CN116989808A - Parallel parking path planning method for all-wheel steering vehicle considering uncertainty in positioning - Google Patents
Parallel parking path planning method for all-wheel steering vehicle considering uncertainty in positioning Download PDFInfo
- Publication number
- CN116989808A CN116989808A CN202310772762.2A CN202310772762A CN116989808A CN 116989808 A CN116989808 A CN 116989808A CN 202310772762 A CN202310772762 A CN 202310772762A CN 116989808 A CN116989808 A CN 116989808A
- Authority
- CN
- China
- Prior art keywords
- node
- vehicle
- path
- map
- parking
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000011156 evaluation Methods 0.000 claims abstract description 40
- 230000006870 function Effects 0.000 claims abstract description 25
- 238000010606 normalization Methods 0.000 claims abstract description 17
- 238000009499 grossing Methods 0.000 claims abstract description 15
- 238000007476 Maximum Likelihood Methods 0.000 claims abstract description 12
- 230000008569 process Effects 0.000 claims description 14
- 238000005457 optimization Methods 0.000 claims description 11
- 230000004888 barrier function Effects 0.000 claims description 7
- 239000000725 suspension Substances 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000002093 peripheral effect Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 230000006872 improvement Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 14
- 230000033001 locomotion Effects 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000008447 perception Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004807 localization Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000003016 pheromone Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
- G01C21/1652—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments with ranging devices, e.g. LIDAR or RADAR
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096805—Systems involving transmission of navigation instructions to the vehicle where the transmitted instructions are used to compute a route
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- Steering Control In Accordance With Driving Conditions (AREA)
Abstract
The application aims to provide a method for planning parallel parking paths of all-wheel steering vehicles with uncertain positioning, which adopts an inertial navigation system to collect real-time coordinate information of the vehicles, calculates a locatable evaluation value through a maximum likelihood estimation method by using heading angle data acquired by a gyroscope sensor, and carries out normalization smoothing to construct a locatable map; the environment information is converted into grid map representation, boundaries of the map and obstacles of the map are set, heuristic cost functions of optimized nodes are adopted according to the map smooth normalized locatability evaluation value, path planning is guided to avoid areas with low locatability values, and then the path is smoothed, so that parking path planning tasks are completed.
Description
Technical Field
The application belongs to the technical field of all-wheel steering vehicle path planning, and particularly relates to a method for planning a parallel parking path of an all-wheel steering vehicle with uncertain positioning.
Background
With the rapid development of technology and the continuous increase of traffic demands, research and application of intelligent vehicles are considered as a key ring for promoting the intellectualization and modernization of traffic systems. All-wheel steering vehicles are widely applied to the fields of engineering construction and the like due to the characteristics of strong power performance and high bearing capacity. By introducing the intelligent driving related technology, the efficiency of intelligent transportation and engineering construction can be greatly improved, the bottleneck of efficient circulation of goods is solved by aid of assistance, and the intelligent driving system has great research value.
Parallel parking is the most common parking mode of long and narrow roads, and is more suitable for large vehicles to park in a small-range space. When the intelligent all-wheel steering vehicle is used for detecting the parking environment, the data obtained by a plurality of sensors are required to be fused, so that the influence of blurring and uncertainty on the perception of the surrounding environment of the vehicle caused by perception aliasing is faced. Such positioning uncertainty can cause errors to accumulate in the planned path of the vehicle, so that the vehicle has a motion deviation in the parallel parking process, which brings about a safety hazard. Therefore, the parking movement planning of the vehicle needs to consider the influence of the sensor on the positioning uncertainty of the actual environment, and the reliability, the safety and the adaptability of the parking path planning are ensured while the accuracy of environment perception is improved.
Heuristic parking path planning is widely applied in the field of intelligent vehicles by analyzing and evaluating characteristics and limiting conditions of the surrounding environment of the vehicle to quickly and effectively find an optimal parking path. By utilizing the problem-specific heuristic information and heuristic functions, candidate paths are quickly searched, and path selection and optimization are performed according to predefined evaluation indexes. As described in chinese patent 202210570957.4, based on an improved ant colony algorithm, ant colony is divided into an optimization layer and an optimizing layer, and updating of pheromones is performed in real time, so as to obtain an optimal parking path. Considering the safety, comfort and efficiency of the vehicle, the vehicle is combined into a comprehensive evaluation index to perform path optimization, and a reasonable parking path is re-planned through a path reconstruction module as described in China patent 202110456189.5, so that the instantaneity and the adaptability of the parking path planning are improved. These parallel parking path approaches help to increase the efficiency of autonomous vehicle parking, but still suffer from a number of shortcomings and limitations, mainly represented by:
1. when map navigation planning is carried out, the vehicle inevitably runs in a fuzzy environment comprising a symmetrical map area or a map area without features, so that sensing aliasing of an external sensor is caused, and the planned parking path is in a high-risk running area due to accumulation of positioning errors, so that accidents are easy to occur during parking.
2. The existing intelligent vehicle heuristic path planning method limits the flexibility and adaptability of the path based on specific heuristic rules and strategies, the quality of the path is generally low, and the problem that the tracking is difficult to realize due to the fact that the motion constraint of the vehicle is not met due to the fact that the parking curve obtained by heuristic path planning is directly adopted.
Disclosure of Invention
Aiming at the first problem existing in the prior art, the application calculates the positioning confusion probability of the map in order to ensure the safety of the vehicle when automatically running on the planned path, and the planned path avoids the areas with uncertain positioning as much as possible, thereby improving the safety and reliability of parking movement.
Aiming at the second problem existing in the prior art, the heuristic algorithm A is improved, the motion constraint conditions of the multi-axis vehicle are fused on the basis of considering positioning uncertainty, curvature smooth optimization is carried out on the generated path, the generated path is ensured to meet the motion constraint of the vehicle and has good traceability, so that the acceleration and deceleration time of the vehicle in the turning process is reduced, and the quality and feasibility of path planning are improved.
Therefore, the application provides a path planning method of an all-wheel steering vehicle considering map locatable errors, which utilizes an inertial navigation system to collect real-time coordinate information of the vehicle, uses a gyroscope sensor to obtain course angle data, accurately obtains pose information of the whole vehicle through a maximum likelihood estimation method, calculates a locatable evaluation value LEV for quantitatively estimating the locating capability of the vehicle on a map, and carries out normalization smoothing to construct a locatable map LAM. The method comprises the steps of collecting information of surrounding environment of a vehicle by using a sensor such as a laser radar, converting the environment information into grid map representation, setting boundaries of the map and obstacles of the map, optimizing a heuristic cost function of a node according to a locatability evaluation value Smooth_LEV' after Smooth normalization of the map, guiding path planning to avoid an area with a low locatability value, completing a parking path planning task, smoothing the path by adjusting curvature in the path, converting the path information into tracking signals of the vehicle, realizing parallel parking path planning of the all-wheel steering vehicle considering positioning uncertainty, and improving safety and reliability of parallel parking path planning of the all-wheel steering vehicle.
The technical scheme adopted for solving the technical problems is as follows:
the parallel parking path planning method for the all-wheel steering vehicle considering uncertainty in positioning is characterized by comprising the following steps of: acquiring real-time coordinate information of a vehicle by adopting an inertial navigation system, calculating a locatable evaluation value by using course angle data acquired by a gyroscope sensor through a maximum likelihood estimation method, and carrying out normalization smoothing to construct a locatable map; the environment information is converted into grid map representation, boundaries of the map and obstacles of the map are set, heuristic cost functions of optimized nodes are adopted according to the map smooth normalized locatability evaluation value, path planning is guided to avoid areas with low locatability values, and then the path is smoothed, so that parking path planning tasks are completed.
Further, the method specifically comprises the following steps:
s1, acquiring real-time coordinate information of a vehicle by using an inertial navigation system, acquiring heading angle data acquired by a gyroscope sensor, acquiring pose information of the whole vehicle by using a maximum likelihood estimation method, and calculating positioning confusion probability LCP;
s2, calculating a locatable evaluation value LEV by taking the calculated locating confusion probability LCP as a weight, and smoothing the locatable evaluation value LEV by adopting a Gaussian filter after normalization;
s3, collecting information of surrounding environment of a vehicle, converting the environment information into a grid map OHM for representation, constructing a locatable map LAM based on a locatable evaluation value Smooth_LEV' obtained by calculating in the step S2 after the map is smoothed and normalized, adding a three-axis intelligent all-wheel steering vehicle model, setting boundaries of the map and obstacles of the map, and establishing a parallel parking scene;
step S4, based on an A-scale algorithm of heuristic cost function improvement of locatable measurement, calculating and obtaining a locatable evaluation value Smooth_LEV' after map smoothing normalization according to the step S2, and optimizing a heuristic cost function of a node to guide path planning to avoid a region with a low locatable value:
firstly, determining the positions of a starting parking point and a target parking point, taking the positions as a starting point and an end point of path planning, creating an openlist and a closelist set for improving an A-algorithm, storing nodes to be expanded and explored nodes, and placing the starting point in the closelist;
checking whether the target point is reached, if the target point is not reached, searching for the child nodes in 8 directions around the parent node, selecting the child node with the minimum cost as the next path point, adding the next path point into a close set, updating the parent node information of the child node until the target parking point is reached, completing parking path planning, and recording the planned path in the close set;
step S5: in the extraction step S4, path nodes are obtained through improved A-algorithm planning, curvature optimization is carried out by adopting an arc and a quintic polynomial curve, a continuous smooth path curve is generated, and path information is converted into a tracking control signal of a vehicle so as to ensure that the generated parking path can be accurately tracked by the vehicle.
Further, in step S1, pose information of the whole vehicle is obtained by a maximum likelihood estimation method, and the calculating of the positioning confusion probability LCP specifically includes: for event a: l (x) m )+ε≥L(x a ) When the positioning confusion probability LCP occurs, the following method is adopted for calculating:
wherein x is m To input pose, x a To give the pose, L (x) m )、L(x a ) The likelihood values of the input pose and the given pose, respectively, epsilon is a small scalar for compensating the unmodeled factor,is observation data->Probability distribution of->Is an indicator function.
Further, in step S2, the specific process of calculating the locatable evaluation value LEV by using the calculated locating confusion probability LCP as a weight and smoothing the locatable evaluation value LEV by using a gaussian filter after normalization is as follows:
Smooth_LEV'(x)＝imgaussfilt(LEV'(x),σ)
in the method, in the process of the application,is the i-th increment relative to the pose x, k is a distance coefficient, omega is the central pose x and the peripheral poses x+delta x i All sets of (phi) d (Ω) and Φ θ (Ω) is the distance range and the direction range of the set Ω, the values are 0.5m,5 °, LEV (x) is the calculated locatability evaluation value, LEV '(x) is the normalized locatability evaluation value, smoth_lev' (x) is the locatability evaluation value after gaussian filtering, and σ is the standard deviation of the gaussian filter.
Further, the construction of step S3 specifically includes:
vehicle model:
wherein A (x, y), B (x, y), C (x, y), D (x, y) represent four appearance points of the vehicle, x, y are the coordinates of the centroid of the vehicle, θ is the yaw angle of the vehicle, l f ，l r The distances between the mass center and the front shaft and the rear shaft are respectively L f 、L r The front suspension distance and the rear suspension distance of the vehicle are respectively, and W is the width of the vehicle;
obstacle setting:
boundary setting:
wherein the obstacle array represents two parts of left and right barriers obs_left and obs_right in the map, coordinates of each point are represented as (obs_left_x, obs_y), (obs_right_x, obs_y), the front array represents a boundary in the map and is divided into four parts of upper, lower, left and right, map_L is a map length, map_W is a map width, and L is a map width p For parking space length, W p And r is the resolution of the grid map, which is the width of the parking space.
Further, in step S4, the cost function of the a algorithm is as follows:
h(n)＝β 1 (|n ix -targe_node_x|+|n iy -targe_node_y|)+β 2 Smooth_LEV'(n i )
where n is a node in the grid map,representing the total cost of the path from the starting node to the current node n, including the actual cost +.>Heuristic cost->Practical cost->Starting a parking spot from two parts to a current node n i And the calculated Smooth_LEV' value of the current node, alpha 1 ,α 2 Is the corresponding weight coefficient; heuristic cost->Also comprises two parts of Manhattan distance between the current node and the target point and calculated Smooth_LEV' value of the current node, beta 1 ,β 2 Is the corresponding weight coefficient;
initializing an improved A algorithm, firstly determining the positions of a starting parking point and a target parking point as a starting point and an end point of path planning, creating an algorithm openlist and a closure list set, storing nodes to be expanded and explored optimal path nodes, and adding the starting point to the closure list set:
start_node＝[start_node_x,start_node_y]
target_node＝[target_node_x,target_node_y]
wherein, the start_node is the initial parking point, which is set as [0,0], the target parking points are two, the first target point is set at a certain safety distance behind the parking space, and the second target is set at the end point for completing the parking task
Searching the child nodes in 8 directions around the father node, removing the nodes which are barriers and are stored in the close, updating the explored nodes, selecting the child node with the minimum cost as the next path point, adding the next path point into the close set, updating the father node information of the child node, completing the planning of the parking path until reaching the target parking point, and obtaining a planned path:
openlist＝[openlist；chlid_nodes]
[～,min_idx]＝min(openlist_cost)
closelist＝[closelist；min(openlist_cost)]
parent_node'＝openlist(min_idx,:)
in the formula, parent_node is a current father node, chlid_nodes are a plurality of child nodes expanded in each step, the expanded child nodes are stored in an openlist set, min_idx is a node serial number with the minimum cost in the current openlist_cost set, parent_node' is the updated next father node, and the most cost node in each step is stored in a closed list set.
Further, the step S5 specifically includes: extracting and improving an algorithm planning to obtain path nodes, optimizing curvature by adopting an arc and a quintic polynomial curve, and generating a continuous and smooth path curve:
X＝[X 1 X 2 X 3 ]
Y＝[Y 1 Y 2 Y 3 ]
ΔX＝X(i+1)-X(i)
ΔY＝Y(i+1)-Y(i)
wherein, the closelist (i, 1) is X, y coordinate data of the ith node, n is the total number of the nodes, and X 1 ，Y 1 ，X 3 ，Y 3 Is a two-segment polynomial curve equation, X 2 ，Y 2 Is a circular curve equation, theta is the yaw angle of the vehicle, and theta 1 ，θ 2 Respectively yaw angles at the intersection points of the second section of arc and the two sections of curves, wherein X and Y are total paths optimized by three sections of curves, deltaX and DeltaY are coordinate differences among the spacing points, and Cur is the curvature of the paths;
calculating the corner according to the zero centroid cornering control and the kinematic model of the vehicle, converting the path information into corner signals of each axis of the vehicle, and carrying out open-loop tracking on the path:
δ f ＝arcsin(l f k r )
wherein D is the vector distance between the calculated instantaneous center and the mass center of the vehicle, m is the mass of the three-axle all-wheel steering vehicle, u is the longitudinal speed of the vehicle, and k f ，k m ，k r Respectively, are front axle, middleShaft and rear axle wheel-tyre cornering stiffness, l f ，l m ，l r Delta is the vector distance between each axis and the centroid of the vehicle f ，δ m ，δ r Which is the rotation angle of each axle of the vehicle.
Compared with the prior art, the application and the preferred scheme thereof have at least the following beneficial effects:
1) The problem of intelligent steering vehicle carries out parallel parking and when moving in fuzzy environment, external sensor perception aliases and leads to positioning error accumulation is solved. Aiming at the defects of the existing parallel parking environment positioning path planning method, in order to evaluate the positioning capability of the environment, the positioning confusion probability of a map is provided, the LEV value of the positionable map is calculated, the LAM of the positionable map is constructed, and on the basis of considering positioning uncertainty, the area with higher positioning confusion probability is avoided by improving a heuristic A-x algorithm, so that the safety and reliability of parking movement are improved.
2) The method solves the problems that the parking path generated by the parallel parking heuristic path planning method of the vehicle is low in quality and does not meet the motion constraint of the multi-axis vehicle. And on the planned path, fusing the motion constraint conditions of the multi-axis vehicle, and carrying out curvature smooth optimization on the generated path to ensure that the generated path meets the motion constraint of the vehicle, and obtaining the rotation angle signals of each axis according to the dynamics formula of the multi-axis vehicle, so that the path has good trackability at a given speed, the acceleration and deceleration of the vehicle at the position with large curvature fluctuation and the in-situ steering time are reduced, and the quality and feasibility of path planning are improved.
Drawings
The application is described in further detail below with reference to the attached drawings and detailed description:
fig. 1 is a schematic view of an environment constructed based on a locatable evaluation value LEV in an embodiment of the present application.
FIG. 2 is a diagram of a map of locatability after normalization smoothing in an embodiment of the present application.
FIG. 3 is a schematic illustration of an all-wheel steering parallel parking path planning and design flow considering uncertainty in positioning in an embodiment of the present application.
Fig. 4 is a schematic diagram of an all-wheel steering vehicle parallel parking scene based on a grid map in an embodiment of the application.
Fig. 5 is a schematic diagram of a parking path obtained by the modified a algorithm in the embodiment of the present application.
Fig. 6 is a schematic view of a parking path after curvature optimization in an embodiment of the present application.
Fig. 7 is a schematic diagram of a model structure of an all-wheel steering vehicle in an embodiment of the application.
FIG. 8 is a graph of path-following axle rotation angle signals for an all-wheel-steering vehicle in accordance with an embodiment of the present application, wherein:
fig. 8 (a) is a curvature map of the path of the all-wheel steering vehicle in the embodiment of the present application, and fig. 8 (b) is a graph of each axle rotation angle signal at the time of tracking.
Detailed Description
In order to make the features and advantages of the present patent more comprehensible, embodiments accompanied with figures are described in detail below:
it should be noted that the following detailed description is illustrative and is intended to provide further explanation of the application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
Fig. 1 is a schematic view of an environment constructed based on a locatable evaluation value LEV in an embodiment of the present application. And calculating the probability LCP of positioning confusion when the pose information of the whole vehicle is estimated by adopting a maximum likelihood estimation method, and calculating a locatability evaluation value LEV in a parking environment by taking the probability LCP as a weight.
FIG. 2 is a diagram of a map of locatability after normalization smoothing in an embodiment of the present application. And distributing the calculated locatability evaluation value LEV between 0 and 1 by using minimum-maximum normalization, and processing the normalized LEV by using a Gaussian filter.
FIG. 3 is a schematic illustration of an all-wheel steering parallel parking path planning and design flow considering uncertainty in positioning in an embodiment of the present application. Specific improved heuristic path planning and optimization processes considering positioning uncertainty are provided.
Fig. 4 is a schematic diagram of an all-wheel steering vehicle parallel parking scene based on a grid map in an embodiment of the application. And processing the grid map, setting boundaries and barriers of a parking environment, adding a three-axis intelligent all-wheel steering vehicle model, and establishing a parallel parking scene.
Fig. 5 is a schematic diagram of a parking path obtained by the modified a algorithm in the embodiment of the present application. And (3) improving the heuristic function in the A-algorithm, and optimizing the heuristic cost function of the node based on the locatability evaluation value LEV of the map so as to guide the path planning to avoid the area with low locatability value.
Fig. 6 is a schematic view of a parking path after curvature optimization in an embodiment of the present application. Extracting and improving an algorithm planning to obtain path nodes, generating a continuous path curve, and optimizing curvature by considering physical constraint conditions of vehicles to obtain a smooth path.
Fig. 7 is a schematic diagram of a model structure of an all-wheel steering vehicle in an embodiment of the application, including distance from the center of mass and size information for each axle of the vehicle.
Fig. 8 (a) is a curvature map of the path of the all-wheel steering vehicle in the embodiment of the present application, and fig. 8 (b) is a graph of each axle rotation angle signal at the time of tracking. And calculating curvature information of the optimized path, and converting the curvature information into rotation angle signals of each shaft tracked by the vehicle.
In this embodiment, all parameters including the road parking scene and all-wheel steering vehicle are as follows:
the embodiment provides a path planning method for improving parallel parking efficiency of a heavy all-wheel steering vehicle, which comprises the following steps: s1, acquiring real-time coordinate information of a vehicle by using an inertial navigation system, acquiring course angle data by using a gyroscope sensor, accurately acquiring pose information of the whole vehicle by using a maximum likelihood estimation method, and calculating positioning confusion probability LCP;
step S2, in order to quantitatively estimate the positioning capability of the vehicle on the map, calculating a locatability evaluation value LEV according to the calculated positioning confusion probability LCP as a weight, distributing the value between 0 and 1 by using a normalization process, and smoothing the LEV by adopting a Gaussian filter with a mask;
s3, collecting information of surrounding environment of a vehicle by using sensors such as a laser radar, converting the environment information into a grid map OHM representation, constructing a locatable map LAM, adding a three-axis intelligent all-wheel steering vehicle model, setting boundaries of the map and obstacles of the map, and establishing a parallel parking scene;
step S4, improving an A-algorithm according to a heuristic cost function of the locatable measurement, and optimizing the heuristic cost function of the node according to a locatable evaluation value Smooth_LEV' after map smoothing normalization so as to guide path planning to avoid a region with a low locatable value;
firstly, determining the positions of a starting parking point and a target parking point, taking the positions as a starting point and an end point of path planning, creating an openlist and a closelist set for improving an A-algorithm, storing nodes to be expanded and explored nodes, and placing the starting point in the closelist;
continuously checking whether the target point is reached in the path planning process, searching the child nodes in 8 directions around the parent node if the target point is not reached, selecting the child node with the minimum cost as the next path point, adding the next path point into a close set, updating the parent node information of the child node until the target parking point is reached, completing the parking path planning, and recording the planned path in the close set;
and S5, extracting an improved A algorithm to plan to obtain path nodes, optimizing curvature by adopting an arc and a quintic polynomial curve, generating a continuous smooth path curve, converting path information into a tracking control signal of the vehicle, and ensuring that the generated parking path can be accurately tracked by the vehicle.
In step S1, based on a sensor mounted on the vehicleAnd calculating pose information of the whole vehicle by adopting a maximum likelihood estimation method, wherein for an event A: l (x) m )+ε≥L(x a ) When the method occurs, the possibility of confusion exists in the maximum likelihood estimation vehicle pose, and the positioning confusion probability LCP is calculated by adopting the following method:
wherein x is m To input pose, x a To give the pose, L (x) m )、L(x a ) The likelihood values of the input pose and the given pose, respectively, epsilon is a small scalar for compensating the unmodeled factor,is observation data->Probability distribution of->Is an indicator function.
In step S2, according to the calculated positioning confusion probability LCP as a weight, a locatable evaluation value LEV is calculated, a normalization process is used to distribute the value between 0 and 1, and a gaussian filter is used to process the normalized LEV', so as to realize the following steps:
Smooth_LEV'(x)＝imgaussfilt(LEV'(x),σ)
in the method, in the process of the application,is the i-th increment relative to the pose x, k is a distance coefficient, omega is the central pose x and the peripheral poses x+delta x i All sets of (phi) d (Ω) and Φ θ (Ω) is the distance range and the direction range of the set Ω, the values are 0.5m,5 °, LEV (x) is the calculated locatability evaluation value, LEV '(x) is the normalized locatability evaluation value, smoth_lev' (x) is the locatability evaluation value after gaussian filtering, and σ is the standard deviation of the gaussian filter.
In step S3, information of the surrounding environment of the vehicle is collected using a sensor such as a laser radar, the environmental information is converted into a grid map OGM, and a localization map LAM is constructed based on the calculated localization evaluation value smoth_lev'. Processing the grid map, adding a three-axis intelligent all-wheel steering vehicle model, setting the boundary and the barrier of a parking environment, and establishing a parallel parking scene, wherein the establishment process is as follows:
vehicle model:
wherein A (x, y), B (x, y), C (x, y), D (x, y) represent four appearance points of the vehicle, x, y are the coordinates of the centroid of the vehicle, θ is the yaw angle of the vehicle, l f ，l r The distances between the mass center and the front shaft and the rear shaft are respectively L f 、L r The front suspension distance and the rear suspension distance of the vehicle are respectively, and W is the width of the vehicle.
Obstacle setting:
boundary setting:
wherein the obstacle array represents two parts of left and right barriers obs_left and obs_right in the map, coordinates of each point are represented as (obs_left_x, obs_y), (obs_right_x, obs_y), the front array represents a boundary in the map and is divided into four parts of upper, lower, left and right, map_L is a map length, map_W is a map width, and L is a map width p For parking space length, W p And r is the resolution of the grid map, which is the width of the parking space.
In step S4, an improved a algorithm is initialized, first, positions of a start parking point and a target parking point are determined, the positions are used as a start point and an end point of path planning, an algorithm openlist and a closed list set are created, the nodes to be expanded and the explored optimal path nodes are stored, and the start point is added to the closed list set.
start_node＝[start_node_x,start_node_y]
target_node＝[target_node_x,target_node_y]
In the formula, the start_node is the initial parking point, is set as [0,0], and two target parking points are provided, wherein the first target point is arranged at a certain safety distance behind a parking space, and the second target point is arranged at the end point for completing a parking task.
And (3) improving a heuristic function in the A-algorithm, optimizing a heuristic cost function of the node based on a map locatability evaluation value Smooth_LEV', and guiding path planning to avoid a region with a low locatability value, wherein the cost function is designed as follows:
h(n)＝β 1 (|n ix -targe_node_x|+|n iy -targe_node_y|)+β 2 Smooth_LEV'(n i )
where n is a node in the grid map,representing the total cost of the path from the starting node to the current node n, including the actual cost +.>Heuristic cost->Practical cost->Starting a parking spot from two parts to a current node n i And the calculated Smooth_LEV' value of the current node, alpha 1 ,α 2 Is the corresponding weight coefficient. Heuristic cost->Also comprises two parts of Manhattan distance between the current node and the target point and calculated Smooth_LEV' value of the current node, beta 1 ,β 2 Is the corresponding weight coefficient.
Checking whether the vehicle reaches a target point, if the vehicle does not reach the target point, searching for the child nodes in 8 directions around the father node, excluding the nodes which are obstacles and are stored in the closlist, updating the explored nodes, selecting the child node with the minimum cost as the next path point, adding the next path point into the closlist set, updating the father node information until the target parking point is reached, completing parking path planning, and obtaining a planned path:
openlist＝[openlist；chlid_nodes]
[～,min_idx]＝min(openlist_cost)
closelist＝[closelist；min(openlist_cost)]
parent_node'＝openlist(min_idx,:)
in the formula, parent_node is a current father node, chlid_nodes are a plurality of child nodes expanded in each step, the expanded child nodes are stored in an openlist set, min_idx is a node serial number with the minimum cost in the current openlist_cost set, parent_node' is the updated next father node, and the most cost node in each step is stored in a closed list set.
In step S5, path nodes are obtained by extracting and planning an improved a-th algorithm, and curvature optimization is performed by adopting an arc and a quintic polynomial curve, so as to generate a continuous and smooth path curve. Calculating a corner according to the zero centroid cornering control and the kinematic model of the vehicle, converting path information into corner signals of each axis of the vehicle, and carrying out open-loop tracking on the path:
X＝[X 1 X 2 X 3 ]
Y＝[Y 1 Y 2 Y 3 ]
ΔX＝X(i+1)-X(i)
ΔY＝Y(i+1)-Y(i)
δ f ＝arcsin(l f Cur)
wherein, the closelist (i, 1) is X, y coordinate data of the ith node, n is the total number of the nodes, and X 1 ，Y 1 ，X 3 ，Y 3 Is a two-segment polynomial curve equation, X 2 ，Y 2 Is a circular curve equation, theta is the yaw angle of the vehicle, and theta 1 ，θ 2 The yaw angles at the intersection points of the second section of arc and the two sections of curves are respectively, X and Y are the total paths optimized by the three sections of curves, deltaX and DeltaY are coordinate differences among the spacing points, and Cur is the curvature of the paths. Delta 1 For the calculated first axle rotation angle of the vehicle, D is the calculated vector distance of the instantaneous center of the vehicle from the center of mass, m is the mass of the three-axle all-wheel steering vehicle, u is the longitudinal speed of the vehicle, k f ，k m ，k r Lateral deflection rigidity of front axle, middle axle and rear axle tyre respectively f ，l m ，l r Delta is the vector distance between each axis and the centroid of the vehicle f ，δ m ，δ r Which is the rotation angle of each axle of the vehicle.
According to the method, the parallel parking path planning of the all-wheel steering vehicle considering positioning uncertainty is realized, and the safety and reliability of the parallel parking path planning of the all-wheel steering vehicle are improved.
The above description of the preferred embodiments of the present application includes values, definitions, etc. and is not intended to limit the present application in any way, and any person skilled in the art may make modifications or alterations to the disclosed technical content to equivalent embodiments. However, any simple modification, equivalent variation and variation of the above embodiments according to the technical substance of the present application still fall within the protection scope of the technical solution of the present application.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The present application is not limited to the above-mentioned best mode, any person can obtain other various methods for planning parallel parking paths of all-wheel steering vehicles considering uncertainty in positioning under the teaching of the present application, and all equivalent changes and modifications made according to the scope of the present application should be covered by the present application.
Claims (7)
1. The parallel parking path planning method for the all-wheel steering vehicle considering uncertainty in positioning is characterized by comprising the following steps of: acquiring real-time coordinate information of a vehicle by adopting an inertial navigation system, calculating a locatable evaluation value by using course angle data acquired by a gyroscope sensor through a maximum likelihood estimation method, and carrying out normalization smoothing to construct a locatable map; the environment information is converted into grid map representation, boundaries of the map and obstacles of the map are set, heuristic cost functions of optimized nodes are adopted according to the map smooth normalized locatability evaluation value, path planning is guided to avoid areas with low locatability values, and then the path is smoothed, so that parking path planning tasks are completed.
2. The all-wheel-steering vehicle parallel parking path planning method considering uncertainty in positioning according to claim 1, wherein:
the method comprises the following steps:
s1, acquiring real-time coordinate information of a vehicle by using an inertial navigation system, acquiring heading angle data acquired by a gyroscope sensor, acquiring pose information of the whole vehicle by using a maximum likelihood estimation method, and calculating positioning confusion probability LCP;
s2, calculating a locatable evaluation value LEV by taking the calculated locating confusion probability LCP as a weight, and smoothing the locatable evaluation value LEV by adopting a Gaussian filter after normalization;
s3, collecting information of surrounding environment of a vehicle, converting the environment information into a grid map OHM for representation, constructing a locatable map LAM based on a locatable evaluation value Smooth_LEV' obtained by calculating in the step S2 after the map is smoothed and normalized, adding a three-axis intelligent all-wheel steering vehicle model, setting boundaries of the map and obstacles of the map, and establishing a parallel parking scene;
step S4, based on an A-scale algorithm of heuristic cost function improvement of locatable measurement, calculating and obtaining a locatable evaluation value Smooth_LEV' after map smoothing normalization according to the step S2, and optimizing a heuristic cost function of a node to guide path planning to avoid a region with a low locatable value:
firstly, determining the positions of a starting parking point and a target parking point, taking the positions as a starting point and an end point of path planning, creating an openlist and a closelist set for improving an A-algorithm, storing nodes to be expanded and explored nodes, and placing the starting point in the closelist;
checking whether the target point is reached, if the target point is not reached, searching for the child nodes in 8 directions around the parent node, selecting the child node with the minimum cost as the next path point, adding the next path point into a close set, updating the parent node information of the child node until the target parking point is reached, completing parking path planning, and recording the planned path in the close set;
step S5: in the extraction step S4, path nodes are obtained through improved A-algorithm planning, curvature optimization is carried out by adopting an arc and a quintic polynomial curve, a continuous smooth path curve is generated, and path information is converted into a tracking control signal of a vehicle so as to ensure that the generated parking path can be accurately tracked by the vehicle.
3. The all-wheel-steering vehicle parallel parking path planning method considering uncertainty in positioning according to claim 2, wherein:
in step S1, pose information of the whole vehicle is obtained by a maximum likelihood estimation method, and the calculating of the positioning confusion probability LCP specifically includes: for event a: l (x) m )+ε≥L(x a ) When the positioning confusion probability LCP occurs, the following method is adopted for calculating:
wherein x is m To input pose, x a To give the pose, L (x) m )、L(x a ) The likelihood values of the input pose and the given pose, respectively, epsilon is a small scalar for compensating the unmodeled factor,is observation data->Probability distribution of->Is an indicator function.
4. A method of planning a parallel parking path for an all-wheel-steered vehicle with uncertainty in positioning in view of claim 3, wherein:
in step S2, the specific process of smoothing the locatable evaluation value LEV by using the calculated locating confusion probability LCP as a weight and adopting a gaussian filter after normalization is as follows:
Smooth_LEV'(x)＝imgaussfilt(LEV'(x),σ)
in the method, in the process of the application,is the i-th increment relative to the pose x, k is a distance coefficient, omega is the central pose x and the peripheral poses x+delta x i All sets of (phi) d (Ω) and Φ θ (Ω) is the distance range and the direction range of the set Ω, the values are 0.5m,5 °, LEV (x) is the calculated locatability evaluation value, LEV '(x) is the normalized locatability evaluation value, smoth_lev' (x) is the locatability evaluation value after gaussian filtering, and σ is the standard deviation of the gaussian filter.
5. The method for planning parallel parking paths of all-wheel-steering vehicles considering uncertainty in positioning according to claim 4, wherein:
the construction of the step S3 specifically comprises the following steps:
vehicle model:
wherein A (x, y), B (x, y), C (x, y), D (x, y) representFour appearance points of the vehicle, x and y are coordinates of a mass center of the vehicle, theta is a yaw angle of the vehicle, and l f ，l r The distances between the mass center and the front shaft and the rear shaft are respectively L f 、L r The front suspension distance and the rear suspension distance of the vehicle are respectively, and W is the width of the vehicle;
obstacle setting:
boundary setting:
wherein the obstacle array represents two parts of left and right barriers obs_left and obs_right in the map, coordinates of each point are represented as (obs_left_x, obs_y), (obs_right_x, obs_y), the front array represents a boundary in the map and is divided into four parts of upper, lower, left and right, map_L is a map length, map_W is a map width, and L is a map width p For parking space length, W p And r is the resolution of the grid map, which is the width of the parking space.
6. The method for planning parallel parking paths of all-wheel-steered vehicles with uncertainty in positioning considered as recited in claim 5, wherein:
in step S4, the cost function of the a-algorithm is as follows:
h(n)＝β 1 (|n ix -targe_node_x|+|n iy -targe_node_y|)+β 2 Smooth_LEV'(n i )
where n is a node in the grid map,representing the total cost of the path from the starting node to the current node n, including the actual cost +.>Heuristic cost->Practical cost->Starting a parking spot from two parts to a current node n i And the calculated Smooth_LEV' value of the current node, alpha 1 ,α 2 Is the corresponding weight coefficient; heuristic costAlso comprises two parts of Manhattan distance between the current node and the target point and calculated Smooth_LEV' value of the current node, beta 1 ,β 2 Is the corresponding weight coefficient;
initializing an improved A algorithm, firstly determining the positions of a starting parking point and a target parking point as a starting point and an end point of path planning, creating an algorithm openlist and a closure list set, storing nodes to be expanded and explored optimal path nodes, and adding the starting point to the closure list set:
start_node＝[start_node_x,start_node_y]
target_node＝[target_node_x,target_node_y]
wherein, the start_node is the initial parking point, which is set as [0,0], the target parking points are two, the first target point is set at a certain safety distance behind the parking space, and the second target is set at the end point for completing the parking task
Searching the child nodes in 8 directions around the father node, removing the nodes which are barriers and are stored in the close, updating the explored nodes, selecting the child node with the minimum cost as the next path point, adding the next path point into the close set, updating the father node information of the child node, completing the planning of the parking path until reaching the target parking point, and obtaining a planned path:
openlist＝[openlist；chlid_nodes]
[～,min_idx]＝min(openlist_cost)
closelist＝[closelist；min(openlist_cost)]
parent_node'＝openlist(min_idx,:)
in the formula, parent_node is a current father node, chlid_nodes are a plurality of child nodes expanded in each step, the expanded child nodes are stored in an openlist set, min_idx is a node serial number with the minimum cost in the current openlist_cost set, parent_node' is the updated next father node, and the most cost node in each step is stored in a closed list set.
7. The method for planning parallel parking paths of all-wheel-steered vehicles with uncertainty in positioning considered as recited in claim 6, wherein:
the step S5 specifically comprises the following steps: extracting and improving an algorithm planning to obtain path nodes, optimizing curvature by adopting an arc and a quintic polynomial curve, and generating a continuous and smooth path curve:
X＝[X 1 X 2 X 3 ]
Y＝[Y 1 Y 2 Y 3 ]
ΔX＝X(i+1)-X(i)
ΔY＝Y(i+1)-Y(i)
wherein, the closelist (i, 1) is X, y coordinate data of the ith node, n is the total number of the nodes, and X 1 ，Y 1 ，X 3 ，Y 3 Is a two-segment polynomial curve equation, X 2 ，Y 2 Is a circular curve equation, theta is the yaw angle of the vehicle, and theta 1 ，θ 2 Respectively yaw angles at the intersection points of the second section of arc and the two sections of curves, wherein X and Y are total paths optimized by three sections of curves, deltaX and DeltaY are coordinate differences among the spacing points, and Cur is the curvature of the paths;
calculating the corner according to the zero centroid cornering control and the kinematic model of the vehicle, converting the path information into corner signals of each axis of the vehicle, and carrying out open-loop tracking on the path:
δ f ＝arcsin(l f k r )
wherein D is the vector distance between the calculated instantaneous center and the mass center of the vehicle, m is the mass of the three-axle all-wheel steering vehicle, u is the longitudinal speed of the vehicle, and k f ，k m ，k r Lateral deflection stiffness of front axle, middle axle and rear axle tire, respectively, l f ，l m ，l r Delta is the vector distance between each axis and the centroid of the vehicle f ，δ m ，δ r Which is the rotation angle of each axle of the vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310772762.2A CN116989808A (en) | 2023-06-28 | 2023-06-28 | Parallel parking path planning method for all-wheel steering vehicle considering uncertainty in positioning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310772762.2A CN116989808A (en) | 2023-06-28 | 2023-06-28 | Parallel parking path planning method for all-wheel steering vehicle considering uncertainty in positioning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116989808A true CN116989808A (en) | 2023-11-03 |
Family
ID=88527393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310772762.2A Pending CN116989808A (en) | 2023-06-28 | 2023-06-28 | Parallel parking path planning method for all-wheel steering vehicle considering uncertainty in positioning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116989808A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117782088A (en) * | 2023-12-13 | 2024-03-29 | 深圳大学 | Collaborative target map building positioning navigation method |
-
2023
- 2023-06-28 CN CN202310772762.2A patent/CN116989808A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117782088A (en) * | 2023-12-13 | 2024-03-29 | 深圳大学 | Collaborative target map building positioning navigation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11921510B1 (en) | Approach for consolidating observed vehicle trajectories into a single representative trajectory | |
| JP6969962B2 (en) | Map information providing system for vehicle driving support and / or driving control | |
| CN109263639B (en) | Driving path planning method based on state grid method | |
| RU2737874C1 (en) | Method of storing information of vehicle, method of controlling movement of vehicle and device for storing information of vehicle | |
| CN106394650B (en) | Field-based torque steering control | |
| US8880272B1 (en) | Approach for estimating the geometry of roads and lanes by using vehicle trajectories | |
| CN110361013B (en) | Path planning system and method for vehicle model | |
| RU2742213C1 (en) | Method to control information on lanes, method of traffic control and device for control of information on lanes | |
| Zhao et al. | Dynamic motion planning for autonomous vehicle in unknown environments | |
| US20080059015A1 (en) | Software architecture for high-speed traversal of prescribed routes | |
| CN105936276A (en) | Travel control device | |
| WO2018142527A1 (en) | Travel history storage method, method for producing travel path model, method for estimating local position, and travel history storage device | |
| CN110914639B (en) | Data generation method for generating and updating a topological map of at least one space of at least one building | |
| CN116989808A (en) | Parallel parking path planning method for all-wheel steering vehicle considering uncertainty in positioning | |
| CN116337045A (en) | High-speed map building navigation method based on karto and teb | |
| CN115016458B (en) | RRT algorithm-based path planning method for hole exploration robot | |
| CN114200945A (en) | Safety control method of mobile robot | |
| Kanchwala et al. | Development of an intelligent transport system for EV | |
| CN112666950B (en) | Unmanned automobile obstacle avoidance method based on ultrasonic distance detection | |
| CN117146838A (en) | Path planning method and device and related products | |
| CN118225105B (en) | Textile workshop logistics AGV navigation method based on multi-source information perception | |
| CN115246394A (en) | Intelligent vehicle overtaking obstacle avoidance method | |
| Cantas et al. | Camera based automated lane keeping application complemented by gps localization based path following | |
| Smaili et al. | Multi-sensor fusion method using bayesian network for precise multi-vehicle localization | |
| Spenko | Hazard avoidance for high-speed rough-terrain unmanned ground vehicles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |