CN114723903A - Obstacle risk field environment modeling method and device and related products - Google Patents
Obstacle risk field environment modeling method and device and related products Download PDFInfo
- Publication number
- CN114723903A CN114723903A CN202210272795.6A CN202210272795A CN114723903A CN 114723903 A CN114723903 A CN 114723903A CN 202210272795 A CN202210272795 A CN 202210272795A CN 114723903 A CN114723903 A CN 114723903A
- Authority
- CN
- China
- Prior art keywords
- current frame
- obstacle
- grid
- area
- occupation
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Remote Sensing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Graphics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an obstacle risk field environment modeling method and device and related products, wherein the method comprises the following steps: establishing a current frame barrier grid map in a freset coordinate system by taking the current position of the own vehicle as an origin; determining a current frame occupied area of the obstacle in a current frame obstacle raster image according to current frame sensing data of the obstacle; and calculating and updating the current frame occupation probability of each barrier in the current frame occupation area in the current frame barrier grid image to obtain a current frame barrier risk field. The environment modeling method improves the stability and effectiveness of the environment model of the obstacle risk field.
Description
Technical Field
The present invention relates to the field of automatic driving, and in particular, to an obstacle risk field environment modeling method, an obstacle risk field environment modeling apparatus, a storage medium, a computer program product containing instructions, an electronic device, and a mobile tool.
Background
The automatic driving system is a comprehensive system integrating functions of environment perception, decision control, action execution and the like, is a system fully considering coordination planning of vehicles and traffic environment, and is also an important component of a future intelligent traffic system.
In an automatic driving system, a decision control module is a vital component, basic information output such as sensing, positioning and the like is arranged at the upstream of the decision control module, and because the description of the environment by a sensing sensor is mainly depended on a vehicle body coordinate system, and the description of the self-vehicle information by positioning is mainly depended on a geodetic coordinate system, environment modeling is required when the decision planning module uses sensing and positioning information, and a static map and dynamic environment information are integrated. The obstacle risk field is built as a key link of environment modeling, and the authenticity and stability of the risk field determine the functional effect of the automatic driving system on obstacle interaction in the transverse and longitudinal directions.
The existing method for modeling the environment of the barrier risk field mainly aims at the non-structural road working condition, and directly performs local path planning after processing the sensed peripheral environment barriers by methods such as a grid map or an artificial potential field and the like in a global coordinate system or a self-vehicle coordinate system.
Under the working condition of a structured road, the self vehicle and the barrier are restricted by traffic rules and traffic identification, so that the conventional grid map or artificial potential field method cannot be directly applied to the modeling of the barrier risk field environment.
Disclosure of Invention
The embodiment of the invention aims to solve at least one of the technical problems.
In a first aspect, an embodiment of the present invention provides an obstacle risk field environment modeling method, including:
establishing a current frame barrier grid map in a freset coordinate system by taking the current position of the own vehicle as an origin;
determining a current frame occupied area of the obstacle in a current frame obstacle raster image according to current frame sensing data of the obstacle;
and calculating and updating the current frame occupation probability of each barrier in the current frame occupation area in the current frame barrier grid image to obtain a current frame barrier risk field.
In a second aspect, an embodiment of the present invention provides an obstacle risk field environment modeling apparatus, including:
the image establishing module is used for establishing a current frame barrier raster image in a freset coordinate system by taking the current position of the own vehicle as an origin;
the occupied area determining module is used for determining the current frame occupied area of the obstacle in the current frame obstacle raster image according to the current frame sensing data of the obstacle;
and the obstacle risk field building module is used for calculating and updating the current frame occupation probability of each obstacle in each grid in the current frame occupation area in the current frame obstacle grid map so as to obtain the current frame obstacle risk field.
In a third aspect, an embodiment of the present invention provides a storage medium storing a computer program, where the computer program is executed by a processor to implement the steps of the method provided in the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer program product containing instructions for causing a computer to perform the steps of the method provided in the first aspect when the computer program product runs on the computer.
In a fifth aspect, an embodiment of the present invention provides an electronic device, including: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method provided by the first aspect of the invention.
In a sixth aspect, an embodiment of the present invention provides a mobile tool, which is characterized by including the electronic device as shown in the fifth aspect.
The method comprises the steps of establishing a current frame barrier grid image based on a frenet coordinate system, calculating the occupation probability of each grid in the occupation area after determining the occupation area of a barrier in the current frame barrier grid image, namely rasterizing the barrier risk field established by the technical scheme, and refining until each grid has the corresponding occupation probability, so that the barrier risk field is more precise and accurate, the effectiveness of the barrier risk field is enhanced, and meanwhile, the time dimension and the space dimension of the barrier are effectively combined, so that the stability and the effectiveness of an environment model of the barrier risk field are improved, the SL and ST grid images are applicable to modeling of the barrier risk field, and accurate environment model support is provided for more reasonable decision planning.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of an obstacle risk field environment modeling method according to an embodiment of the present invention;
FIGS. 2A-2C are schematic diagrams of SL coordinate system updates provided by embodiments of the invention;
FIGS. 3A-3C are schematic diagrams of ST coordinate system updates provided by embodiments of the present invention;
FIG. 4 is a schematic diagram of a method for determining a current occupied area of a static obstacle in a current-frame obstacle raster map according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a method for determining a current occupancy area of a dynamic obstacle in a current-frame obstacle grid map according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a current frame ST risk field determination method for a dynamic obstacle according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of an implementation method of step S132 in FIG. 6;
FIG. 8 is a schematic block diagram of an obstacle risk field environment modeling apparatus according to an embodiment of the present invention;
FIG. 9 is a functional block diagram of the modeling module 100 of FIG. 8;
FIG. 10 is a schematic block diagram of an obstacle risk field environment modeling apparatus according to another embodiment of the present invention;
fig. 11 is a functional block diagram of the dynamic obstacle occupying region determining unit 220 in fig. 10;
FIG. 12 is a schematic block diagram of an obstacle risk field environment modeling apparatus according to yet another embodiment of the present invention;
FIG. 13 is a functional block diagram of the dynamic obstacle risk field construction unit 320 of FIG. 12;
FIG. 14 is a schematic block diagram of an obstacle risk field environment modeling apparatus according to yet another embodiment of the present invention;
fig. 15 is a schematic structural diagram of an embodiment of an electronic device according to the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
As used in this disclosure, "module," "device," "system," and the like are intended to refer to a computer-related entity, either hardware, a combination of hardware and software, or software in execution. In particular, for example, an element may be, but is not limited to being, a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. Also, an application or script running on a server, or a server, may be an element. One or more elements may be in a process and/or thread of execution and an element may be localized on one computer and/or distributed between two or more computers and may be operated by various computer-readable media. The elements may also communicate by way of local and/or remote processes in accordance with a signal having one or more data packets, e.g., signals from data interacting with another element in a local system, distributed system, and/or across a network of the internet with other systems by way of the signal.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The obstacle risk field modeling method in the embodiment of the invention can be applied to electronic equipment, such as but not limited to a smart phone, a smart tablet, a personal PC, a computer, a cloud server, a controller and the like.
The technical scheme of the invention mainly realizes the environment modeling of the obstacle risk field under the structured road, and the environment modeling is mainly expressed by a grid method based on a freset coordinate system (also called a road coordinate system). I.e. the grid characterizes the spatial position of the obstacle in the grid map, i.e. in the structured road. The obstacle risk field defined herein may be characterized as a relationship of the spatial position in the grid map of each grid point and its corresponding probability of occupation.
Fig. 1 is a schematic diagram of an obstacle risk field environment modeling method according to an embodiment of the present invention, which may be applied to any mobile tool capable of automatic driving, such as an automatic driving vehicle (passenger car, bus, mini-bus, truck, off-road vehicle, sanitation vehicle, cleaning vehicle, ground cleaning vehicle, and vacuum cleaner), a sweeping robot, and the like, and the present invention is not limited thereto. As shown in fig. 1, the method includes:
s11, establishing a current frame obstacle raster image in a freset coordinate system by taking the current position of the vehicle as an origin;
in this embodiment, the origin of the spoke coordinate system is set as the current position of the own vehicle, i.e. the projection point of the own vehicle on the center line of the structured road.
In some embodiments, the obstacle may include a static obstacle and a dynamic obstacle, the type of the obstacle is included in the sensing data, the sensing data is output by a sensing module in a known upstream, and a current frame obstacle raster map is established in a frenet coordinate system by taking a current position of the own vehicle as an origin, including:
establishing a current frame SL raster image corresponding to the static obstacle in a freset coordinate system by taking the current position of the own vehicle as an origin; and the number of the first and second groups,
and establishing a current frame ST raster image corresponding to the dynamic barrier in the freset coordinate system by taking the current position of the own vehicle as an origin.
Specifically, a static obstacle is described by using S, L parameters to establish an SL grid map by using the center line of the structured road as a reference line (i.e., the reference line of the own vehicle) in a freet coordinate system, where S is the longitudinal distance of the static obstacle projected from the reference line, L is the transverse distance of the static obstacle projected from the reference line, and as shown in fig. 2A, 1 represents the own vehicle, 2 represents the projection point of the static obstacle on the reference line (the projection point is at the longitudinal distance S from the own vehicle), 3 represents the static obstacle, and 4 represents the reference line in the SL coordinate system. For a dynamic obstacle, an ST grid graph may be established, where T is an obstacle time based on the current time, and S is a projected longitudinal distance from a reference line at time T, as shown in fig. 3A, 1 represents a host vehicle, 2 represents a dynamic obstacle, 3 represents a collision point between the dynamic obstacle and the host vehicle, 4 represents a reference line, and 5 represents a predicted trajectory of the dynamic obstacle in an ST coordinate system. This approach may combine perceived obstacles with high-precision maps.
S12, determining the current frame occupied area of the obstacle in the current frame obstacle raster image according to the current frame perception data of the obstacle;
wherein the perception data is output by a perception module known upstream. The sensing module needs to acquire a large amount of environmental information including the state of the vehicle, traffic flow information, road conditions, traffic signs and the like through various sensors, and the sensors mainly comprise: laser Radar (Lidar), Camera (Camera), Millimeter Wave Radar (Millimeter Wave Radar), and the like.
Taking a static obstacle as an example, fig. 2B shows that the static obstacle determines the occupied area of the obstacle in the previous frame in the obstacle raster image of the previous frame from the previous frame of sensing data; fig. 2C illustrates a current frame occupied area of an obstacle determined by current frame perceptual data of a static obstacle in a current frame obstacle raster map. And then.
And S13, calculating and updating the current frame occupation probability of each barrier in the current frame occupation area in the current frame barrier grid image to obtain a current frame barrier risk field.
Illustratively, the risk fields for static and dynamic obstacles are denoted as SL risk fields and ST risk fields, respectively. The SL risk field mainly describes the relationship between each occupancy grid point (s, l) of a static obstacle and the occupancy probability P, denoted P (s, l). The ST risk field mainly describes the relationship between each occupancy grid point (s, t) of a dynamic obstacle and the occupancy probability P, denoted P (s, t). A static obstacle risk field (i.e., SL risk field) may be denoted as { s, l, P (s, l) }, and a dynamic obstacle risk field (i.e., ST risk field) may be denoted as { s, t, P (s, t) }.
The method and the device for establishing the obstacle risk field of the current frame are characterized in that the current frame obstacle grid image is established based on a freset coordinate system, after the occupied area of the obstacle in the current frame obstacle grid image is determined, the occupied probability of each grid in the occupied area is calculated, namely the obstacle risk field established by the technical scheme is rasterized and is refined until each grid has the corresponding occupied probability, so that the obstacle risk field is more precise and accurate, and the effectiveness of the obstacle risk field is enhanced.
Before setting forth the invention in more detail, it may be helpful to provide a definition of certain terms used herein to understand the invention.
In a grid diagram, the occupation area of a static obstacle in a SL grid diagram contains a plurality of grid points, the capital SL is defined to represent the collection of grid points contained in the occupation area of a single static obstacle, the lower front corner indicates the Id of the static obstacle, and the occupation area of a static obstacle in a SL grid diagram, for example, with Id of 5, can be represented by (a)5S,5L); defining a lower case SL to represent a certain grid point in SL, with the upper front corner indicating the grid point number, e.g. the 0 th occupying grid point in the occupied area of a static obstacle with Id 5 may be represented by (c) < 2 >0 5s,0 5l). The occupation area of the dynamic obstacle in the ST grid diagram contains a plurality of grid points, the capital ST is defined to represent the collection of grid points contained in the occupation area of a single dynamic obstacle, the top and bottom corner marks represent the Id of the dynamic obstacle, and the occupation area of the dynamic obstacle in the ST grid diagram, for example, with Id 5, can be represented by (a)5S,5T); defining a lower case st TableShowing a certain grid point in ST, the grid point number is shown by the upper corner mark, for example, the 0 th occupied grid point in the occupied area of the dynamic obstacle with Id of 5 can be represented as (0 5s,0 5t)。
Because both SL and ST are described based on a frenet coordinate system, and the original points of the SL and ST are projection points of the own vehicle on a structured road reference center line, historical risk field longitudinal coordinate data need to be continuously updated according to the movement of the own vehicle, a lower corner mark m represents the time for establishing a current frame frenet coordinate system, an upper corner mark n represents the time for establishing a current frame coordinate system of data, and the data refer to corresponding coordinate values of s and t of a dynamic obstacle obtained by calculation according to current frame sensing data and the center line of the own vehicle lane. When superscript is omitted, it means that the two coordinate systems are time-unified, e.g. s2 1Represents t1Data at t2Projection under the frame of the now coordinate system established at the moment, s2Represents t2Data at time t2And (5) projection under a frenet coordinate system established at the moment.
According to the above definition, the current frame occupying area of the static obstacle Id 5 can be represented as (under the current frame fresene coordinate system)5Sm,5Lm) Wherein the 0 th grid point can be represented as: (0 5sm,0 5lm)。
For static obstacles, the s-max value is denoted as max _ s, the s-min value is denoted as min _ s, the l-max value is denoted as max _ l, and the l-min value is denoted as min _ l.
For a dynamic obstacle, the tmax value is denoted as max _ t, and the tmin value is denoted as min _ t. The range s (min _ s, max _ s) of the same dynamic obstacle corresponding to min _ t and max _ t under the same time coordinate system is different, so the range s is distinguished by the superscript "', such as { (min _ s, max _ s), min _ t } and { (min _ s ', max _ s '), max _ t }.
Fig. 4 and 5 schematically illustrate an implementation method for determining a current occupied area of an obstacle in a current frame obstacle raster image when the obstacle is a static obstacle and a dynamic obstacle, respectively.
As shown in fig. 4, the implementation method for determining the current occupied area of the static obstacle in the current-frame obstacle raster image includes:
s1211: determining a coverage area of the static obstacle according to a position point in current frame sensing data of the static obstacle and the size of the obstacle;
s1212: and projecting the coverage area to a current frame SL grid image to obtain a current frame occupied area of the static obstacle in the current frame SL grid.
The occupation areas of the static obstacle in the grid map of the current frame SL can be represented as (min _ s, max _ s) and (min _ l, max _ l), marking the occupied obstacle Id of the grids in the grid map of SL, each occupied obstacle Id being theoretically unique, since there is no overlap in the actual positions between the obstacles.
Note that, for a static obstacle, the situation of the change in the structured road is not large, and therefore, the history frame information may not be considered. As shown in fig. 2B to 2C, fig. 2B is a previous frame occupation area of a static obstacle in a previous frame SL grid image, and fig. 2C is a current frame occupation area of the static obstacle in a current frame SL grid image.
As shown in fig. 5, the implementation method for determining the current occupied area of the dynamic obstacle in the current-frame obstacle raster image includes:
s1221: determining an ST area where the dynamic barrier conflicts with the self vehicle according to the current frame predicted track of the dynamic barrier and the self vehicle reference line;
the determination of the ST area where a dynamic obstacle collides with the own vehicle from the current frame predicted trajectory of the dynamic obstacle and the own vehicle reference line may be represented as { (min _ s, max _ s), min _ t } and { (min _ s ', max _ s'), max _ t }, and the occupied obstacles Id [ ] are marked in the ST grid map, and each occupied obstacle Id is theoretically not unique and therefore marked as Id [ ] due to possible overlap of the predicted trajectories of the dynamic obstacle.
Wherein the predicted trajectory of the current frame of the dynamic obstacle is output by a known upstream prediction module. Like the perception module, the prediction module is also an upstream module of the environment modeling of the present invention, and the present invention is not limited thereto.
It should be noted that the ST area where the dynamic obstacle collides with the own vehicle may be determined according to a method known in the art, and the present invention is not limited thereto. Illustratively, the time t (i.e., min _ t) and s (i.e., min _ s) of a collision starting point during a collision between the host vehicle and the dynamic obstacle and the time t (i.e., max _ t) and s (i.e., max _ s) of a collision ending point are determined according to a current frame predicted trajectory of the dynamic obstacle, the size of the dynamic obstacle, a host vehicle reference line and the size of the host vehicle, and an ST region where the dynamic obstacle collides with the host vehicle is determined according to (min _ t, min _ s), (max _ t, max _ s), and the ST region is not rasterized. For example, a first virtual frame for representing a dynamic obstacle is generated according to the size of the dynamic obstacle, a second virtual frame for representing the own vehicle is generated according to the size of the own vehicle, each track point in the predicted track of the dynamic obstacle is taken as the central point of the first virtual frame, each road point on the reference line of the own vehicle is taken as the central point of the second virtual frame, the first virtual frame is simulated to move along the predicted track, the second virtual frame is simulated to move along the reference line, and the time points when the two start to collide and the time point when the two end to collide and the corresponding s-coordinate values are recorded.
S1222: discretizing the ST region grid into a current frame ST grid image to obtain a first estimated occupied region;
as shown in fig. 3C, a first estimated footprint is shown from discretizing the ST region grid into the current frame ST grid map.
S1223: and projecting the occupied area of the previous frame of the dynamic barrier to the grid image of the current frame ST to obtain a second estimated occupied area.
Illustratively, the occupied area of the previous frame of the dynamic obstacle is displaced according to the time variation and the self-vehicle position variation of the previous frame and the current frame, so as to obtain a second estimated area of the dynamic obstacle in the ST grid map of the current frame.
For example, the coordinates of the second estimated occupation area obtained by projecting the previous frame occupation area into the grid map of the current frame ST may be expressed as:
sm＝sm m-1-△s； (1)
tm＝tm m-1-△t； (2)
here, smThe ordinate, s, representing the moment corresponding to the current framem m-1The time difference is a calculation result of a previous frame, namely, a vertical coordinate of a corresponding moment of the previous frame, Δ s is a moving distance of the current frame and the previous frame along the path direction of the vehicle, and can be obtained by calculating the positioning variation of the vehicle, and Δ t is a time difference of two frames, for example, 0.1 second.
In some embodiments, the corresponding time interval (i.e., the update period) between the current frame and the previous frame may be set as needed, for example, determined according to the hardware frequency of the perception sensor or the like. The invention is not limited in this regard.
S1224: and determining the current frame occupying area of the dynamic barrier in the current frame ST grid image according to the first estimated occupying area and the second estimated occupying area.
For example, the first estimated occupation area and the second estimated occupation area may be filtered to obtain a current frame occupation area of the dynamic obstacle in the current frame ST grid map. The filtering method may include, for example, bayesian filtering, kalman filtering, and the like. The invention is not limited in this regard. As shown in fig. 3B and 3C, fig. 3B is a previous frame occupation area of the dynamic obstacle in the previous frame ST grid map, and fig. 3C is a current frame occupation area of the dynamic obstacle in the current frame ST grid map. The occupied area of the previous frame in fig. 3B is projected into the grid map of the current frame ST in fig. 3C, and the projected area and the occupied area of the current frame in fig. 3C are subjected to filtering processing. For the sake of simplicity, the current frame occupied area of the dynamic obstacle in the current frame ST grid map obtained by the filtering process is not shown in the figure.
Alternatively, the first and second predicted footprints may be directly superimposed, i.e., a union of the first and second predicted footprints may be taken.
In some embodiments, a method for implementing a risk field of a current frame SL for a static obstacle includes:
and regarding each static obstacle in each grid in the current frame occupying area in the current frame SL grid image, and taking the obstacle position reliability in the grid current frame perception data as the current frame occupying probability of the grid.
Therefore, for static obstacles, the probability of occupation of each grid in the current frame can be determined directly from the perceptual data.
In some embodiments, the method for determining the ST risk field of a current frame of a dynamic obstacle, as shown in fig. 6, includes:
s131, calculating and updating the current frame predicted track probability of each grid in the current frame occupied area of each dynamic obstacle in the current frame ST grid image;
s132, determining the current frame occupation probability of each occupied grid in the current frame ST grid map according to the current frame predicted track probability of each dynamic obstacle in each grid in the current frame ST grid map occupation area, so as to obtain a current frame ST risk field.
Exemplarily, with further reference to fig. 7, step S132 may be embodied as:
for each occupied grid in the grid map of the current frame ST, the following steps are performed:
s1321, determining at least one target dynamic obstacle corresponding to each occupied grid according to the current frame occupied area of each dynamic obstacle in the current frame ST grid;
because dynamic obstacles all correspond to predicted trajectories, intersections or overlaps may exist between the predicted trajectories, so that some occupied grids in the current frame ST grid map may be occupied by multiple dynamic obstacles at the same time, and therefore, when calculating the estimated occupation probabilities of the current frames of the occupied grids, the predicted trajectory probabilities of the current frames of the corresponding multiple dynamic obstacles in the occupied grids need to be considered. Therefore, it is first necessary to determine which target dynamic obstacles are occupying each occupancy grid. For example, it may be determined whether each dynamic obstacle includes the occupancy grid in the current frame occupancy area in the current frame ST grid map, and if so, the dynamic obstacle is determined to be the target dynamic obstacle occupying the occupancy grid.
S1322, determining the estimated occupation probability of the current frame occupying the occupying grid according to the predicted trajectory probability and the preset maximum occupation probability of the current frame occupying the occupying grid respectively occupied by each target dynamic obstacle;
illustratively, the dynamic obstacle Id is represented by i, the occupancy grid is represented by j, and the probability that a single target dynamic obstacle occupies the current frame predicted trajectory of the occupancy grid j is represented byiPm＝ikmThe estimated occupation probability of the current frame of the occupation grid j can be expressed as:
Pm＝min(max-p，∑，km) (3)
whereinikmIs Id [ 2 ]]The predicted trajectory probability of the target dynamic obstacle with the median value i in the occupation grid j is, and max _ p is a preset maximum occupation probability.
S1323, calculating to obtain the current frame occupation probability of the occupation grid according to the estimated occupation probability of the current frame of the occupation grid and the occupation probability of the previous frame of the occupation grid.
Illustratively, the current frame occupancy probability of the occupancy grid may be calculated based on a bayesian filtering formula.
Wherein L is an intermediate variable, and when t is the physical meaning represented by the barrier stm m-1<At 0, clear the obstacle P (S, T) risk field.
From this, each risk field occupying a grid point P (s, t) can be calculated and updated. The probability value of P (s, t) is high, representing the prediction result, the stability in the time dimension is high, the repeatability in the space dimension is high, a threshold interval can be defined, and the risk level of the intention of the obstacle and the corresponding prediction track are determined.
Illustratively, bayesian filtering may be replaced with other filtering algorithms, such as kalman filtering, etc.
The obstacle risk field calculated and updated by the method of the embodiment of the invention comprises an SL risk field and an ST risk field, not only provides accurate position information, namely the position of an occupied grid point, but also provides probability values P (s, l) and P (s, t) of each grid point, realizes the establishment of an obstacle risk field environment model, and an automatic driving system can carry out decision planning based on the obstacle risk fields { s, l, P (s, l) } and { s, t, P (s, t) }.
In addition, from the perspective of a single frame, a certain error in the accuracy range of the sensor is allowed, and the original result of 'danger existence/nonexistence' is changed into '0-1' probabilistic risk description, so that the applicability of data is improved. Meanwhile, the continuous results of multiple frames are overlapped, so that the stability of data is improved, the influence of single-frame jumping is avoided, and the accuracy of barrier risk assessment is improved.
According to the technical scheme, when the occupied area of the dynamic barrier in the ST raster image is determined, the ST area where the dynamic barrier of the current frame collides with the own vehicle and the occupied area of the dynamic barrier in the previous frame in the ST raster image of the previous frame are integrated, and the occupied area of the dynamic barrier in the current frame in the ST raster image of the current frame is determined; and when calculating the current frame occupation probability of each occupation grid in the current frame ST grid, integrating the current frame predicted trajectory probability of a plurality of target dynamic obstacles occupying the occupation grid in the occupation grid and the previous frame occupation probability of the occupation grid, and determining the current frame occupation probability of the occupation grid. The technical scheme of the invention can effectively combine the time dimension and the space dimension of the dynamic barrier at the same time, improve the stability and the accuracy of the dynamic barrier risk field and provide accurate environmental model support for more reasonable decision planning.
Fig. 8 is a block diagram illustrating an obstacle risk field environment modeling apparatus according to an embodiment of the present invention. As shown in fig. 8: the device includes:
the map building module 100 is configured to build a current frame barrier grid map in a frient coordinate system with a current position of the vehicle as an origin;
an occupation area determination module 200, configured to determine, according to current frame sensing data of an obstacle, a current frame occupation area of the obstacle in a current frame obstacle raster image;
the obstacle risk field building module 300 is configured to calculate and update a current frame occupation probability of each obstacle in a current frame occupation area in a current frame obstacle grid map, so as to obtain a current frame obstacle risk field.
In some embodiments, the obstacles may include static obstacles and dynamic obstacles, the type of obstacle is included in the sensing data, the sensing data is output by a known upstream sensing module, see fig. 9, and the mapping module 100 further includes:
SL raster map creation unit 101: the system comprises a current frame SL grid map used for establishing a static obstacle corresponding to a free coordinate system by taking the current position of the own vehicle as an origin; and (c) a second step of,
ST raster map creation unit 102: and the grid map of the current frame ST is used for establishing a corresponding dynamic obstacle in the freset coordinate system by taking the current position of the own vehicle as an origin.
The method and the device for establishing the obstacle risk field of the obstacle in the current frame are characterized in that the current frame obstacle grid image is established based on a frenet coordinate system, after the occupied area of the obstacle in the current frame obstacle grid image is determined, the occupied probability of each grid in the occupied area is calculated, namely the obstacle risk field established by the technical scheme is rasterized and is refined to the extent that each grid has the corresponding occupied probability, so that the obstacle risk field is finer and more accurate, and the effectiveness of the obstacle risk field is enhanced.
Fig. 10 is a block diagram illustrating an obstacle risk field environment modeling apparatus according to another embodiment of the present invention. As shown in fig. 10: in the apparatus, the occupied area determining module 200 specifically includes:
static obstacle occupying area determining unit 210: the method for determining the current frame occupied area of the static obstacle in the current frame obstacle raster image according to the current frame sensing data of the static obstacle specifically includes:
determining a coverage area of the static obstacle according to a position point in current frame sensing data of the static obstacle and the size of the obstacle;
and projecting the coverage area to a current frame SL grid image to obtain a current frame occupied area of the static obstacle in the current frame SL grid.
Dynamic obstacle occupying area determining unit 220: the unit is configured to determine, according to current frame sensing data of a dynamic obstacle, a current frame occupied area of the dynamic obstacle in a current frame obstacle raster image, with reference to fig. 11, and specifically includes:
ST region determination subunit 2201: the ST area is used for determining the conflict between the dynamic barrier and the self vehicle according to the current frame predicted track of the dynamic barrier and the self vehicle reference line;
the first estimated occupation area determination subunit 2202: the method comprises the steps of discretizing the ST region grid into a current frame ST grid image to obtain a first estimated occupied region;
the second estimated occupation area determination subunit 2203: the method comprises the steps of projecting a previous frame occupied area of the dynamic barrier to a current frame ST raster image to obtain a second estimated occupied area; and
the current frame occupied area determining subunit 2204: and the method is used for determining the current frame occupying area of the dynamic barrier in the current frame ST raster image according to the first estimated occupying area and the second estimated occupying area.
In this embodiment, for example, the second estimated occupied area determining subunit 2203 is configured to shift the occupied area of the previous frame of the dynamic obstacle according to the time variation and the self-vehicle position variation of the previous frame and the current frame, so as to obtain a second estimated area of the dynamic obstacle in the grid map of the current frame ST.
The corresponding time interval (i.e., the update period) between the current frame and the previous frame may be set as needed, for example, determined according to the hardware frequency of the sensing sensor. The invention is not limited in this regard.
In the present embodiment, the filtering method used in the current frame occupied area determining subunit 2204 may include, for example, bayesian filtering, kalman filtering, or the like. The invention is not limited in this regard. Alternatively, the first and second predicted footprints may be directly superimposed together, i.e., taking the union of the first and second predicted footprints.
Fig. 12 is a block diagram illustrating an obstacle risk field environment modeling apparatus according to still another embodiment of the present invention. As shown in fig. 13: in the apparatus, the obstacle risk field building module 300 specifically includes:
static obstacle risk field construction unit 310: the method comprises the steps of taking the position credibility of an obstacle in the current frame perception data of each grid as the current frame occupation probability of the grid for each grid of each static obstacle in the current frame occupation area in a current frame SL grid map; and
dynamic obstacle risk field construction unit 320: and the method is used for calculating and updating the current frame occupation probability of each dynamic obstacle in each grid in the current frame occupation area in the current frame obstacle grid map so as to obtain a current frame dynamic obstacle risk field. Referring to fig. 13, the dynamic obstacle risk field constructing unit 320 further includes:
the current frame predicted trajectory probability calculation updating subunit 3201: the system is used for calculating and updating the current frame predicted track probability of each grid in the current frame occupied area of each dynamic barrier in the current frame ST grid image;
the current frame ST risk field creation subunit 3202: the method is used for determining the current frame occupation probability of each occupied grid in the current frame ST grid map according to the current frame predicted track probability of each dynamic obstacle in each grid in the current frame occupation area in the current frame ST grid map so as to obtain a current frame ST risk field.
Fig. 14 is a block diagram illustrating an obstacle risk field environment modeling apparatus according to still another embodiment of the present invention. As shown in fig. 11: in the apparatus, the current frame ST risk field establishing subunit 3202 specifically includes:
the target dynamic obstacle determination submodule 3202A: and the method is used for determining at least one target dynamic obstacle corresponding to each occupation grid according to the current frame occupation area of each dynamic obstacle in the current frame ST grid.
The current frame estimated occupation probability determination sub-module 3202B: the device is used for determining the estimated occupation probability of the current frame occupying the occupying grid according to the predicted track probability and the preset maximum occupation probability of the current frame occupying the occupying grid respectively occupied by each target dynamic barrier;
the current frame occupancy probability determination sub-module 3202C: and calculating the occupation probability of the current frame of the occupation grid according to the estimated occupation probability of the current frame of the occupation grid and the occupation probability of the previous frame of the occupation grid.
It should be noted that, for specific implementation processes and implementation principles of each module and unit of the obstacle risk field environment modeling apparatus according to the embodiment of the present invention, reference may be made to the corresponding description of the corresponding method embodiment, and therefore, no further description is given here. For example, the obstacle risk field environment modeling apparatus according to the embodiment of the present invention may be any electronic device having a processor, such as, but not limited to, a smart phone, a smart tablet, a personal PC, a computer, a cloud server, a controller, and the like.
The embodiment of the invention also provides a nonvolatile computer storage medium, wherein the computer storage medium stores computer executable instructions which can execute the obstacle risk field environment modeling method in any embodiment;
as one embodiment, a non-volatile computer storage medium of the present invention stores computer-executable instructions configured to:
establishing a current frame barrier grid map in a freset coordinate system by taking the current position of the own vehicle as an origin;
determining a current frame occupied area of the obstacle in a current frame obstacle raster image according to current frame sensing data of the obstacle;
and calculating and updating the current frame occupation probability of each barrier in the current frame occupation area in the current frame barrier grid image to obtain a current frame barrier risk field.
As a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules corresponding to the methods in embodiments of the present invention. One or more program instructions are stored in a non-transitory computer readable storage medium, which when executed by a processor, perform the method of obstacle risk field environment modeling in any of the method embodiments described above.
The non-volatile computer readable storage medium may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the device, and the like. Further, the non-volatile computer-readable storage medium may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the non-transitory computer readable storage medium optionally includes memory located remotely from the processor, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
In some embodiments, the present application further provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform the method of modeling an obstacle risk field environment of any of the above.
An embodiment of the present invention further provides an electronic device, which includes: the system comprises at least one processor and a memory which is in communication connection with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method for modeling the environment of the obstacle risk field of the structured road according to any embodiment of the invention.
Fig. 15 is a schematic hardware structure diagram of an electronic device for performing a method for modeling an obstacle risk field environment according to another embodiment of the present application, where as shown in fig. 15, the electronic device includes:
one or more processors 1510 and memory 1520, with one processor 1510 being an example in fig. 15.
The apparatus for performing the obstacle risk zone environment modeling method may further include: an input device 1030 and an output device 1540.
The processor 1510, the memory 1520, the input device 1530, and the output device 1540 may be connected by a bus or other means, and the bus connection is exemplified in fig. 15.
The memory 1520, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules corresponding to the obstacle risk field environment modeling method in the embodiments of the present application. The processor 1510 executes various functional applications of the server and data processing by executing nonvolatile software programs, instructions and modules stored in the memory 1520, that is, implements the obstacle risk field environment modeling method of the above-described method embodiment.
The memory 1520 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of the obstacle risk field environment modeling apparatus, and the like. Further, the memory 1520 may include high-speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 1520 may optionally include memory remotely located from the processor 1510, which may be connected to the obstacle risk field environment modeling apparatus via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 1530 may receive input numerical or character information and generate signals related to user setting and function control of the obstacle risk field environment modeling device. The output device 1540 may include a display device such as a display screen.
The one or more modules are stored in the memory 1520 and, when executed by the one or more processors 1510, perform the method of obstacle risk field environment modeling in any of the method embodiments described above.
The product can execute the method provided by the embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the methods provided in the embodiments of the present application.
The electronic device of the embodiments of the present application exists in various forms, including but not limited to:
(1) mobile communication devices, which are characterized by mobile communication capabilities and are primarily targeted at providing voice and data communications. Such terminals include smart phones, multimedia phones, functional phones, and low-end phones, among others.
(2) The ultra-mobile personal computer equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include PDA, MID, and UMPC devices, such as tablet computers.
(3) Portable entertainment devices such devices may display and play multimedia content. Such devices include audio and video players, handheld game consoles, electronic books, as well as smart toys and portable vehicle navigation devices.
(4) The server is similar to a general computer architecture, but has higher requirements on processing capability, stability, reliability, safety, expandability, manageability and the like because of the need of providing highly reliable services.
(5) Other on-board electronic devices with data interaction functions, such as a vehicle-mounted device mounted on a vehicle.
The embodiment of the invention also provides a mobile tool which comprises the electronic equipment. The mobile tools comprise vehicles capable of realizing automatic driving (such as passenger cars, cleaning cars, sanitation cars, bus cars, minibuses, trucks, dust suction trucks and ground washing cars), sweeping robots and the like.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on the understanding, the above technical solutions substantially or otherwise contributing to the prior art may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the various embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (14)
1. An obstacle risk field environment modeling method is characterized by comprising the following steps:
establishing a current frame barrier grid map in a freset coordinate system by taking the current position of the own vehicle as an origin;
determining a current frame occupied area of the obstacle in a current frame obstacle raster image according to current frame sensing data of the obstacle;
and calculating and updating the current frame occupation probability of each barrier in the current frame occupation area in the current frame barrier grid image to obtain a current frame barrier risk field.
2. The method according to claim 1, wherein the obstacles include static obstacles and dynamic obstacles, and the establishing of the grid map of the current frame obstacles in the frenet coordinate system with the current position of the own vehicle as an origin specifically includes:
establishing a current frame SL raster image corresponding to the static obstacle in a freset coordinate system by taking the current position of the own vehicle as an origin; and the number of the first and second groups,
and establishing a current frame ST raster image corresponding to the dynamic barrier in the freset coordinate system by taking the current position of the own vehicle as an origin.
3. The method according to claim 2, wherein determining a current occupying area of the obstacle in the current frame obstacle raster image according to current frame sensing data of the obstacle specifically comprises:
when the obstacle is a static obstacle, determining a coverage area of the static obstacle according to a position point in current frame sensing data of the static obstacle and the size of the obstacle; and projecting the coverage area to a current frame SL grid image to obtain a current frame occupied area of the static obstacle in the current frame SL grid.
4. The method according to claim 2, wherein determining a current occupying area of the obstacle in the current frame obstacle raster image according to current frame sensing data of the obstacle specifically comprises:
when the obstacle is a dynamic obstacle, determining an ST area where the dynamic obstacle conflicts with the self vehicle according to the current frame predicted track of the dynamic obstacle and the self vehicle reference line;
discretizing the ST region grid into a current frame ST grid image to obtain a first estimated occupied region;
projecting the occupation area of the previous frame of the dynamic barrier to the grid image of the current frame ST to obtain a second estimated occupation area;
and determining a current frame occupying area of the dynamic barrier in a current frame ST grid image according to the first estimated occupying area and the second estimated occupying area.
5. The method according to claim 4, wherein projecting the occupied area of the previous frame of the dynamic obstacle into the grid map of the current frame ST to obtain a second estimated area specifically comprises:
and displacing the occupied area of the previous frame of the dynamic barrier according to the time variation and the self-parking position variation of the previous frame and the current frame to obtain a second estimated area of the dynamic barrier in the ST grid image of the current frame.
6. The method according to claim 2, wherein calculating and updating a current frame occupation probability of each obstacle in a current frame occupation area in a current frame obstacle grid map to obtain a current frame obstacle risk field specifically comprises:
and calculating and updating the current frame occupation probability of each static obstacle in each grid in the current frame occupation area in the current frame SL grid pattern aiming at the static obstacles to obtain a current frame SL risk field.
7. The method according to claim 6, wherein calculating and updating the current frame occupation probability of each static obstacle in the current frame occupation area of the current frame SL grid pattern comprises:
for each static obstacle in each grid in a current frame occupied area in a current frame SL grid pattern, determining the reliability of the obstacle position in the grid current frame perception data as the current frame occupied probability of the grid.
8. The method according to claim 2, wherein calculating and updating a current frame occupation probability of each obstacle in a current frame occupation area in a current frame obstacle grid map to obtain a current frame obstacle risk field specifically comprises:
aiming at the dynamic obstacles, calculating and updating the current frame predicted track probability of each grid in the current frame occupied area of each dynamic obstacle in the current frame ST grid image;
and determining the current frame occupation probability of each occupied grid in the current frame ST grid map according to the current frame predicted trajectory probability of each dynamic obstacle in the current frame occupation area in the current frame ST grid map so as to obtain a current frame ST risk field.
9. The method as claimed in claim 8, wherein determining the current frame occupation probability of each occupied grid in the current frame ST grid map according to the current frame predicted trajectory probability of each dynamic obstacle in each grid in the current frame occupation area in the current frame ST grid map comprises:
for each occupied grid in the grid map of the current frame ST, the following steps are performed: determining at least one target dynamic barrier corresponding to each occupied grid according to the current frame occupied area of each dynamic barrier in the current frame ST grid; determining the estimated occupation probability of the current frame occupying the occupying grid according to the predicted trajectory probability of the current frame occupying the occupying grid by each target dynamic barrier and the preset maximum occupation probability; and calculating the current frame occupation probability of the occupation grid according to the estimated occupation probability of the current frame of the occupation grid and the occupation probability of the previous frame of the occupation grid.
10. An obstacle risk field environment modeling apparatus, comprising:
the image establishing module is used for establishing a current frame barrier raster image in a freset coordinate system by taking the current position of the own vehicle as an origin;
the occupied area determining module is used for determining the current frame occupied area of the obstacle in the current frame obstacle raster image according to the current frame sensing data of the obstacle;
and the obstacle risk field building module is used for calculating and updating the current frame occupation probability of each obstacle in each grid in the current frame occupation area in the current frame obstacle grid map so as to obtain the current frame obstacle risk field.
11. A storage medium storing a computer program, characterized in that the program, when being executed by a processor, carries out the steps of the method according to any one of claims 1-9.
12. A computer program product comprising instructions for causing a computer to perform the steps of the method according to any one of claims 1 to 9 when said computer program product is run on the computer.
13. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method of any of claims 1-9.
14. A mobile tool comprising the electronic device of claim 13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210272795.6A CN114723903A (en) | 2022-03-18 | 2022-03-18 | Obstacle risk field environment modeling method and device and related products |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210272795.6A CN114723903A (en) | 2022-03-18 | 2022-03-18 | Obstacle risk field environment modeling method and device and related products |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114723903A true CN114723903A (en) | 2022-07-08 |
Family
ID=82238196
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210272795.6A Pending CN114723903A (en) | 2022-03-18 | 2022-03-18 | Obstacle risk field environment modeling method and device and related products |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114723903A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115326093A (en) * | 2022-08-11 | 2022-11-11 | 合众新能源汽车有限公司 | Method and device for calculating track of self-vehicle coordinate system, storage medium and electronic equipment |
| CN115683145A (en) * | 2022-11-03 | 2023-02-03 | 北京踏歌智行科技有限公司 | Automatic driving safety obstacle avoidance method based on track prediction |
| CN116540745A (en) * | 2023-07-05 | 2023-08-04 | 新石器慧通（北京）科技有限公司 | Track planning method and device, unmanned vehicle and storage medium |
-
2022
- 2022-03-18 CN CN202210272795.6A patent/CN114723903A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115326093A (en) * | 2022-08-11 | 2022-11-11 | 合众新能源汽车有限公司 | Method and device for calculating track of self-vehicle coordinate system, storage medium and electronic equipment |
| CN115683145A (en) * | 2022-11-03 | 2023-02-03 | 北京踏歌智行科技有限公司 | Automatic driving safety obstacle avoidance method based on track prediction |
| CN115683145B (en) * | 2022-11-03 | 2024-06-11 | 北京踏歌智行科技有限公司 | Automatic driving safety obstacle avoidance method based on track prediction |
| CN116540745A (en) * | 2023-07-05 | 2023-08-04 | 新石器慧通（北京）科技有限公司 | Track planning method and device, unmanned vehicle and storage medium |
| CN116540745B (en) * | 2023-07-05 | 2023-09-12 | 新石器慧通（北京）科技有限公司 | Track planning method and device, unmanned vehicle and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11608057B2 (en) | Navigation at alternating merge zones | |
| US11897518B2 (en) | Systems and methods for navigating with sensing uncertainty | |
| CN109313857B (en) | Surrounding environment recognition device | |
| JP6708793B2 (en) | Navigation system with limited liability | |
| CN113267199B (en) | Method and device for planning driving track | |
| JP6601696B2 (en) | Prediction device, prediction method, and program | |
| CN114723903A (en) | Obstacle risk field environment modeling method and device and related products | |
| CN112601686A (en) | System and method for navigation with safe distance | |
| CN110914641A (en) | Fusion framework and batch alignment of navigation information for autonomous navigation | |
| CN109213153B (en) | Automatic vehicle driving method and electronic equipment | |
| CN112051855A (en) | Navigation system for a host vehicle, autonomous vehicle and method of navigating an autonomous vehicle | |
| CN115235500B (en) | Lane line constraint-based pose correction method and device and all-condition static environment modeling method and device | |
| DE112021005104T5 (en) | SYSTEMS AND METHODS FOR EVALUATION OF DOMAIN-SPECIFIC CAPABILITIES OF A NAVIGATION SYSTEM | |
| CN114945952A (en) | Generating depth from camera images and known depth data using neural networks | |
| CN114782912A (en) | Obstacle risk field environment modeling method and device and related products | |
| CN114894206A (en) | Path planning method and device, vehicle and storage medium | |
| CN114926809A (en) | Passable area detection method and device, moving tool and storage medium | |
| CN112363511A (en) | Vehicle path planning method and device, vehicle-mounted device and storage medium | |
| CN113071522A (en) | Control method and control device for unmanned vehicle and unmanned vehicle | |
| CN114670870A (en) | Obstacle SLT space risk field environment modeling method and device and related products | |
| CN115810291A (en) | Associated target identification method and device, road side equipment and vehicle | |
| CN115447607A (en) | Method and device for planning a vehicle driving trajectory | |
| US20220065647A1 (en) | Autonomous vehicle planned route prediction | |
| US20220065638A1 (en) | Joint routing of transportation services for autonomous vehicles | |
| CN117858020A (en) | Track prediction method and device and Internet of vehicles equipment |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 101-901, 8th Floor, Building 4, Zone 3, No. 22, Jinghai 4th Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing 100176 (Yizhuang Cluster, High end Industrial Zone, Beijing Pilot Free Trade Zone) Applicant after: Beijing Idriverplus Technology Co.,Ltd. Address before: 100176 room 2602, 22 / F, building 4, yard 8, Wenhua Park West Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing Applicant before: Beijing Idriverplus Technology Co.,Ltd. |