A trajectory planning method for unmanned vehicles
By using local trajectory planner and trajectory tracking controller in driverless car trajectory planning, combined with kinematic models and optimization parameters, the problem of low trajectory planning in the existing technology is solved, and more efficient trajectory planning and calculation are achieved Reduced time.
Patent Information
- Application Number
- CN202210664523.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-06-13
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2042-06-13
AI Technical Summary
The existing trajectory planning methods for driverless cars are difficult to improve trajectory planning efficiency and reduce calculation time while ensuring the accuracy of the model, and the generated trajectory is discontinuous or time-consuming.
The local trajectory planner is used to plan the local optimal trajectory based on the kinematic model, and calculate the optimal action sequence of the vehicle's front steering wheel through the trajectory tracking controller. Combining optimization parameters and constraints, the calculation complexity and time step length are reduced, and the calculation complexity and time step length are improved. Trajectory planning efficiency.
On the premise of ensuring the accuracy of the model, the trajectory planning efficiency is improved, the calculation time is reduced, and the safety and efficiency of the trajectory are ensured by optimizing parameters and constraints.
Smart Images

Figure CN114942642B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of unmanned driving technology, and in particular to a trajectory planning method for an unmanned driving vehicle. Background Art
[0002] Over the past few decades, the number of casualties caused by traffic accidents has increased every year. Autonomous vehicles can greatly reduce accidents caused by driver distraction and fatigue due to their fast operation and accurate perception. In addition to improving safety, autonomous vehicles can also greatly improve driving comfort, traffic efficiency and energy economy.
[0003] At present, the four main methods of trajectory planning are graph search-based methods, incremental search methods, curve interpolation methods, and numerical optimization methods. Among them, graph search finds the shortest path by traversing all environmental grids. However, the resulting path is not continuous and is therefore not suitable for autonomous vehicles. The incremental search method allows nodes to extend randomly toward the target in a continuous space. However, the generated trajectory is jerky and is usually not the optimal trajectory. The curve interpolation method can generate a smooth path, but the result of trajectory planning depends on the global waypoints, and the method is very time-consuming in a changing environment. In the prior art, numerical optimization methods are usually used to consider the constraints of roads and host vehicles. The trajectory is generated by constraints and objective functions. However, the optimization process needs to be executed synchronously at each time, which is time-consuming and requires higher-level hardware.
[0004] Therefore, based on the existing unmanned driving trajectory planning technology, how to improve the trajectory planning efficiency and reduce the calculation time while ensuring the accuracy of the model has become an urgent problem that technical personnel in this field need to solve. Summary of the invention
[0005] In view of the above problems, the present invention proposes a method for unmanned vehicle trajectory planning that solves at least some of the above technical problems. The method can effectively improve the efficiency of trajectory planning and reduce the calculation time.
[0006] The present invention provides a method for planning a trajectory of an unmanned vehicle, comprising the following steps:
[0007] S1. Obtaining the environment and vehicle status information of the unmanned vehicle to be trajectory planned; the environment and vehicle status information includes: vehicle status, vehicle position, environment information, traffic information and road information;
[0008] S2, inputting the environment and vehicle state information into a local trajectory planner, and planning a local optimal trajectory based on a kinematic model and corresponding evaluation indicators;
[0009] S3, inputting the planned local optimal trajectory into the trajectory tracking controller as the expected trajectory, taking the objective function including the optimization parameters as the evaluation basis, and calculating the optimal action sequence of the front steering wheel of the unmanned vehicle to be trajectory planned under the corresponding preset constraints; the optimization parameters include: lateral tracking error and control amount change rate;
[0010] S4. According to the optimal action sequence, the actuator of the unmanned vehicle to be trajectory planned is manipulated to ensure that the unmanned vehicle to be trajectory planned drives safely according to the planned trajectory.
[0011] Furthermore, the step S3 also includes: resampling the planned local optimal trajectory to convert a larger discrete time step into a smaller discrete time step; and inputting the resampled local optimal trajectory into a trajectory tracking controller as a desired trajectory.
[0012] Furthermore, in step S2, the local trajectory planner expresses the planning of the local optimal trajectory as an optimal control problem of an equation, and generates an optimal control sequence of control variables in a preset prediction range:
[0013]
[0014] In the above formula, L(X(t), U(t), t) is the cost function of the preset prediction range [t, t+T]; U(t) is the optimal control sequence within the preset prediction range [t, t+T]; f(X(t), U(t)) is the state space expression; X(t) is the state variable.
[0015] Furthermore, the cost function includes environmental cost and trajectory cost; the environmental cost includes: lane keeping cost function, road boundary cost function and obstacle avoidance cost function; the trajectory cost includes: trajectory speed index cost function, trajectory control amount change cost function and trajectory consistency cost function.
[0016] Furthermore, the expression of the obstacle avoidance cost function is:
[0017]
[0018] In the above formula, A obs represents the weight coefficient of the obstacle avoidance cost function; v(t) represents the speed of the vehicle; x(t) is the horizontal coordinate position of the vehicle at time t; y(t) is the vertical coordinate position of the vehicle at time t; x obs Represents the horizontal coordinate position of the obstacle; y obs represents the vertical coordinate position of the obstacle; ζ is the adjustment coefficient.
[0019] Furthermore, in the step S2, after generating the optimal control sequence of the control variables in the preset prediction range, it also includes: constraining the optimal control sequence according to preset conditions; the preset conditions include: controlling the acceleration and front wheel steering angle of the vehicle within a first preset range and a second preset range, respectively, and constraining the position of the vehicle.
[0020] Furthermore, the position of the vehicle is constrained by the following formula:
[0021]
[0022] In the above formula, x(t) is the horizontal coordinate position of the vehicle at time t; x(t) obs is the horizontal coordinate position of the vehicle in the environment at time t; r x The preset safety distance of the horizontal coordinate when no collision occurs; y(t) is the vertical coordinate position of the vehicle at time t; y(t) obs is the vertical coordinate position of the vehicle in the environment at time t; r y The preset safety distance for the vertical axis in case of no collision.
[0023] Furthermore, the local trajectory planner has a larger discrete time step.
[0024] Furthermore, the trajectory tracking controller has a smaller discrete time step.
[0025] Furthermore, the objective function of the trajectory tracking controller includes two performance indicators, namely: the tracking capability of the local optimal trajectory and the stability of the control amount.
[0026] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least:
[0027] An unmanned vehicle trajectory planning method provided by an embodiment of the present invention includes: obtaining the environment and vehicle state information of the unmanned vehicle to be trajectory planned; inputting the environment and vehicle state information into a local trajectory planner, and planning a local optimal trajectory based on a kinematic model and following corresponding evaluation indicators; inputting the planned local optimal trajectory into a trajectory tracking controller as the expected trajectory, and using an objective function including optimization parameters as an evaluation basis, and under corresponding preset constraints, calculating the optimal action sequence of the front steering wheel of the unmanned vehicle to be trajectory planned; according to the optimal action sequence, by manipulating the actuator of the unmanned vehicle to be trajectory planned, ensuring that the unmanned vehicle to be trajectory planned drives safely according to the planned trajectory. This method improves the efficiency of trajectory planning, reduces the complexity of the model, and reduces the calculation time under the premise of ensuring the accuracy of the model.
[0028] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.
[0029] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0031] Figure 1 A flow chart of a method for trajectory planning of an unmanned vehicle provided in an embodiment of the present invention;
[0032] Figure 2 A structural block diagram provided for an embodiment of the present invention;
[0033] Figure 3 A schematic diagram of the connection process between the planning layer and the control layer provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0034] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.
[0035] The embodiment of the present invention provides a method for planning a trajectory of an unmanned vehicle, referring to Figure 1 As shown, the following steps are included:
[0036] S1. Obtaining the environment and vehicle status information of the unmanned vehicle to be trajectory planned; the environment and vehicle status information includes: vehicle status, vehicle position, environment information, traffic information and road information;
[0037] S2, input the environment and vehicle state information into the local trajectory planner, and plan the local optimal trajectory based on the kinematic model and the corresponding evaluation indicators;
[0038] S3, the planned local optimal trajectory is input into the trajectory tracking controller as the expected trajectory, and the objective function including the optimization parameters is used as the evaluation basis, and under the corresponding preset constraints (referring to the control amount and the control amount increment constraints), the optimal action sequence of the front steering wheel of the unmanned vehicle to be trajectory planned is calculated; the optimization parameters include: lateral tracking error and control amount change rate;
[0039] S4. According to the optimal action sequence, the actuator of the unmanned vehicle to be trajectory planned is manipulated to ensure that the unmanned vehicle to be trajectory planned drives safely according to the planned trajectory.
[0040] The unmanned vehicle trajectory planning method provided in this embodiment improves trajectory planning efficiency, reduces model complexity, and reduces calculation time while ensuring model accuracy.
[0041] Specifically, the method includes multiple submodules, and its structural block diagram is as follows: Figure 2 As shown in the figure, it mainly includes: perception system, planning system and control system. Based on known environmental information, in the field of unmanned driving that dominates the local movement of the vehicle, the local trajectory planning (implemented through the planning layer) and tracking control (implemented through the control layer) of the unmanned vehicle are the key and foundation for realizing unmanned driving technology. Under the global path reference, the local trajectory planning controller (MPC planner) receives the state information of the environment and vehicle perceived by the perception module or other sensors (including: vehicle state, vehicle position, environmental information, traffic information and road information), and plans a better local trajectory that meets the constraints and is safe and feasible in complex environments such as lane lines, road boundaries, surrounding vehicles and environmental obstacles based on the kinematic model of appropriate accuracy and following the corresponding evaluation indicators; the trajectory planned by the upper layer is used as the expected trajectory of the lower trajectory tracking layer. The trajectory tracking controller (MPC controller) is based on the nonlinear vehicle model, and takes the objective function that includes optimization parameters such as lateral and longitudinal tracking errors and the rate of change of control quantity as the evaluation basis. Under specific constraints, it calculates the optimal action sequence of the front steering wheel of the vehicle to ensure that the actual trajectory of the vehicle can not only timely fit the expected value of the upstream planning, but also ensure the safety, comfort and efficiency of the vehicle.
[0042] Among them, the perception system is used to obtain the driving status information of the current vehicle and the surrounding vehicles, and perform signal processing, including: using the radar environment perception element in the on-board intelligent perception module and the on-board camera to obtain the lanes, speeds and accelerations of the surrounding vehicles, the lanes, speeds and relative distances of the vehicle based on the lanes of the vehicle, and obtaining the driving intentions of the surrounding vehicles through the offset between the center line of the surrounding vehicles and their lanes or the turn signal information, and collecting data for use in subsequent planning control systems.
[0043] The planning system collects environmental information from the perception system. The environmental information includes: the lanes, speeds and accelerations of surrounding vehicles; the lanes, speeds and relative distances of the vehicle based on the lane; and the driving intentions of the surrounding vehicles are obtained through the offset of the center line of the surrounding vehicles and their lanes or the turn signal information. The surrounding environmental information obtained by the perception system determines the current position of the intelligent vehicle itself, as well as the surrounding obstacle vehicle information and road information. Determine whether to execute the lane change decision and plan the vehicle status in the future.
[0044] The control system is mainly responsible for accurately executing the results planned by the planning system, sending signals to the actuators on the smart car at the right time, and ensuring that the smart car can drive safely according to the planned results by manipulating the actuators such as the accelerator, brake and steering wheel.
[0045] The specific planning system includes the following steps:
[0046] Step 1: Establishment of planner model:
[0047] The planning layer uses an MPC planner (local trajectory planner) based on a kinematic model. A vehicle kinematic model (planner prediction model) is established. This includes:
[0048] Establishment of vehicle kinematic model:
[0049] The kinematic model is based on longitudinal and lateral dynamics. The vehicle model in autonomous driving can be simplified to a rigid body structure moving on a two-dimensional plane, the state of the vehicle at any time, the origin of the vehicle coordinates is located at the center of the rear axle, and the coordinate axis is parallel to the vehicle body. The vehicle kinematic model is established based on the single vehicle model, where (X, Y) is the coordinate of the rear axle center; ψ is the heading angle; v is the vehicle speed; δ f is the front wheel turning angle; δ r is the rear wheel steering angle, which is always 0°; w is the yaw rate; β is the slip angle, which is extremely small and is assumed to be 0; 1 is the wheelbase of the front and rear axles of the vehicle. When the state quantity is [X, Y, ψ] T , the controlled quantity is u=[v,δ f ] T When , we have the following formula (2.1):
[0050]
[0051] However, in the control process of unmanned vehicles, the general control quantity u=[a,w] T , a is the longitudinal acceleration of the vehicle, then formula (2.1) can be written as formula (2.2):
[0052]
[0053] Step 2: Establish the planner optimization problem:
[0054] The kinematic model planning method of the MPC planner adjusts the optimization target and obtains the constraints according to the surrounding environment parameters; and performs trajectory planning by solving the optimization problem online and performing rolling optimization without being based on a fixed trajectory form.
[0055] Following the corresponding evaluation indicators, the solution is based on various constraints. The specific solution process is as follows:
[0056] First, the main vehicle status, traffic information and path planning information are used as input to the trajectory planning module of the MPC planner; the trajectory planning module plans the optimal trajectory based on the transmitted information and generates a sequence of (x(t), y(t), δ(t), a(t)), where x(t) is the vehicle's horizontal coordinate at time t (the lateral position of the vehicle), y(t) is the vehicle's vertical coordinate at time t (the longitudinal position of the vehicle), δ(t) is the front wheel turning angle at time t, and a(t) is the longitudinal acceleration of the vehicle at time t; the sequence is subsequently converted to the trajectory tracking controller so that the autonomous vehicle follows the generated optimal trajectory.
[0057] Secondly, the trajectory planning algorithm of the MPC planner is responsible for planning the trajectory so that the vehicle performs lane change or lane keeping actions; the trajectory planning implementation is expressed as an optimal control problem in the equation to find the control variable U(t) = [δ(t), a(t)] in the prediction horizon [t, t+T]. T The optimal control sequence of , thus obtaining equations (6a) and (6b):
[0058]
[0059]
[0060] In the above formula, L(X(t), U(t), t) is the cost function of the prediction range [t, t+T]; U(t) is the optimal control sequence within the prediction range [t, t+T]; f(X(t), U(t)) is the state space expression; X(t) is the state variable.
[0061] Among them, the cost function can be expressed as follows:
[0062] L(X(t),U(t),t)
[0063] =L road (X(t),U(t),t)+L lane (X(t),U(t),t)+L obs (X(t),U(t),t)+L keep (X(t),U(t),t)+L v (X(t),U(t),t)+Lcon (X(t), U(t), t) (3)
[0064] The cost function mainly includes environmental cost and trajectory cost. The cost function considering environmental cost mainly includes L road (X(t),U(t),t),L keep (X(t),U(t),t),L obs (X(t), U(t), t) three items.
[0065] Among them, in order to enable the vehicle to perform lane keeping actions when there is no need to change lanes, the lane keeping cost function used is as follows:
[0066]
[0067] In the above formula, A keep represents the weight coefficient of this cost function, y(t) represents the longitudinal position of the vehicle, σ keep is an adjustment factor related to lane width, L keep1 With L keep2 Represent the positions of lane centerline 1 and lane centerline 2 respectively.
[0068] In order to prevent the vehicle from crossing the road boundary, the road boundary cost function used is as follows:
[0069]
[0070] In the above formula, A road represents the weight coefficient of this cost function, y(t) represents the longitudinal position of the vehicle, L road1 With L road2 They represent the positions of lane boundary line 1 and lane boundary line 2 respectively.
[0071] In order to keep the vehicle as far away from obstacles as possible, the obstacle avoidance cost function used is as follows:
[0072]
[0073] In the above formula, A obs represents the weight coefficient of this cost function, v(t) represents the vehicle speed, x(t) represents the lateral position of the vehicle, y(t) represents the longitudinal position of the vehicle, and x obs With y obs Respectively represent the horizontal and vertical coordinates of the obstacle vehicle (object), ζ is a factor to prevent L obs (X(t), U(t), t) is too large an adjustment factor.
[0074] The cost function considering trajectory cost (generated trajectory performance) mainly includes L u (X(t),U(t),t),L v(X(t),U(t),t),L con (X(t), U(t), t) three items.
[0075] The cost function considering the planning trajectory speed index is as follows:
[0076] L v (X(t),U(t),t)=A v |v max -v(t)| (7)
[0077] In the above formula, A v represents the weight coefficient of this cost function, v(t) represents the speed of the vehicle, v max Represents the maximum permissible speed.
[0078] The cost function considering the change in the control amount of the planned trajectory is as follows:
[0079]
[0080] In the above formula, A u represents the weight coefficient of this cost function, M represents the prediction time domain step, and Δu represents the change in the control amount.
[0081] In order to reduce unnecessary changes in planning trajectories, the cost function of the planning trajectory consistency function is considered as follows:
[0082]
[0083] In the above formula, A con represents the weight coefficient of this cost function, and Represents the natural coordinate system coordinate value of the i-th point on the candidate trajectory at time t for comparison. and Represents the abscissa and ordinate values of the natural coordinate system of the i-th point on the candidate trajectory at time t-Δt for comparison. k is used to indicate that the rolling time domain rolls back once, covering k times the model discrete step length. N b Represents the total number of discrete points of the candidate trajectory from t = 0 to t = T; after the trajectory is discretized, it will become trajectory points, here it refers to the total number of trajectory points.
[0084] Step 3: Quick solution:
[0085] The trajectory is obtained directly through optimization. During the optimization process, the calculation time is reduced by simplifying the planner prediction model, and the number of variables to be solved is reduced by extending the control time step (control time domain remains unchanged, increase control step). In order to ensure the control accuracy of the control layer, before the planning trajectory is passed to the trajectory tracking layer (trajectory tracking controller), the trajectory needs to be resampled to complete the connection between the planning layer trajectory and the tracking control layer trajectory, and convert the larger discrete time step into a smaller discrete time step.
[0086] When resampling the planned trajectory, let represents the velocity of the i-th point on the candidate trajectory before resampling at time t, then the resampling method can be expressed as formula (10).
[0087]
[0088] In the above formula, represents the trajectory vector, Represents the trajectory vector of the i-th point of the candidate trajectory before resampling, Represents the trajectory vector of the j trajectory points after the i-th point of the original candidate trajectory after resampling.
[0089] Step 4: Establishment and solution of nonlinear model predictive control problem:
[0090] An MPC controller (trajectory tracking controller) based on a nonlinear vehicle model is used. To ensure control accuracy, the controller model selects the vehicle nonlinear dynamics model (nonlinear vehicle model) to track the trajectory solved in step 3. The trajectory tracking controller has a smaller discrete time step (the control time domain remains unchanged and the control step size is reduced).
[0091] When tracking the resampled trajectory, the controller cost function J(k) (objective function) adopts a tracking indicator, as shown in formula (11).
[0092]
[0093] In order to integrate the effects of the two performance indicators in the controller, the weight matrices Q and R are set. The weight matrix Q reflects the system's ability to track the reference trajectory, and the weight matrix R reflects the stability of the control quantity. ρ is the weight coefficient, and ε is the relaxation factor. ε is used to ensure that the optimal solution exists. P Represents the prediction time domain step, N C Represents the control time domain step size.
[0094] Accuracy cost function J 1 (k) is:
[0095] Prediction output in the prediction time domain With the expected output The form of the sum of squares of the differences between the two is used to convert the stationary objective function J 2 (k) is set as the control quantity increment Δu in the control time domain f The form of the sum of squares of (k+i).
[0096] The unmanned vehicle trajectory planning method provided in this embodiment can achieve the following beneficial effects:
[0097] The unmanned vehicle trajectory planning method of this embodiment has the following advantages: (1) The MPC planner used includes both lane change decision and trajectory planning. Compared with the traditional sampling-based robot trajectory planning method, the planner can obtain the local optimal trajectory; (2) It uses a nonlinear model that is more accurate than the traditional bicycle model and takes into account both longitudinal and lateral dynamics. The steering and braking systems are used to achieve emergency obstacle avoidance control; (3) The planning layer successfully reduces the time of the solution process by using a simplified model and a larger discrete time step; (4) The control layer uses a more accurate model and a smaller discrete time step to enable the vehicle to obtain good motion control performance even at high speeds.
[0098] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A method for trajectory planning of an unmanned vehicle, characterized in that: The steps include: S1. Obtaining the environment and vehicle status information of the unmanned vehicle to be trajectory planned; the environment and vehicle status information includes: vehicle status, vehicle position, environment information, traffic information and road information; S2, inputting the environment and vehicle state information into a local trajectory planner, and planning a local optimal trajectory based on a kinematic model and corresponding evaluation indicators; S3, inputting the planned local optimal trajectory into the trajectory tracking controller as the expected trajectory, taking the objective function including the optimization parameters as the evaluation basis, and calculating the optimal action sequence of the front steering wheel of the unmanned vehicle to be trajectory planned under the corresponding preset constraints; the optimization parameters include: lateral tracking error and control amount change rate; S4. According to the optimal action sequence, the actuator of the unmanned vehicle to be trajectory planned is manipulated to ensure that the unmanned vehicle to be trajectory planned drives safely according to the planned trajectory; In step S2, the local trajectory planner expresses the planning of the local optimal trajectory as an optimal control problem of the equation, and generates an optimal control sequence of control variables in a preset prediction range: In the above formula, L(X(t), U(t), t) is the cost function of the preset prediction range [t, t+T]; U(t) is the optimal control sequence within the preset prediction range [t, t+T]; f(X(t), U(t)) is the state space expression; X(t) is the state variable; The cost function includes environmental cost and trajectory cost; the environmental cost includes: lane keeping cost function, road boundary cost function and obstacle avoidance cost function; the trajectory cost includes: trajectory speed index cost function, trajectory control amount change cost function and trajectory consistency cost function; The expression of the obstacle avoidance cost function is: In the above formula, A obs represents the weight coefficient of the obstacle avoidance cost function; v(t) represents the speed of the vehicle; x(t) is the horizontal coordinate position of the vehicle at time t; y(t) is the vertical coordinate position of the vehicle at time t; x obs Represents the horizontal coordinate position of the obstacle; y obs represents the vertical coordinate position of the obstacle; ζ is the adjustment coefficient.
2. A method for trajectory planning of an unmanned vehicle as claimed in claim 1, characterized in that: The step S3 also includes: resampling the planned local optimal trajectory to convert the larger discrete time step into a smaller discrete time step; and inputting the resampled local optimal trajectory as the desired trajectory into the trajectory tracking controller.
3. The unmanned vehicle trajectory planning method according to claim 1, characterized in that: In the step S2, after generating the optimal control sequence of the control variables in the preset prediction range, it also includes: constraining the optimal control sequence according to preset conditions; the preset conditions include: controlling the acceleration and front wheel steering angle of the vehicle within a first preset range and a second preset range respectively, and constraining the position of the vehicle.
4. A method for trajectory planning of an unmanned vehicle as claimed in claim 3, characterized in that: The position of the vehicle is constrained by the following formula: In the above formula, x(t) is the horizontal coordinate position of the vehicle at time t; x(t) obs is the horizontal coordinate position of the vehicle in the environment at time t; r x The preset safety distance of the horizontal coordinate when no collision occurs; y(t) is the vertical coordinate position of the vehicle at time t; y(t) obs is the vertical coordinate position of the vehicle in the environment at time t; r y The preset safety distance for the vertical axis in case of no collision.
5. The unmanned vehicle trajectory planning method according to claim 1, characterized in that: The local trajectory planner has a larger discrete time step.
6. The unmanned vehicle trajectory planning method according to claim 1, characterized in that: The trajectory tracking controller has a small discrete time step.
7. The unmanned vehicle trajectory planning method according to claim 1, characterized in that: The objective function of the trajectory tracking controller includes two performance indicators, namely: the tracking capability of the local optimal trajectory and the stability of the control quantity.
