify potential collision risks earlier in complex traffic scenarios, providing more time for subsequent risk avoidance measures, thereby effectively reducing the probability of traffic accidents and improving driving safety and reliability.

[0096] Regarding step S120, in some embodiments, the collision cost of each collision scenario is calculated, including: for each collision scenario, using at least one cost calculation function in a collision cost model, based on the costs corresponding to the collision objects and / or collision positions associated with the collision scenario, and the cost corresponding to the target vehicle, calculating the collision cost of the collision scenario.

[0097] Specifically, the cost of the collision object is determined based on the type of the collision object or the value of the collision object.

[0098] Optionally, the costs associated with the collision object and / or collision location associated with the collision scenario, as well as the cost of the target vehicle, are used as input. A total collision cost for the collision scenario is then calculated by taking these cost factors into account using at least one cost calculation function in the collision cost model.

[0099] Taking the cost corresponding to the collision location as an example, let's assume the cost corresponding to the collision location of the collision object is 50,000 yuan, and the damage cost of the target vehicle itself is 30,000 yuan. Combining these costs through the cost calculation function yields a total collision cost of 80,000 yuan.

[0100] This approach incorporates the costs of the collision object and collision location into the collision cost calculation, ensuring it more accurately reflects the actual potential losses. Furthermore, the damage cost to the target vehicle itself is also considered, avoiding a one-sided cost assessment. This refined cost calculation method provides a more accurate basis for selecting the optimal driving strategy and facilitates more informed decision-making in complex traffic environments.

[0101] For step S120, in some embodiments, the risk cost of each risk avoidance plan is calculated, including: for each risk avoidance plan, at least one cost calculation function in the risk cost model is used to calculate the risk cost of the risk avoidance plan based on the type of risk avoidance action, the status data of surrounding objects, the motion information of the target vehicle, and at least one of the environmental parameters in which it is located.

[0102] Specifically, the risk cost is the expected cost of the risk event probability during the execution of the hedging plan. More specifically, the probability of a risk event occurring refers to the probability of various risk events that may occur during the execution of the hedging plan, such as the probability of a collision due to a failed hedging strategy or the probability of a collision with another vehicle. The expected cost is the expected value of the costs incurred during the execution of the hedging plan, calculated based on the probability of the risk event occurring.

[0103] Optionally, at least one of the following data is used as input: the type of risk avoidance action, the status data of surrounding objects, the motion information of the target vehicle, and the environmental parameters in which it is located. Furthermore, based on the input data, various risk events that may occur during the execution of the risk avoidance plan and their probability of occurrence are analyzed. Then, the risk cost of the risk avoidance plan is calculated by combining the probability of occurrence of the risk event and the corresponding cost assessment through at least one cost calculation function in the risk cost model. Among them, the type of risk avoidance action refers to the specific action taken by the vehicle in the risk avoidance plan, such as emergency braking, emergency lane change, acceleration avoidance, etc. Environmental parameters refer to the environmental conditions in which the target vehicle is located, such as road conditions, weather conditions, traffic flow, etc.

[0104] For example, assume that there is a vehicle that suddenly stops in front of the target vehicle, and the generated avoidance plan is to change lanes to the left. The cost calculation function in the risk cost model considers the following factors:

[0105] Type of evasive action: left lane change;

[0106] Surrounding object status data: There is a fast-moving vehicle in the left lane, relatively close;

[0107] Target vehicle motion information: Current speed is 50 km / h, and lane change time is 3 seconds;

[0108] Environmental parameters: slippery roads, light rain, and low visibility.

[0109] Finally, based on this data, the probability of a collision with the vehicle to the left during the avoidance plan is calculated to be 10%, along with other possible risk events (such as a 5% probability of vehicle loss of control) and their corresponding costs. Combining the probabilities and costs of these risk events, the risk cost of the avoidance plan is calculated.

[0110] This solution calculates the risk cost of the risk avoidance plan using a risk cost model by integrating multiple dimensional factors such as the type of risk avoidance action, surrounding object status data, target vehicle motion information and environmental parameters. This makes the risk cost calculation more scientific and targeted, providing a reliable basis for selecting the optimal risk avoidance strategy, thereby improving the rationality of vehicle decision-making in complex traffic environments.

[0111] Optionally, in some embodiments, the motion information of the target vehicle includes dynamic parameters, including load and / or center of gravity height, and the environmental parameters of the target vehicle include road adhesion coefficient and / or visibility.

[0112] The road adhesion coefficient is a dimensionless parameter that measures the friction between the road surface and the tires. It reflects the adhesion between the vehicle's tires and the road surface, and its value typically ranges between 0 and 1. As you can understand, a higher adhesion coefficient means greater friction between the tires and the road, and better braking performance and handling stability. Visibility refers to the maximum distance at which the driver or vehicle's perception system can clearly see objects or obstacles ahead under current environmental conditions, typically measured in meters (m) or feet (ft).

[0113] For example, assume that the target vehicle is traveling on a slippery road with a low road adhesion coefficient and reduced visibility due to fog. The vehicle is heavily loaded and has a high center of gravity. In the evasion scenario, the vehicle needs to change lanes urgently. Due to the heavy load and high vehicle inertia, a greater centrifugal force is required when changing lanes, and the higher center of gravity may cause the vehicle to tilt more easily when changing lanes. The low road adhesion coefficient reduces the friction between the tires and the road, reducing the stability of lane changes. Low visibility may delay the driver's or system's reaction time, increasing the risk of evasion failure. Taking all these factors into consideration, the risk cost model will calculate a higher risk cost because these conditions increase the possibility of evasion failure, which may lead to more serious consequences.

[0114] This plan makes the calculation of risk cost more accurate by taking into account multiple practical factors, which helps to make more reasonable risk hedging decisions.

[0115] Figure 4 The figure shows a flow chart of determining a target driving strategy according to an embodiment of the present application. Figure 1Based on the embodiment shown, Figure 4 The embodiment shown is described below in detail. Figure 4 The embodiment shown and Figure 1 The differences and similarities between the illustrated embodiments are not described in detail.

[0116] like Figure 4 As shown, in this embodiment, based on the collision costs of each collision solution and the risk costs of each risk avoidance solution, a target driving strategy is determined from at least one collision solution and at least one risk avoidance solution, including the following steps.

[0117] Step S410 : comparing the collision cost of the collision solution and the risk cost of the risk avoidance solution, and selecting the solution with the smallest value as the target driving strategy.

[0118] Specifically, the collision cost of each collision plan and the risk cost of each risk avoidance plan are obtained. Then, the collision cost of each collision plan and the risk cost of each risk avoidance plan are compared one by one, and the plan with the smallest cost value is selected as the target driving strategy.

[0119] For example, in a complex traffic scenario, a target vehicle needs to choose between two options: a collision option with a collision cost of 100,000 yuan and a risk avoidance option with a risk cost of 80,000 yuan. Since the cost of 80,000 yuan is less than 100,000 yuan, the risk avoidance option is selected as the target driving strategy. This cost-comparison approach intuitively selects the optimal driving option for the given situation, balancing safety and economy.

[0120] Step S420 : selecting a set of solutions that meet a safety threshold from the collision solutions and the risk avoidance solutions, and selecting the solution with the lowest cost from the set of solutions as the target driving strategy.

[0121] The safety threshold refers to a pre-set minimum standard for measuring the safety of a solution. Only solutions that meet or exceed this standard will be considered.

[0122] Optionally, a safety assessment is performed on all collision and avoidance scenarios, selecting those that meet safety thresholds to form a set of scenarios. Within the set, the cost (collision cost or risk cost) of each scenario is compared, and the lowest-cost scenario is selected as the target driving strategy.

[0123] For example, a target vehicle faces multiple collision and avoidance scenarios. After a safety assessment, only Scenario C meets the safety threshold, with a collision cost of 120,000 yuan. Among the avoidance scenarios, Scenario A and Scenario B meet the safety threshold, with risk costs of 80,000 yuan and 100,000 yuan, respectively. The scenario set now includes Scenario C, Scenario A, and Scenario B. After comparing the costs of these three scenarios, Scenario A, with the lowest cost, is selected as the target driving strategy. This approach ensures that the most economical driving strategy is selected while meeting safety requirements.

[0124] Figure 5 FIG. 1 is a flow chart of a vehicle mixed traffic control method provided by an embodiment of the present application. Figure 5 As shown, the method includes the following steps.

[0125] Step S510 : When there is a risk of collision between the unmanned vehicle and a manned vehicle, a target driving strategy corresponding to the unmanned vehicle is determined.

[0126] An unmanned vehicle is a vehicle that can travel autonomously without a human operator. A manned vehicle is a vehicle controlled by a human operator. The target driving strategy is obtained based on the vehicle driving strategy determination method described in the aforementioned embodiment.

[0127] Optionally, while the unmanned vehicle is in motion, its relative position and speed with the manned vehicle are monitored in real time to assess collision risk. Once a risk is identified, the aforementioned method is used to determine the optimal target driving strategy.

[0128] Step S520: Control the driving of the unmanned vehicle based on the target driving strategy.

[0129] Optionally, the autonomous vehicle's control system generates specific control instructions based on the target driving strategy, such as adjusting vehicle speed and steering. During driving, the autonomous vehicle continuously monitors environmental changes and driving status, dynamically adjusting control instructions to ensure effective execution of the driving strategy.

[0130] For example, an autonomous vehicle detects a sudden stop in front of a manned vehicle, posing a collision risk. By evaluating the costs and risks of various possible driving strategies (such as emergency braking and lane changes), the optimal target driving strategy is determined to be emergency braking. The autonomous vehicle's control system then executes the emergency braking command, smoothly decelerating the vehicle and successfully avoiding a collision with the vehicle ahead.

[0131] This solution uses the aforementioned method to determine the optimal driving strategy and control vehicle driving accordingly when there is a risk of collision between an unmanned vehicle and a manned vehicle. On the one hand, it ensures that the unmanned vehicle can make decisions quickly and accurately when faced with complex traffic conditions, thereby reducing the probability of collision with manned vehicles. On the other hand, based on a comprehensive assessment of cost and risk, it optimizes the driving path and speed of the unmanned vehicle and improves driving efficiency.

[0132] Combined with the above Figures 1 to 5 , describes the method embodiment of the present application in detail, and the following is combined with Figure 6 and Figure 7 , the device embodiment of the present application is described in detail. It should be understood that the description of the method embodiment corresponds to the description of the device embodiment, so for parts not described in detail, reference can be made to the previous method embodiment.

[0133] Figure 6 The figure shows a schematic diagram of the structure of a vehicle driving strategy determination device provided by an embodiment of the present application. Figure 6 As shown, the vehicle driving strategy determination device 60 provided in the embodiment of the present application includes:

[0134] A generation module 610 is configured to generate at least one collision plan and at least one avoidance plan when a collision risk exists between the target vehicle and surrounding objects. The collision plan refers to a collision response method adopted by the target vehicle when a collision is unavoidable, and the avoidance plan refers to an evasive response method adopted by the target vehicle to avoid a collision.

[0135] A calculation module 620 is used to calculate the collision cost of each collision plan and the risk cost of each risk avoidance plan;

[0136] The first determination module 630 is configured to determine a target driving strategy from at least one collision solution and at least one avoidance solution based on the collision costs of the collision solutions and the risk costs of the avoidance solutions.

[0137] In one embodiment of the present application, the generation module 610 is further configured to generate at least one risk avoidance plan when it is determined that there is a risk of collision between the target vehicle and surrounding objects; and generate a corresponding collision plan based on the at least one risk avoidance plan.

[0138] In one embodiment of the present application, the generation module 610 is also used to obtain the motion information of the target vehicle and the status data of the surrounding objects; based on the motion information of the target vehicle and the status data of the surrounding objects, generate a candidate avoidance sequence, the candidate avoidance sequence including a combination of one or more actions of steering, braking and acceleration; perform a feasibility check on each candidate avoidance sequence, and determine the candidate avoidance sequence that passes the feasibility check as the avoidance plan.

[0139] In one embodiment of the present application, the generation module 610 is also used to predict the execution process of each risk avoidance plan; if the risk avoidance plan fails to be executed, the potential collision object and / or potential collision position after the risk avoidance plan is determined, and the execution failure indicates that the target vehicle cannot avoid collision with surrounding objects; based on the potential collision object and / or potential collision position after the risk avoidance plan is executed, a collision plan corresponding to the risk avoidance plan is generated, and the associated information of the collision plan includes the collision object and / or collision position.

[0140] In one embodiment of the present application, the collision scheme corresponding to the avoidance scheme includes a collision posture optimization instruction and / or a collision energy distribution strategy; the generation module 610 is also used to generate a collision posture optimization instruction based on the type of potential collision object and / or the potential collision position, and the collision posture optimization instruction is used to indicate collision position optimization and / or collision angle optimization; and / or, based on the distribution of the potential collision position and the buffer zone of the target vehicle, generate a collision energy distribution strategy, and the collision energy distribution strategy includes a distribution rule for dispersing the impact energy generated by the collision to the buffer zone according to a preset proportion.

[0141] In one embodiment of the present application, the generation module 610 is also used to obtain motion information of the target vehicle and status data of surrounding objects; based on the motion information of the target vehicle, generate at least one predicted trajectory of the target vehicle within a future target time; if, based on the status data of the surrounding objects, it is determined that there is an overlap between the predicted trajectory of the target vehicle and the surrounding objects, it is determined that there is a risk of collision between the target vehicle and the surrounding objects; wherein the motion information includes at least one of posture, velocity, acceleration, kinematic parameters and dynamic parameters; the status data includes at least one of position, velocity, size and direction of motion.

[0142] In one embodiment of the present application, the generation module 610 is also used to calculate the spatiotemporal overlap probability between the predicted trajectory of the target vehicle and the surrounding objects based on the status data of the surrounding objects; if the spatiotemporal overlap probability is greater than a preset probability threshold, it is determined that there is overlap between the predicted trajectory of the target vehicle and the surrounding objects.

[0143] In one embodiment of the present application, the calculation module 620 is also used to calculate the collision cost of each collision scenario based on the costs corresponding to the collision objects and / or collision positions associated with the collision scenario, and the cost corresponding to the target vehicle through at least one cost calculation function in the collision cost model; wherein the cost of the collision object is determined based on the type of the collision object or the value of the collision object.

[0144] In one embodiment of the present application, the calculation module 620 is also used to calculate the risk cost of each risk avoidance plan through at least one cost calculation function in the risk cost model, based on the type of risk avoidance action, status data of surrounding objects, motion information of the target vehicle and at least one of the environmental parameters in which it is located, wherein the risk cost is the expected cost of the probability of a risk event occurring during the execution of the risk avoidance plan.

[0145] In one embodiment of the present application, the motion information of the target vehicle includes dynamic parameters, which include load and / or center of gravity height, and the environmental parameters of the target vehicle include road adhesion coefficient and / or visibility.

[0146] In one embodiment of the present application, the first determination module 630 is also used to compare the numerical values ​​of the collision cost of the collision plan and the risk cost of the risk avoidance plan, and select the plan with the smallest numerical value as the target driving strategy; or, select a set of plans that meet the safety threshold from the collision plan and the risk avoidance plan, and select the plan with the lowest cost from the plan set as the target driving strategy.

[0147] Figure 7 The figure shows a schematic diagram of the structure of a vehicle mixed traffic control device provided by an embodiment of the present application. Figure 7 As shown, the vehicle mixed traffic control device 70 provided in the embodiment of the present application includes:

[0148] The second determination module 710 is configured to determine a target driving strategy corresponding to the unmanned vehicle when there is a risk of collision between the unmanned vehicle and the manned vehicle;

[0149] The control module 720 is used to control the driving of the unmanned vehicle based on the target driving strategy.

[0150] Below, reference Figure 8 To describe the unmanned vehicle according to an embodiment of the present application. Figure 8 Shown is a schematic structural diagram of an unmanned vehicle provided by an exemplary embodiment of the present application.

[0151] like Figure 8 As shown, the unmanned vehicle 80 includes one or more processors 801 and memory 802 .

[0152] The processor 801 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the unmanned vehicle 80 to perform desired functions.

[0153] The memory 802 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), a hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 801 may execute the program instructions to implement the methods of the various embodiments of the present application described above and / or other desired functions. The computer-readable storage medium may also store various contents, such as collision plans, risk avoidance plans, collision costs, and risk avoidance costs.

[0154] In one example, the unmanned vehicle 80 may further include an input device 803 and an output device 804 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0155] The input device 803 may include, for example, a keyboard, a mouse, and the like.

[0156] The output device 804 can output various information to the outside, including collision solutions, risk avoidance solutions, collision costs, risk avoidance costs, etc. The output device 804 can include, for example, a display, a speaker, a printer, a communication network and its connected remote output devices, etc.

[0157] Of course, to simplify, Figure 8 Only some of the components related to the present application in the unmanned vehicle 80 are shown, and components such as buses, input / output interfaces, etc. are omitted. In addition, the unmanned vehicle 80 may further include any other appropriate components depending on the specific application.

[0158] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present application described above in this specification.

[0159] The computer program product may be written in any combination of one or more programming languages ​​to implement the program code for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0160] In addition, an embodiment of the present application may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enables the processor to execute the steps of the method according to various embodiments of the present application described above in this specification.

[0161] The computer-readable storage medium may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0162] The basic principles of the present application have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this application are merely illustrative and not restrictive, and it should not be assumed that these advantages, strengths, and effects are required of each embodiment of this application. In addition, the specific details disclosed above are merely illustrative and facilitating understanding, and are not restrictive. The above details do not limit this application to necessarily being implemented using the above specific details.

[0163] The block diagrams of the devices, devices, equipment, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "include," "comprise," "have," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0164] It should also be noted that in the apparatus, device, and method of the present application, each component or each step can be decomposed and / or recombined, and such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0165] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0166] The above description has been provided for the purpose of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for determining a vehicle driving strategy, characterized in that: include: When there is a risk of collision between the target vehicle and surrounding objects, generating at least one collision plan and at least one avoidance plan, wherein the collision plan refers to a collision response method adopted by the target vehicle when the collision is unavoidable, and the avoidance plan refers to an evasive response method adopted by the target vehicle to avoid the collision; Calculate the collision cost of each collision plan and the risk cost of each hedging plan; determining a target driving strategy from the at least one collision scenario and the at least one avoidance scenario based on the collision costs of the respective collision scenarios and the risk costs of the respective avoidance scenarios; The determining of a target driving strategy from the at least one collision scenario and the at least one avoidance scenario based on the collision costs of the respective collision scenarios and the risk costs of the respective avoidance scenarios includes: comparing the collision cost of the collision solution and the risk cost of the risk avoidance solution, and selecting the solution with the smallest value as the target driving strategy; Alternatively, a set of solutions that meet a safety threshold is selected from the collision solutions and the risk avoidance solutions, and a solution with the lowest cost is selected from the set of solutions as the target driving strategy.

2. The vehicle driving strategy determination method according to claim 1, characterized in that: The generating of at least one collision solution and at least one risk avoidance solution when there is a risk of collision between the target vehicle and surrounding objects includes: generating the at least one risk avoidance plan when it is determined that there is a collision risk between the target vehicle and the surrounding objects; Based on the at least one avoidance plan, a corresponding collision plan is generated.

3. The vehicle driving strategy determination method according to claim 2, characterized in that: Generating at least one hedging solution includes: Acquiring motion information of the target vehicle and status data of the surrounding objects; generating a candidate avoidance sequence based on the motion information of the target vehicle and the state data of the surrounding objects, the candidate avoidance sequence comprising a combination of one or more actions of steering, braking, and accelerating; A feasibility check is performed on each candidate hedging sequence, and the candidate hedging sequence that passes the feasibility check is determined as the hedging solution.

4. The vehicle driving strategy determination method according to claim 2, characterized in that: The generating a corresponding collision solution based on the at least one risk avoidance solution includes: For each hedging plan, predict the execution process of the hedging plan; If the avoidance plan fails to be executed, determining a potential collision object and / or potential collision position after the avoidance plan is executed, wherein the execution failure indicates that the target vehicle cannot avoid a collision with the surrounding object; Based on the potential collision object and / or potential collision position after the avoidance plan is executed, a collision plan corresponding to the avoidance plan is generated, and the associated information of the collision plan includes the collision object and / or collision position.

5. The vehicle driving strategy determination method according to claim 4, characterized in that: The collision solution corresponding to the risk avoidance solution includes collision posture optimization instructions and / or collision energy distribution strategy; The generating of a collision solution corresponding to the risk avoidance solution based on the potential collision object and / or potential collision position after the risk avoidance solution is executed includes: generating the collision posture optimization instruction based on the type of the potential collision object and / or the potential collision position, wherein the collision posture optimization instruction is used to instruct collision position optimization and / or collision angle optimization; And / or, based on the distribution of the potential collision position and the buffer zone of the target vehicle, a collision energy distribution strategy is generated, wherein the collision energy distribution strategy includes a distribution rule for distributing the impact energy generated by the collision to the buffer zone according to a preset ratio.

6. The vehicle driving strategy determination method according to any one of claims 1 to 5, characterized in that: Before generating at least one collision solution and at least one risk avoidance solution when there is a risk of collision between the target vehicle and surrounding objects, the method further includes: Acquiring motion information of the target vehicle and status data of the surrounding objects; generating at least one predicted trajectory of the target vehicle within a future target time based on the motion information of the target vehicle; If it is determined based on the state data of the surrounding objects that the predicted trajectory of the target vehicle overlaps with the surrounding objects, then it is determined that there is a collision risk between the target vehicle and the surrounding objects; The motion information includes at least one of posture, velocity, acceleration, kinematic parameters and dynamic parameters; and the state data includes at least one of position, velocity, size and motion direction.

7. The method for determining a vehicle driving strategy according to claim 6, wherein: If, based on the state data of the surrounding objects, it is determined that there is overlap between the predicted trajectory of the target vehicle and the surrounding objects, the method includes: Calculating a spatiotemporal overlap probability between the predicted trajectory of the target vehicle and the surrounding objects based on the state data of the surrounding objects; If the spatiotemporal overlap probability is greater than a preset probability threshold, it is determined that there is overlap between the predicted trajectory of the target vehicle and the surrounding objects.

8. The vehicle driving strategy determination method according to any one of claims 1 to 5, characterized in that: The calculation of the collision cost of each collision solution includes: For each collision scenario, calculating the collision cost of the collision scenario based on the costs corresponding to the collision objects and / or collision locations associated with the collision scenario and the cost corresponding to the target vehicle using at least one cost calculation function in the collision cost model; The cost of the collision object is determined based on the type of the collision object or the value of the collision object.

9. The vehicle driving strategy determination method according to any one of claims 1 to 5, characterized in that: The calculation of the risk cost of each hedging solution includes: For each risk avoidance plan, the risk cost of the risk avoidance plan is calculated through at least one cost calculation function in the risk cost model based on the type of risk avoidance action, the status data of the surrounding objects, the motion information of the target vehicle and at least one of the environmental parameters in which it is located, wherein the risk cost is the expected cost of the probability of a risk event occurring during the execution of the risk avoidance plan.

10. The vehicle driving strategy determination method according to claim 9, characterized in that: The motion information of the target vehicle includes dynamic parameters, which include load and / or center of gravity height. The environmental parameters of the target vehicle include road adhesion coefficient and / or visibility.

11. A vehicle mixed traffic control method, characterized in that: include: In the event that there is a risk of collision between an unmanned vehicle and a manned vehicle, determining a target driving strategy corresponding to the unmanned vehicle, wherein the target driving strategy is obtained based on the method according to any one of claims 1 to 10; Based on the target driving strategy, the unmanned vehicle is controlled to drive.

12. An unmanned vehicle, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is used to execute the vehicle driving strategy determination method described in any one of claims 1 to 10, or the vehicle mixed traffic control method described in claim 11.

Images