Automatic driving compliance space-time motion planning method and device in urban scene

Abstract

The invention relates to the technical field of path planning, in particular to an automatic driving compliance space-time motion planning method and device in an urban scene, and the method comprises the steps: obtaining an urban road traffic regulation text and an expressway traffic regulation text, analyzing the urban road traffic regulation text and the expressway traffic regulation text, and obtaining an urban road traffic regulation text and an expressway traffic regulation text; generating compliance constraint information in the city scene; time-space semantic corridor information of the automatic driving vehicle is constructed according to the compliance constraint information in the city scene, and a compliance time-space feasible region of the automatic driving vehicle is constructed according to the time-space semantic corridor information; and constructing a safety potential field of the autonomous vehicle according to the compliance space-time feasible region, and planning a compliance target movement track of the autonomous vehicle according to the gradient of the safety potential field and the dynamic model of the autonomous vehicle, thereby realizing real-time generation of the autonomous vehicle which strictly complies with traffic laws and regulations in a complex city scene. And the automatic driving track is dynamic, feasible, safe and smooth.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of path planning, in particular to a method and device for planning a space-time motion of an autonomous vehicle in a city scenario. BACKGROUND

[0002] The space-time motion planning technology plays a very important role in the whole technical framework of autonomous driving. Currently, the mainstream motion planning of autonomous driving is based on search, sampling, optimization and learning methods. In terms of compliance, the planned path of autonomous driving needs to strictly comply with traffic regulations, including but not limited to speed limit, lane driving rules, right of way, etc. In terms of generating feasible domain, the motion planning of autonomous driving needs to consider the kinematic characteristics of the vehicle to generate a dynamic feasible domain, so as to ensure the smoothness and safety of the planned path. Therefore, there is an urgent need for a motion planning method that can meet the requirements of compliance, space-time semantic corridor generation and real-time in a complex urban environment. SUMMARY

[0003] The present application provides a method and device for planning a space-time motion of an autonomous vehicle in a city scenario, which realizes real-time generation of an autonomous driving trajectory that strictly complies with traffic regulations and is dynamically feasible, safe and smooth in a complex city scenario.

[0004] The first aspect of the present application provides a method for planning a space-time motion of an autonomous vehicle in a city scenario, comprising the following steps: obtaining city road traffic regulation texts and highway traffic regulation texts, and parsing the city road traffic regulation texts and the highway traffic regulation texts to generate compliance constraint information in a city scenario; constructing space-time semantic corridor information of the autonomous vehicle according to the compliance constraint information in the city scenario, and constructing a compliance space-time feasible domain of the autonomous vehicle according to the space-time semantic corridor information; constructing a safety potential field of the autonomous vehicle according to the compliance space-time feasible domain, and planning a compliance target motion trajectory of the autonomous vehicle according to the gradient of the safety potential field and the dynamic model of the autonomous vehicle.

[0005] Optionally, the compliance constraint information in the city scenario includes one or more combinations of speed limit regulation constraint information, vehicle-to-vehicle safety distance constraint information, lane changing behavior specification information, right of way determination criteria and parking constraint information of the autonomous vehicle.

[0006] Optionally, the space-time semantic corridor information contains obstacle-type semantic elements and constraint-type semantic elements, wherein the obstacle-type semantic elements contain at least one of dynamic and static obstacle constraints and dynamic obstacle constraints, and the constraint-type semantic elements include at least one of traffic light constraints, space-time semantic corridor driving distance constraints and vehicle bounding box vertex constraints.

[0007] Optionally, the objective function of the compliance space-time feasible domain is:

[0008]

[0009] where t represents time, and κ1 and κ2 represent weight coefficients, represents the corridor size cost at t, represents the corridor center point cost at t.

[0010] Optionally, the first derivative h s and the second derivative h ss of the safety potential field are:

[0011]

[0012] where ρ safe represents the safety potential field value, D safe represents the normalized distance, a1 represents the control potential field strength, and b1 represents the control attenuation speed.

[0013] Optionally, the gradient of the safety potential field is calculated according to the following formula:

[0014]

[0015] where, represents the component of the repulsive force in the longitudinal direction (X-axis direction), represents the partial derivative of the normalized distance with respect to the global coordinate X of the vehicle, S represents the normalized distance, and X represents the X-axis coordinate, represents the component of the repulsive force in the transverse direction (Y-axis direction), represents the partial derivative of the normalized distance with respect to the global coordinate Y of the vehicle, Y represents the Y-axis coordinate, represents the curvature of the X direction itself (measures the bending degree of the potential field in the pure longitudinal (X) motion. The greater the value, the deeper or steeper the "potential well" in the longitudinal direction.), represents the square of the unit direction vector in the X direction, represents the second-order partial derivative of the normalized distance with respect to the X coordinate, represents the curvature of the Y direction itself (measures the bending degree of the potential field in the pure transverse (Y) motion. The greater the value, the steeper the "potential wall" in the transverse direction.), represents the square of the unit direction vector in the Y direction, represents the second-order partial derivative of the normalized distance with respect to the Y coordinate, represents the cross curvature (measures the coupling relationship between the longitudinal and transverse motions), represents the product of the partial derivative of the normalized distance S with respect to the X coordinate and the partial derivative of the normalized distance S with respect to the Y coordinate, denotes the partial derivative of S with respect to Y first and then with respect to X (this is a mixed partial derivative, which measures how fast the directional vector in the X direction changes when moving along the Y direction)

[0016] Optionally, a planning formula of the compliance target motion trajectory is:

[0017]

[0018] x(0) = x 初始 , u(0) = u 初始

[0019] x(T) = x 终止 , u(T) = u 终止

[0020] wherein, denotes a minimum target function of the generated trajectory, x(t) denotes a state variable, t denotes time, u(t) denotes a control variable, J(x(t), u(t)) denotes a cost function, denotes the derivative of the state variable x(t) with respect to time, f(x(t), u(t)) denotes a state equation, x(0) = x 初始 denotes an initial state constraint, u(0) = u 初始 denotes an initial control constraint, x(T) = x 终止 denotes a terminal state constraint, u(T) = u 终止 a terminal control constraint.

[0021] The second aspect embodiment of the present application provides a device for spatiotemporal motion planning of autonomous driving in an urban scenario, comprising: an acquisition module configured to acquire urban road traffic regulation texts and highway traffic regulation texts, and parse the urban road traffic regulation texts and the highway traffic regulation texts to generate compliance constraint information in the urban scenario; a construction module configured to construct spatiotemporal semantic corridor information of an autonomous driving vehicle according to the compliance constraint information in the urban scenario, and construct a compliance spatiotemporal feasible region of the autonomous driving vehicle according to the spatiotemporal semantic corridor information; and a planning module configured to construct a safety potential field of the autonomous driving vehicle according to the compliance spatiotemporal feasible region, and plan a compliance target motion trajectory of the autonomous driving vehicle according to a gradient of the safety potential field and a dynamics model of the autonomous driving vehicle.

[0022] Optionally, the compliance constraint information in the urban scenario comprises one or more of a combination of speed limit regulation constraint information, inter-vehicle safety distance constraint information, lane changing behavior specification information, priority right judgment criteria, and parking yielding constraint information of the autonomous driving vehicle.

[0023] ​Optionally, the spatiotemporal semantic corridor information comprises an obstacle-type semantic element and a constraint-type semantic element, wherein the obstacle-type semantic element comprises at least one of a static obstacle constraint and a dynamic obstacle constraint, and the constraint-type semantic element comprises at least one of a traffic light constraint, a spatiotemporal semantic corridor driving distance constraint, and a vehicle bounding box vertex constraint.

[0024] Optionally, the objective function of the compliance spatiotemporal feasible region is:

[0025]

[0026] wherein t represents a time, κ1 and κ2 represent weight coefficients, represents a corridor size cost at the time t, represents a corridor center point cost at the time t.

[0027] Optionally, the first derivative h s and the second derivative h ss of the safety potential field are:

[0028]

[0029] wherein ρ safe represents a safety potential field value, D safe represents a normalized distance of the safety potential field, a1 represents a control potential field intensity, and b1 represents a control attenuation speed.

[0030] Optionally, the calculation formula of the gradient of the safety potential field is:

[0031]

[0032] wherein, represents a component of the repulsive force in the longitudinal direction (X-axis direction), represents a partial derivative of the normalized distance with respect to the global coordinate X of the vehicle, S represents the normalized distance, and X represents the X-axis coordinate, represents a component of the repulsive force in the transverse direction (Y-axis direction), represents a partial derivative of the normalized distance with respect to the global coordinate Y of the vehicle, Y represents the Y-axis coordinate, represents the curvature of the X direction itself (measures the bending degree of the potential field in the pure longitudinal (X) motion. The greater the value, the deeper or steeper the "potential well" in the longitudinal direction is.), and represents the square of the unit directional vector in the X direction, represents the second-order partial derivative of the normalized distance with respect to the X coordinate, represents the curvature of the Y direction itself (measures the bending degree of the potential field in the pure transverse (Y) motion. The greater the value, the steeper the "potential wall" in the transverse direction is.), and represents the square of the unit directional vector in the Y direction, Let denote the second partial derivative of the normalized distance with respect to the Y-coordinate. This indicates the cross curvature (a measure of the coupling relationship between longitudinal and lateral motion). This represents the product of the partial derivative of the normalized distance S with respect to the X coordinate and the partial derivative of the normalized distance S with respect to the Y coordinate. This means that the normalized distance S is first derived with respect to Y, and then with respect to X (this is the mixed partial derivative, which measures the direction vector in the X direction when moving along the Y direction). How fast things are changing.

[0033] Optionally, the formula for planning the trajectory of the compliance target is:

[0034]

[0035] x(0)=x 初始 u(0)=u 初始

[0036] x(T)=x 终止 u(T)=u 终止

[0037] in, Let J(x(t), u(t)) represent the objective function for minimizing the generated trajectory, where x(t) represents the state variable, t represents time, u(t) represents the control variable, and J(x(t), u(t)) represents the cost function. Let f(x(t),u(t)) represent the time derivative of the state variable x(t), and let f(x(t),u(t)) represent the state equation, where x(0) = x 初始 Denotes the initial state constraint, u(0) = u 初始 Denotes the initial control constraint, x(T) = x 终止 Representing the terminal state constraint, u(T) = u 终止 Terminal control constraints.

[0038] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the spatiotemporal motion planning method for autonomous driving compliance in urban scenarios as described in the above embodiments.

[0039] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the spatiotemporal motion planning method for autonomous driving compliance in urban scenarios as described in the above embodiments.

[0040] Therefore, this application has the following beneficial effects:

[0041] The embodiments of the present application can analyze urban road traffic regulations and generate compliance constraint information under an urban scenario, construct a time-space semantic corridor information of an autonomous vehicle according to the compliance constraint information under the urban scenario, generate a compliance time-space feasible region of the autonomous vehicle according to the time-space semantic corridor information. Finally, based on the compliance time-space feasible region, a safety potential field is constructed, and a trajectory solving model considering dynamic constraints is established, which realizes real-time generation of an autonomous driving trajectory that strictly obeys traffic regulations, is dynamically feasible and safe and smooth under a complex urban scenario, and effectively solves the problem that the prior art cannot balance compliance, safety and real-time performance.

[0042] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0043] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, taken in conjunction with the accompanying drawings, in which:

[0044] Figure 1 A flow chart of a method for autonomous driving compliance time-space motion planning under an urban scenario according to an embodiment of the present application;

[0045] Figure 2 A block diagram of an apparatus for autonomous driving compliance time-space motion planning under an urban scenario according to an embodiment of the present application;

[0046] Figure 3 A structural schematic diagram of a vehicle according to an embodiment of the present application. DETAILED DESCRIPTION

[0047] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the drawings, in which the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below are exemplary and are intended to explain the present application, and cannot be understood as limiting the present application.

[0048] The method and device for automatic driving compliance spatiotemporal motion planning in a city scenario are described below with reference to the accompanying drawings. To address the problems mentioned in the background art, the present application provides a method for automatic driving compliance spatiotemporal motion planning in a city scenario. In the method, city road traffic regulations are analyzed to generate compliance constraint information in a city scenario, a spatiotemporal semantic corridor of an autonomous vehicle is constructed according to the compliance constraint information in the city scenario, and a compliance spatiotemporal feasible region of the autonomous vehicle is generated according to the spatiotemporal semantic corridor. Finally, based on the compliance spatiotemporal feasible region, a safety potential field is constructed, and a trajectory solving model considering dynamic constraints is established, which realizes real-time generation of an autonomous driving trajectory that strictly complies with traffic regulations, is dynamically feasible, and is safe and smooth in a complex city scenario, effectively solving the problem that existing technologies cannot balance compliance, safety, and real-time performance.

[0049] Specifically, Figure 1 A flowchart of a method for automatic driving compliance spatiotemporal motion planning in a city scenario is provided.

[0050] As Figure 1 shown, the method for automatic driving compliance spatiotemporal motion planning in a city scenario includes the following steps:

[0051] In step S101, city road traffic regulation texts and highway traffic regulation texts are obtained, and the city road traffic regulation texts and the highway traffic regulation texts are analyzed to generate compliance constraint information in a city scenario.

[0052] The compliance constraint information in a city scenario includes one or more combinations of speed limit regulation constraint information, vehicle-to-vehicle safety distance constraint information, lane changing behavior specification information, priority right of way determination criteria, and automatic driving vehicle parking and yielding constraint information.

[0053] Specifically, in the present application, the speed limit regulation constraint information is:

[0054] The maximum speed on a highway is not more than 120 km / h, and the minimum speed is not less than 60 km / h, i.e.

[0055] 60≤v 正常 ≤120 (1)

[0056] For two lanes in the same direction, the minimum speed on the left lane is 100 km / h

[0057] 100≤v 2，左 ≤120 (2)

[0058] For more than three lanes in the same direction, the minimum speed on the leftmost lane is 110 km / h

[0059] 90≤v 3，中 ≤120 (3)

[0060] If the speed limit sign indicates a speed that is inconsistent with the regulations for driving in the lane, obtain the speed value indicated by the speed limit sign through automatic driving perception information, and drive at the speed indicated by the speed limit sign.

[0061] The inter-vehicle safety distance constraint information is:

[0062] When a motor vehicle is driving on a highway and its speed exceeds 100 km / h, it should maintain a distance of more than 100 meters from the vehicle in front of the same lane

[0063] 100≤d 车速大于100与前车距离 (4)

[0064] When a motor vehicle is driving on a highway and its speed does not exceed 100 km / h, it should maintain a distance of more than 50 meters from the vehicle in front of the same lane

[0065] 50≤d 车速小于100与前车距离 (5)

[0066] The lane changing behavior specification information is:

[0067] On roads with more than two lanes in the same direction, a motor vehicle changing lanes should not affect the normal driving of vehicles in the relevant lanes, and the minimum safety distance d min between vehicles should be met:

[0068]

[0069] v f is the speed of the vehicle in front, v is the speed of the ego vehicle, ρ is the reaction time, α max is the maximum acceleration, β min is the minimum braking acceleration, and β max is the maximum braking acceleration.

[0070] The priority right determination criterion is:

[0071] Priority right rules are usually used at intersections or special road sections, and specify that certain vehicles have the right to pass through under certain conditions. For example, at an intersection without traffic lights, vehicles traveling straight usually have the right of way. If vehicle A arrives at the intersection earlier than or at the same time as vehicle B, vehicle A has the right of way, i.e.

[0072] If the arrival time of vehicle A at the intersection is earlier than the arrival time of vehicle B at the intersection, vehicle A has the right of way (7)

[0073] The automatic driving vehicle's parking yielding constraint information is:

[0074] Stop-and-yield rules require vehicles to stop under certain circumstances and wait for pedestrians or other vehicles to pass. For example, when encountering a stop sign, a vehicle must come to a complete stop and then proceed only after confirming it is safe to do so.

[0075] If a pedestrian appears or perceives the stop sign, then v = 0 (8)

[0076] In step S102, spatiotemporal semantic corridor information of autonomous vehicles is constructed based on compliance constraint information in urban scenarios, and compliance spatiotemporal feasible domain of autonomous vehicles is constructed based on spatiotemporal semantic corridor information.

[0077] It is understood that the embodiments of this application can provide compliance input for generating spatiotemporal semantic corridor information for autonomous vehicles based on the compliance constraint information of formulas (1)-(8), and construct the spatiotemporal semantic corridor information for autonomous vehicles based on the compliance constraint information in the above embodiments as input.

[0078] The spatiotemporal semantic corridor information includes obstacle-type semantic elements and constraint-type semantic elements. The obstacle-type semantic elements include at least one of static and dynamic obstacle constraints and one of dynamic obstacle constraints. The constraint-type semantic elements include at least one of traffic light constraints, spatiotemporal semantic corridor driving distance constraints, and vehicle bounding box vertex constraints.

[0079] In this embodiment, obstacle-type semantic elements mainly include dynamic and static obstacles and traffic lights. The trajectories of dynamic and static obstacles in the time domain can be viewed as a series of static obstacles combined along a discrete time dimension, forming a spatiotemporal semantic corridor of obstacles composed of a series of steps. Traffic light semantic elements are represented in a three-dimensional spatiotemporal map as obstacles occupying a specific longitudinal position on the road at a specific time. In addition to obstacle-type semantic elements, there are also vehicle state constraints. Speed ​​limit signs on the road can be considered as speed constraints within vehicle state constraints; during lane changes, vehicles need to ensure they do not cross lane lines for too long, and this constraint can be represented as a time constraint. Specifically:

[0080] 1) Dynamic and static obstacle constraints

[0081] Static obstacles (such as walls, curbs, stationary vehicles, etc.) are usually represented by geometric shapes (such as polygons, circles). Constraints require that the planned trajectory does not overlap with the obstacle area.

[0082] For circular obstacles, the Euclidean space obstacle avoidance method is used, based on the vehicle's position p(t) = (x(t), y(t)) and the center O of the static obstacle. i radius r i Obstacle avoidance constraints can be expressed as:

[0083] ||p(t)-Oi ||2≥r i +r ego +d safe (9)

[0084] where r ego is the radius of the circumscribed circle, d safe is the safety distance threshold, and ||·||2is the Euclidean distance representation.

[0085] For a polygonal obstacle, its interior can be represented as a set of linear inequalities A i p≤b i with constraints:

[0086] A i p(t)≤b i +d safe (10)

[0087] where A i is an m x 2 matrix (m is the number of edges of the polygon), each row corresponds to the normal vector of an edge of the polygon pointing to the interior of the polygon). b i is an m x 1 vector, each row corresponds to the offset of the edge to the origin (related to the normal vector).

[0088] For dynamic obstacles, the constraints of dynamic obstacles (such as other vehicles, pedestrians) need to consider the time dimension, usually described by a motion prediction model to describe its future trajectory.

[0089] For time-varying safety distance constraints, assume that the position of dynamic obstacle j at time t is O j (t), and the shape is approximately circular:

[0090] ||p(t)-O j ||2≥r j +r ego +d safe (t) (11)

[0091] where d safe (t) is the distance that increases with the speed v j (t), and k is a constant. d safe (t) = d0+ k · v j (t), d0is the initial distance between the vehicle and the obstacle, and v j (t) is the speed of dynamic obstacle j.

[0092] 2) Traffic light constraints

[0093] A red light can be rendered as an obstacle that occupies a certain longitudinal position and time period, during the red light period [t i , t i + Tf This can be likened to a red light being a static obstacle barrier, meaning the position of a static obstacle on the lane's coordinates, which can be represented as...

[0094] P red ={P t red ,t∈[t i ,t i +T f ]} (12)

[0095] A green light indicates that there are no obstacles ahead, meaning you can continue.

[0096] 3) Spatiotemporal semantic corridor travel distance constraints

[0097] Each step of the constructed spatiotemporal semantic corridor is a three-dimensional cube built in the Frenét coordinate system. The physical properties of each step of the spatiotemporal semantic corridor include (s, d, t, l, w, h, P). parent ,P child ), where s represents the vertical coordinate s, the horizontal coordinate d, and the time coordinate t in three-dimensional space, and l, w, h represent the length, width, and height of the spatiotemporal semantic corridor steps, respectively, and represents the parent node and child node of the spatiotemporal semantic corridor steps.

[0098] In the planning process, lanes and time intervals Δt are used to generate spatiotemporal semantic corridor steps. One spatiotemporal semantic corridor step corresponds to the set of all drivable areas on the corresponding lane within time Δt. In the i-th time interval, i.e., [t i ,t i Therefore, the i-th spatiotemporal semantic corridor step can be represented as:

[0099]

[0100]

[0101] Among them, v 初始 It is t 初始 The initial velocity at time [time] Indicates with v 初始 With an initial speed, the autonomous vehicle travels to time t. i The minimum speed and minimum longitudinal displacement at (the start time of the i-th time interval). and The table is v initial With an initial speed, the autonomous vehicle travels to time t. i The maximum speed and maximum longitudinal displacement are calculated as follows: +Δt (the end time of the i-th time interval). min a max v min vmax These represent the minimum acceleration, maximum acceleration, minimum speed, and maximum speed of an autonomous vehicle, respectively.

[0102] 4) Vehicle bounding box vertex constraints

[0103]

[0104] Among them, P k,1 P k,2 P k,3 P k,4 Let L be the left front, right front, left rear, and right rear vertices of the vehicle's bounding box at time k. f L r These are the distances from the center of the rear axle to the front of the vehicle and from the center of the rear axle to the rear of the vehicle, respectively, with W representing the width of the vehicle.

[0105] Furthermore, embodiments of this application can construct a spatiotemporal semantic feasible domain objective function based on the above constraints:

[0106] The cost of corridor size can be expressed as:

[0107]

[0108] The cost of the corridor center point can be expressed as:

[0109]

[0110] Finally, the objective function for minimizing the compliance spatiotemporal feasible region can be expressed as:

[0111]

[0112] formulas st (1)-(20)

[0113] Where t represents time, and κ1 and κ2 represent weight coefficients. This represents the cost of the corridor size at time t. Let J represent the cost at the center point of the corridor at time t, in minimizing the objective function J. STSC In addition, the embodiments of this application also need to satisfy the constraints defined by formulas (1) to (20).

[0114] In step S103, a safety potential field for autonomous vehicles is constructed based on the compliance spatiotemporal feasible domain, and the compliance target motion trajectory of autonomous vehicles is planned based on the gradient of the safety potential field and the dynamic model of autonomous vehicles.

[0115] It is understood that the embodiments of this application can construct the safety potential field of autonomous vehicles based on the compliance spatiotemporal feasible domain constructed in the above embodiments. Specifically,

[0116] First, the longitudinal d x and lateral d y distance values between ego vehicle and the jth obstacle vehicle at the ith time instant are calculated.

[0117]

[0118] where O x (i,j) denotes the longitudinal position of the jth obstacle vehicle at the ith time instant, Ego(i) denotes the longitudinal position of the ego vehicle at the ith time instant, y safe denotes the lateral safety threshold.

[0119] The rear longitudinal D x distance and lateral D y distance considering the target obstacle vehicle heading angle can be expressed as

[0120]

[0121] The longitudinal x n and lateral y n safety distances between ego vehicle and the jth obstacle vehicle are:

[0122]

[0123] where X0denotes the minimum longitudinal safety distance, Y0denotes the minimum lateral safety distance, denotes the ego vehicle longitudinal velocity, denotes the ego vehicle lateral velocity, T safe denotes the preset safety buffer time (e.g., brake reaction time), v j denotes the jth obstacle vehicle velocity, a n denotes the ego vehicle acceleration information.

[0124] The angle of the safety potential field (normalized direction angle of the obstacle relative to the ego vehicle) can be obtained as:

[0125]

[0126] where atan2 is the four-quadrant arctangent function, ensuring the angle range is in (-π, π], D x , D y denote the components of (d x , d y ) converted to the obstacle local coordinate system, considering the orientation of the obstacle through a rotation matrix, so that the distance calculation is aligned with the obstacle movement direction. x n denotes the longitudinal dynamic safety distance, y n denotes the lateral dynamic safety distance.

[0127] The normalized distance (normalized Euclidean distance of the current point to the obstacle) D of the safety potential field safe Can be expressed as:

[0128]

[0129] Therefore, the safety potential field value ρ safe Can be expressed as:

[0130]

[0131] Where a1 represents the control potential field intensity, b1 represents the control attenuation speed, and the larger b1 is, the faster the potential field attenuates.

[0132] Next, based on the safety potential field value, the safety potential field gradient is calculated,

[0133] The first derivative h s of the safety potential field and the second derivative h ss are:

[0134]

[0135] The partial derivative of the normalized distance with respect to the X and Y coordinates can be expressed as:

[0136]

[0137] γ safe represents the safety potential field angle.

[0138] Finally, the gradient of the potential field can be obtained:

[0139]

[0140] Further, according to the obtained gradient and the established dynamics model, the trajectory planning solution can be performed.

[0141] First, the Jacobian matrix with a matrix a of 8x8 is constructed, and the elements corresponding to the partial derivative of the vehicle dynamics equation can be expressed as:

[0142]

[0143] Where the state vector Control input: u = [δ f ,F x ] T

[0144]

[0145] respectively represent the change of vehicle longitudinal speed, lateral speed, yaw rate, change of roll rate, roll rate, global coordinate system X, Y, u = [delta f x T represent the front wheel steering angle, longitudinal force.

[0146] C f front tire cornering stiffness, C r rear tire cornering stiffness, l f distance from the center of mass to the front axle, l r distance from the center of mass to the rear axle, m total mass of the vehicle, m2 suspension mass, I z moment of inertia around the Z axis, I x moment of inertia around the X axis, h vertical distance from the roll center to the center of mass, B r roll damping of the suspension, K r stiffness of the suspension.

[0147] Finally, the above modeling of the automatic driving compliance spatiotemporal motion planning in the urban scene as an optimal control problem can enable the automatic driving to generate a compliance trajectory in a complex interactive scene. The specific form is as follows:

[0148]

[0149] x(0) = x 初始 , u(0) = u 初始

[0150] x(T) = x 终止 , u(T) = u 终止

[0151] ​​In summary, the embodiments of the present application convert complex traffic regulations (including speed limit regulations, safe distance between vehicles, lane changing behavior regulations, priority right determination, parking and yielding, etc.) into calculable mathematical constraint models (formulas 1-8), ensuring that the subsequently generated trajectories comply with the traffic regulations from the source. On the basis of compliance constraints, the spatial constraints of dynamic and static obstacles, traffic signal timing constraints, spatio-temporal semantic corridor boundary constraints, and vehicle collision envelope (bounding box) constraints are considered to construct a compliance feasible region that meets both regulatory requirements and environmental safety, accurately depicting the drivable area of the vehicle within a specific time and space. Based on the constructed compliance feasible region, the risk between the ego vehicle and other vehicles (obstacles) is quantified using the safety potential field theory. This method not only considers the relative distance, but also introduces dynamic factors such as heading angle, speed, and acceleration, calculates the normalized longitudinal and lateral safety distance, and constructs a dynamic safety potential field (formula 29) and its gradient (formula 32), thereby more accurately reflecting the real-time collision risk. Finally, the motion planning problem is modeled as an optimal control problem, with the objective function incorporating the effects of corridor size, center point distance, and safety potential field. During the solution process, a vehicle dynamics model (formula 33) is introduced to ensure that the generated trajectory not only meets the compliance and safety requirements, but also conforms to the vehicle's kinematic and dynamic characteristics, guaranteeing the smoothness and executability of the trajectory.

[0152] According to the automatic driving compliance spatio-temporal motion planning method in a city scene proposed in the embodiments of the present application, the city road traffic regulations are analyzed and compliance constraint information in a city scene is generated, the spatio-temporal semantic corridor information of the automatic driving vehicle is constructed according to the compliance constraint information in a city scene, and the automatic driving vehicle compliance spatio-temporal feasible region is generated according to the spatio-temporal semantic corridor information. Finally, based on the compliance spatio-temporal feasible region, a safety potential field is constructed, and a trajectory solving model considering dynamic constraints is established, realizing real-time generation of an automatic driving trajectory that strictly complies with traffic regulations, is dynamically feasible, safe, and smooth in a complex city scene, and effectively solving the problem that the existing technology cannot balance compliance, safety, and real-time performance.

[0153] Secondly, the automatic driving compliance spatio-temporal motion planning device in a city scene proposed in the embodiments of the present application is described with reference to the accompanying drawings.

[0154] Figure 2 is a block schematic diagram of the automatic driving compliance spatio-temporal motion planning device in a city scene of the embodiments of the present application.

[0155] As shown in Figure 2 , the automatic driving compliance spatio-temporal motion planning device 10 in a city scene includes an acquisition module 100, a construction module 200, and a planning module 300.

[0156] The acquisition module 100 is configured to acquire urban road traffic regulation texts and expressway traffic regulation texts, and analyze the urban road traffic regulation texts and the expressway traffic regulation texts to generate compliance constraint information in an urban scenario; the construction module 200 is configured to construct a space-time semantic corridor information of the autonomous vehicle according to the compliance constraint information in the urban scenario, and construct a compliance space-time feasible region of the autonomous vehicle according to the space-time semantic corridor information; the planning module 300 is configured to construct a safety potential field of the autonomous vehicle according to the compliance space-time feasible region, and plan a compliance target motion trajectory of the autonomous vehicle according to a gradient of the safety potential field and a dynamics model of the autonomous vehicle.

[0157] In an embodiment of the present application, the compliance constraint information in the urban scenario includes one or more of a combination of speed limit regulation constraint information, inter-vehicle safety distance constraint information, lane changing behavior specification information, priority right judgment criteria, and parking giving way constraint information of the autonomous vehicle.

[0158] In an embodiment of the present application, the space-time semantic corridor information includes an obstacle-type semantic element and a constraint-type semantic element, wherein the obstacle-type semantic element includes at least one of dynamic and static obstacle constraints and dynamic obstacle constraints, and the constraint-type semantic element includes at least one of traffic light constraints, space-time semantic corridor driving distance constraints, and vehicle bounding box vertex constraints.

[0159] In an embodiment of the present application, the objective function of the compliance space-time feasible region is:

[0160]

[0161] wherein t represents a time, κ1 and κ2 represent weight coefficients, represents a corridor size cost at t, represents a corridor center point cost at t.

[0162] In an embodiment of the present application, the first derivative h s and the second derivative h ss of the safety potential field are:

[0163]

[0164] wherein ρ safe represents a safety potential field value, D safe represents a normalized distance of the safety potential field, a1 represents a control potential field intensity, and b1 represents a control attenuation speed.

[0165] In an embodiment of the present application, the calculation formula of the gradient of the safety potential field is:

[0166]

[0167] Among them, among them, This represents the longitudinal component of the repulsive force (X-axis direction). S represents the partial derivative of the normalized distance with respect to the vehicle's global coordinate X, where S represents the normalized distance and X represents the X-axis coordinate. This represents the transverse component of the repulsive force (Y-axis direction). This represents the partial derivative of the normalized distance with respect to the vehicle's global coordinates Y, where Y represents the Y-axis coordinate. This represents the curvature in the X direction (a measure of the degree of curvature of the potential field in pure longitudinal (X) motion. A larger value indicates a deeper or steeper longitudinal "potential well"). It represents the square of the unit direction vector in the X direction. This represents the second-order partial derivative of the normalized distance with respect to the X-coordinate. This represents the curvature in the Y direction (a measure of the degree of curvature of the potential field in pure transverse (Y) motion; the larger the value, the steeper the transverse "potential wall"). This represents the square of the unit direction vector in the Y direction. Let denote the second partial derivative of the normalized distance with respect to the Y-coordinate. This indicates the cross curvature (a measure of the coupling relationship between longitudinal and lateral motion). This represents the product of the partial derivative of the normalized distance S with respect to the X coordinate and the partial derivative of the normalized distance S with respect to the Y coordinate. This means that the normalized distance S is first derived with respect to Y, and then with respect to X (this is the mixed partial derivative, which measures the direction vector in the X direction when moving along the Y direction). How fast things are changing.

[0168] In one embodiment of this application, the formula for planning the trajectory of the compliance target is:

[0169]

[0170] x(0)=x 初始 u(0)=u 初始

[0171] x(T)=x 终止 u(T)=u 终止

[0172] in, Let J(x(t), u(t)) represent the objective function for minimizing the generated trajectory, where x(t) represents the state variable, t represents time, u(t) represents the control variable, and J(x(t), u(t)) represents the cost function. Let f(x(t),u(t)) represent the time derivative of the state variable x(t), and let f(x(t),u(t)) represent the state equation, where x(0) = x 初始 Denotes the initial state constraint, u(0) = u初始 denotes initial control constraints, x(T)=x 终止 denotes terminal state constraints, u(T)=u 终止 terminal control constraints.

[0173] It should be noted that the foregoing explanation of the embodiment of the method for spatiotemporal motion planning of autonomous driving compliance in a city scene is also applicable to the embodiment of the device for spatiotemporal motion planning of autonomous driving compliance in a city scene, which will not be described here again.

[0174] The device for spatiotemporal motion planning of autonomous driving compliance in a city scene according to the embodiment of the present application analyzes city road traffic regulations and generates compliance constraint information in a city scene, constructs spatiotemporal semantic corridor information of an autonomous driving vehicle according to the compliance constraint information in a city scene, and generates a spatiotemporal feasible region of autonomous driving vehicle compliance according to the spatiotemporal semantic corridor information. Finally, based on the spatiotemporal feasible region of compliance, a safety potential field is constructed, and a trajectory solving model considering dynamic constraints is established, which realizes real-time generation of an autonomous driving trajectory that strictly obeys traffic regulations, is dynamically feasible, and is safe and smooth in a complex city scene, and effectively solves the problem that the prior art cannot balance compliance, safety, and real-time performance.

[0175] Figure 3 The vehicle according to the embodiment of the present application is provided with a structure diagram. The vehicle can include:

[0176] The memory 301, the processor 302, and the computer program stored in the memory 301 and executable on the processor 302.

[0177] The processor 302 implements the method for spatiotemporal motion planning of autonomous driving compliance in a city scene provided in the above embodiments when executing the program.

[0178] Further, the vehicle further includes:

[0179] The communication interface 303 is used for communication between the memory 301 and the processor 302.

[0180] The memory 301 is used to store the computer program executable on the processor 302.

[0181] The memory 301 can include a high-speed RAM (Random Access Memory, random access memory) memory, and can also include a non-volatile memory, such as at least one disk memory.

[0182] If the memory 301, the processor 302 and the communication interface 303 are implemented independently, the communication interface 303, the memory 301 and the processor 302 can be connected with each other through a bus and complete communication between each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 3 Only one thick line is used in the figure to represent the bus, but it does not mean that there is only one bus or only one type of bus.

[0183] Optionally, in a specific implementation, if the memory 301, the processor 302 and the communication interface 303 are integrated on a chip, the memory 301, the processor 302 and the communication interface 303 can complete communication between each other through an internal interface.

[0184] The processor 302 can be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0185] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the above-mentioned method for automatically driving compliance spatiotemporal motion planning in a city scene.

[0186] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms is not necessarily for the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0187] Furthermore, the terms "first", "second", etc. are used herein only to describe different steps or features and do not imply a relative importance or a specific order of steps or features. Thus, a feature defined with "first", "second", etc. can explicitly or implicitly include at least one of the feature. In the description of the present application, the meaning of "N" is at least two, for example, two, three, etc., unless otherwise explicitly specified.

[0188] Any process or method descriptions or blocks in flow charts or otherwise described herein represent embodiments of modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps, and alternate implementations are possible. The steps or functions described herein can be implemented in software, firmware, hardware, or a combination thereof. In one embodiment, the steps or functions described herein are implemented in software that is executable by a processing unit of a computer system.

[0189] It should be understood that aspects of the present application can be implemented in hardware, software, firmware, or combinations thereof. In the above embodiments, steps or functions can be implemented in software or firmware that is stored in memory and executed by a suitable instruction execution system. As with a hardware implementation, aspects of the present application can be realized with any of the many technologies for implementing software or firmware in hardware, including: a set of logic gates for the logical functions of the software, a dedicated integrated circuit, a PLD, etc.

[0190] Those of skill in the art will appreciate that the steps or functions of the methods described above can be carried out by a program for use with a computer system. The program can be stored in a computer readable storage medium, which is coupled to a computer system bus, which can carry information which the computer system can process. The program can cause the computer system to execute the steps or functions described above.

[0191] Although the embodiments of the present application have been shown and described above, it is to be understood that the above-described embodiments are merely exemplary, and are not to be taken as limiting the present application. Accordingly, those skilled in the art will appreciate that the embodiments described above are susceptible to variations and modifications other than those specifically described.

Claims

1. A spatiotemporal motion planning method for autonomous driving compliance in urban scenarios, characterized in that, Includes the following steps: Obtain the texts of urban road traffic regulations and highway traffic regulations, parse the texts of urban road traffic regulations and highway traffic regulations, and generate compliance constraint information in urban scenarios; Based on the compliance constraint information in the urban scenario, the spatiotemporal semantic corridor information of the autonomous vehicle is constructed, and the compliance spatiotemporal feasible domain of the autonomous vehicle is constructed based on the spatiotemporal semantic corridor information. Based on the compliance spatiotemporal feasible domain, a safety potential field for the autonomous vehicle is constructed. Based on the gradient of the safety potential field and the dynamic model of the autonomous vehicle, the compliance target motion trajectory of the autonomous vehicle is planned.

2. The spatiotemporal motion planning method for autonomous driving compliance in urban scenarios according to claim 1, characterized in that, The compliance constraints in the urban scenario include one or more combinations of speed limit regulations, safe distance constraints between vehicles, lane changing behavior regulations, right-of-way determination criteria, and stop and yield constraints for autonomous vehicles.

3. The spatiotemporal motion planning method for autonomous driving compliance in urban scenarios according to claim 1, characterized in that, The spatiotemporal semantic corridor information includes obstacle-type semantic elements and constraint-type semantic elements. The obstacle-type semantic elements include at least one of static and dynamic obstacle constraints and dynamic obstacle constraints. The constraint-type semantic elements include at least one of traffic light constraints, spatiotemporal semantic corridor driving distance constraints, and vehicle bounding box vertex constraints.

4. The spatiotemporal motion planning method for autonomous driving compliance in urban scenarios according to claim 1, characterized in that, The objective function of the compliance spatiotemporal feasible region is: Where t represents time, and κ1 and κ2 represent weight coefficients. This represents the cost of the corridor size at time t. This represents the cost of the corridor center point at time t.

5. The spatiotemporal motion planning method for autonomous driving compliance in urban scenarios according to claim 1, characterized in that, The first derivative h of the safety potential field s and the second derivative h ss for: Where, ρ safe D represents the safety potential field value. safe denoted by , a1 represents the normalized distance of the safety potential field, b1 represents the control potential field strength, and b1 represents the control decay rate.

6. The spatiotemporal motion planning method for autonomous driving compliance in urban scenarios according to claim 1, characterized in that, The formula for calculating the gradient of the safety potential field is: in, This represents the component of the repulsive force along the X-axis. Let S represent the partial derivative of the normalized distance with respect to the vehicle's global coordinates X, and let S represent the normalized distance. This represents the component of the repulsive force along the Y-axis. This represents the partial derivative of the normalized distance with respect to the vehicle's global coordinate Y. This represents the curvature of the x-axis itself. This represents the square of the unit direction vector along the X-axis. This represents the second-order partial derivative of the normalized distance with respect to the X-coordinate. This represents the curvature itself in the Y direction. This represents the square of the unit direction vector in the Y direction. This represents the second-order partial derivative of the normalized distance with respect to the Y-coordinate. Indicates the cross curvature.

7. The spatiotemporal motion planning method for autonomous driving compliance in urban scenarios according to claim 1, characterized in that, The formula for planning the trajectory of the compliance target is: x(0)=x 初始 ,u(0)=u 初始 x(T)=x 终止 ,u(T)=u 终止 in, Let J(x(t), u(t)) represent the objective function for minimizing the generated trajectory, where x(t) represents the state variable, t represents time, u(t) represents the control variable, and J(x(t), u(t)) represents the cost function. Let f(x(t),u(t)) represent the time derivative of the state variable x(t), and let f(x(t),u(t)) represent the state equation, where x(0) = x 初始 Denotes the initial state constraint, u(0) = u 初始 Denotes the initial control constraint, x(T) = x 终止 Representing the terminal state constraint, u(T) = u 终止 Terminal control constraints.

8. A spatiotemporal motion planning device for autonomous driving compliance in urban scenarios, characterized in that, include: The acquisition module is used to acquire urban road traffic regulations text and highway traffic regulations text, parse the urban road traffic regulations text and the highway traffic regulations text to generate compliance constraint information in urban scenarios; The construction module is used to construct the spatiotemporal semantic corridor information of the autonomous vehicle based on the compliance constraint information in the urban scenario, and to construct the compliance spatiotemporal feasible domain of the autonomous vehicle based on the spatiotemporal semantic corridor information. The planning module is used to construct the safety potential field of the autonomous vehicle based on the compliance spatiotemporal feasible domain, and to plan the compliance target motion trajectory of the autonomous vehicle based on the gradient of the safety potential field and the dynamic model of the autonomous vehicle.

9. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the spatiotemporal motion planning method for autonomous driving compliance in urban scenarios as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed, they implement the spatiotemporal motion planning method for autonomous driving compliance in urban scenarios as described in any one of claims 1-7.

Images