CN115098989A - Road environment modeling method and device, storage medium, terminal and mobile device - Google Patents
Road environment modeling method and device, storage medium, terminal and mobile device Download PDFInfo
- Publication number
- CN115098989A CN115098989A CN202210497193.0A CN202210497193A CN115098989A CN 115098989 A CN115098989 A CN 115098989A CN 202210497193 A CN202210497193 A CN 202210497193A CN 115098989 A CN115098989 A CN 115098989A
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- lane
- road
- self
- 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 74
- 238000003860 storage Methods 0.000 title claims abstract description 24
- 230000003068 static effect Effects 0.000 claims abstract description 46
- 238000013499 data model Methods 0.000 claims abstract description 44
- 238000011144 upstream manufacturing Methods 0.000 claims abstract description 19
- 230000004927 fusion Effects 0.000 claims abstract description 8
- 230000008569 process Effects 0.000 claims description 25
- 230000004888 barrier function Effects 0.000 claims description 24
- 238000010276 construction Methods 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 11
- 230000006399 behavior Effects 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims 1
- 230000007613 environmental effect Effects 0.000 abstract description 5
- 238000011161 development Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 18
- 230000006870 function Effects 0.000 description 11
- 238000012545 processing Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000004387 environmental modeling Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 231100000817 safety factor Toxicity 0.000 description 1
- 239000010865 sewage Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computer Networks & Wireless Communication (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a road environment modeling method and device, a storage medium, a terminal and mobile equipment, wherein the modeling method comprises the following steps: receiving upstream input data and internal history data; and performing data fusion and data reconstruction based on the received upstream input data and the internal historical data, and respectively constructing a static data model, a dynamic data model and a prediction data model. The invention has the following beneficial effects: 1. the invention can effectively organize the environmental data around the vehicle, not only can provide stable environmental data for the downstream use module, but also can effectively avoid the problem of inconsistent data taken by the downstream module; 2. the invention can cover each road scene at present, can express the environmental data more completely, and effectively avoid the data loss at the same time; 3. the invention has clear modeling flow and clear data hierarchy, and can be used for downstream modules to select according to requirements, thereby improving the development and use efficiency.
Description
Technical Field
The invention relates to the technical field of automatic driving environment modeling, in particular to a road environment modeling method and device, a storage medium, a terminal and mobile equipment.
Background
With the vigorous support of governments and related enterprises on the artificial intelligence industry in recent years, the automatic driving technology is rapidly developed, test sections special for automatic driving are continuously opened in various regions, and more automatic driving companies start large-scale road testing by taking the iteration of the technology and products as a target. In view of the current development of unmanned driving, most of automatic driving vehicles not only highly rely on road topology information of high-precision maps, but also need to obtain obstacle information around the vehicles in real time by means of various sensors, and the surrounding environment information is the basis of all upper-layer technologies, so that modeling the road environment around the vehicles or digitally processing the surrounding environment is very important.
As is known, a computer software system does not have the capability of directly processing world information like a human being, and it needs to perform logic calculation and judgment only by explicit digital input, so that it needs to highly abstract a real world environment and convert the real world environment into corresponding environment data, and this process is environment modeling. Just as the importance of the foundation to the house, the quality of the environment model directly influences the realization difficulty and efficiency of the upper technology, so that the establishment of an efficient and perfect environment model is imperative.
The current major environmental modeling methods fall into two categories: one is based on map topology and the other is based on a three-lane model.
The map topology-based method is derived from the topology of the high-precision map, and the essence of the method is further processing and packaging of the high-precision map. The method generally relies on positioning to obtain road topology information (including road grade and lane grade information) in a certain range around the vehicle from a high-precision map, then perceptually recognized obstacle information and lane grade information are associated together, and finally obstacle analysis and other processing are carried out based on the associated information. For users of environment results (such as a decision module and a planning module), to use an environment model based on a map topology structure, it is first required to associate the position of an interested obstacle or a vehicle onto road topology information, and then obtain the required information and association relationship by means of the topology structure of the map itself. In such a modeling structure, it can be considered that the high-precision map topology is a medium connecting all the materials through which the own vehicle and the surrounding obstacles must determine the relationship with each other; the method based on the map topological structure mainly depends on a high-precision map, but the map is an objective description of the physical world, however, a user needs a subjective position relation of the left side, the right side or the front and back, and a certain difference exists between supply and demand, and the user is often required to perform secondary abstraction. Secondly, the process of accessing the model is complicated and low in efficiency, when the relation between any two obstacles needs to be found, the two obstacles need to be projected onto a high-precision map, then the relation between the two obstacles is determined according to the relation between roads, and the process can be realized only by carrying out projection and conversion for many times. When the map is large, the efficiency of searching the relationship through the map topology becomes abnormally low, and even the operation efficiency of the algorithm is limited. Finally, when the obstacle is projected onto the map, a misprojection (matching to a wrong road) may occur or a projection result may not be found, so that the actually existing obstacle cannot be abstracted into effective data, and the environment data taken by a user is wrong or missing, so that it is difficult to make a comprehensive judgment based on the modeling result, and finally a safety accident may occur.
The modeling method based on the three-lane model is another common modeling method, and is different from a method of directly depending on a topological relation between high-definition maps, and the surrounding environment is abstracted into a left, middle and right three-lane model which is only visually and intuitively seen. The modeling method comprises the steps that firstly, the current vehicle position is obtained according to a high-precision map and positioning, and then a lane center line with a certain length, the center line of an isometric left parallel lane of a current lane and the center line of an isometric right parallel lane are obtained; perceptually provided current obstacle information is then associated onto the three centerlines, respectively. Under the model, the self vehicle and the surrounding obstacles are only related to the left lane, the middle lane and the right lane, and the quick relation positioning can be realized. The method based on the three-lane model is a relatively mainstream method at present, and basically can meet the functional requirements of simple automatic driving, but because the model only covers data in three lanes around the vehicle, which is equivalent to artificial loss of a part of effective data, the result is too subjective; in addition, the three-lane model cannot express some complex traffic scenes, such as road confluence, diversion, intersection and the like, so that the model cannot cope with complex traffic environments. The relationship between obstacles in a special scene, such as a reverse lane obstacle, an afflux lane obstacle and the like, cannot be effectively expressed by the last three-lane model, which is an inherent defect of the model and also a main reason why the model cannot be applied to a large-scale landing.
Disclosure of Invention
In view of the technical problems in the prior art, an object of the present invention is to provide a road environment modeling method and apparatus, a storage medium, a terminal, and a mobile device, so as to better meet the use requirements of users.
In order to achieve the purpose of the present invention, the technical solutions of a road environment modeling method and apparatus, a storage medium, a terminal, and a mobile device provided by the present invention are as follows:
first aspect of the invention
The embodiment of the invention provides a road environment modeling method, which comprises the following steps:
receiving upstream input data and internal history data;
and performing data fusion and data reconstruction based on the received upstream input data and the internal historical data, and respectively constructing a static data model, a dynamic data model and a prediction data model.
Further, constructing the static data model comprises:
step S11: determining the surrounding lane relation according to the position of the vehicle;
step S12: forming a lane reference line according to the lane relation determined in the step S11;
step S13: associating the road equipment and the identification information to the lane reference line formed at step S12, thereby obtaining static data;
step S14: and performing static semantic analysis on the static data obtained in the step S13, and overlaying the analysis result on the static data.
Further, when lane diversion is performed, the process of constructing the static data model further includes:
when lane diversion is carried out, if the own vehicle is in front of a diversion point, the left lane of the own vehicle comprises a route where the own vehicle is located in front of the diversion point and a diversion route;
if the vehicle is behind the diversion point, when the vehicle is on the main road, the diversion road is the left lane of the vehicle, and the barrier on the diversion road is brought into the range of the concerned barrier; when the vehicle is on the diversion road, the main road is the right lane of the vehicle, and the obstacles on the main road are brought into the range of the concerned obstacles.
Further, constructing the dynamic data model comprises the following steps:
step S21: projecting an obstacle onto a high-precision map to determine its location;
step S22: judging whether the obstacle conflicts with a current lane reference line or not, and selecting an attention obstacle;
step S23: associating the obstacle of interest selected in step S22 to a lane reference line, thereby obtaining dynamic data;
step S24: and performing dynamic semantic analysis on the dynamic data obtained in the step S23, and superimposing the analysis result on the dynamic data.
Further, when performing lane merging, the process of constructing the dynamic data model further includes:
if the self-vehicle is on the main road, the obstacles on the lane to be merged are related to the right side or the left side lane in a manner of giving a free entry point;
if the self-vehicle is on the lane to be merged, the obstacles on the main road are divided into two situations to be associated: one is that there is a point of intersection on the road structure and the current lane of the self-vehicle, the barrier is related to the current lane of the self-vehicle in a mode of freely entering the point; the other is that the intersection point does not exist on the road structure and the current lane of the self-vehicle, the intersection point exists with the future road of the self-vehicle, and the barrier is brought into the concerned barrier of the current lane of the self-vehicle in a forced entry point mode.
Further, when the intersection travels, the process of constructing the dynamic data model further includes:
if the self-vehicle goes straight at the crossroad, the barrier turning to the left is brought into the range of the concerned barrier in the form of a forced entry point; projecting the barrier of the right turn confluence to the current lane of the self-vehicle into the current lane of the self-vehicle in a free entry point mode;
if the vehicle turns left at the crossroad, the obstacles turning left and going straight to the lane are brought into the range of the concerned obstacles in the form of forced entry points; projecting the barrier of the right turn confluence to the current lane of the self-vehicle into the current lane of the self-vehicle in a free entry point mode;
if the self-vehicle turns right at the crossroad, the barrier turning left on the opposite lane is brought into the range of the barrier concerned in the form of a forced entry point; and projecting the obstacles which go straight to the current lane of the self-vehicle into the current lane of the self-vehicle in the form of free entry points.
Further, constructing the predictive data model includes:
step S31: correlating the predicted obstacle track with the corresponding dynamic obstacle, and superposing the predicted obstacle track on static data;
step S32: and associating the predicted semantic information of the obstacle with the corresponding dynamic obstacle, and superposing the semantic information of the obstacle on the static data.
Further, the upstream input data comprises data information provided by a high-precision map, a positioning device, a sensing device, a business layer module, a vehicle bottom layer module and a prediction module;
the internal historical data comprises the historical frame data of the environment modeling module, the historical decision behavior of the decision module and the local path issued by the planning module.
Second aspect of the invention
The embodiment of the invention provides a road environment modeling device, which comprises a data receiving unit and a model constructing unit,
the data receiving unit is used for receiving upstream input data and internal historical data;
the model construction unit is used for performing data fusion and data reconstruction based on the received upstream input data and the internal historical data, and respectively constructing a static data model, a dynamic data model and a prediction data model.
Third aspect of the invention
An embodiment of the present invention provides a storage medium, where at least one instruction, at least one program, a code set, or an instruction set is stored in the storage medium, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the road environment modeling method.
Fourth aspect of the invention
The embodiment of the invention provides a terminal device, which comprises a processor and a memory, wherein at least one instruction, at least one program, a code set or an instruction set is stored in the memory, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to realize the road environment modeling method.
Fifth aspect of the invention
The embodiment of the invention provides mobile equipment comprising the terminal equipment.
Compared with the prior art, the invention has the following technical advantages:
1. the technical scheme provided by the invention fully combines ideas based on a map topological structure and a three-lane model, establishes a more perfect multi-lane model, and effectively reduces the use complexity while ensuring the integrity of model data; not only can stable environmental data be provided for the downstream use module, but also the problem of inconsistent data acquired by the downstream module can be effectively avoided;
2. the construction process of the technical scheme method provided by the invention is divided into three levels and steps: static data and semantics thereof are constructed, dynamic data and semantics thereof are constructed, and prediction data and semantics thereof are constructed, so that a user can extract data and semantics of different layers according to different requirements of the user, the modeling process is clear, the data hierarchy is clear, and downstream modules can be selected as required, thereby improving the development and use efficiency;
3. the multi-lane-based model provided by the invention can express almost all the current structured road scenes, can express environmental data more completely, and simultaneously effectively avoids data loss, and the model has higher universality and practicability.
Drawings
FIG. 1 is a flow chart of a road environment modeling method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of interaction relationship between modeling data of a road environment according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a multi-lane road structure according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of the data model construction according to the embodiment of the present invention;
FIG. 5 is a schematic diagram of a situation in which a host vehicle is on a main road in a vehicle merging scenario according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a situation in which a vehicle is on a merging lane in a merging scene of the vehicle according to the embodiment of the present invention;
FIG. 7 is a schematic diagram of a situation in which a vehicle is ahead of a diversion point in a vehicle diversion scenario according to an embodiment of the present invention;
FIG. 8 is a first schematic diagram of a vehicle following a diversion point in a vehicle diversion scenario in accordance with an embodiment of the present invention;
FIG. 9 is a second schematic illustration of a vehicle following a diversion point in a vehicle diversion scenario, in accordance with an embodiment of the present invention;
FIG. 10 is a schematic diagram of a situation where a vehicle is traveling straight at an intersection in an intersection scene according to an embodiment of the present invention;
FIG. 11 is a schematic diagram of a left turn of a vehicle at an intersection in an embodiment of the present invention;
FIG. 12 is a schematic diagram of a vehicle turning right at an intersection in an intersection scene according to an embodiment of the present invention;
FIG. 13 is a block diagram of a road environment modeling apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention are 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 only some embodiments of the present invention, and not all embodiments. 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.
As shown in fig. 1, an embodiment of the present invention provides a road environment modeling method, including:
receiving upstream input data and internal history data;
and performing data fusion and data reconstruction based on the received upstream input data and the internal historical data, and respectively constructing a static data model, a dynamic data model and a prediction data model.
It should be noted that the environment modeling module is located at the most upstream of the whole planning node (planning), and its main function is to perform fusion and data reconstruction on planning upstream input data and planning internal historical data. As shown in fig. 2, the upstream input data mainly includes information such as road topology, reference path, and boundary provided by the high-precision map; positioning the provided position and posture information of the vehicle; sensing the information such as obstacles, traffic lights, road signs and the like in a certain range around the vehicle; information such as tasks and modes issued by a service layer; and the real-time vehicle state information fed back by the vehicle bottom layer and the information such as the obstacle prediction line and intention provided by the prediction module. The internal historical data mainly comprises historical frame data of an environment modeling module, historical decision-making behaviors of a decision-making module, local paths issued by a planning module and the like. The environment modeling module further abstracts and reconstructs the data to form a digital environment model, and provides the digital environment model for a downstream module (such as decision and planning) to use, thereby ensuring the consistency and the high efficiency of the data of the downstream module.
It should be noted that, in the embodiment of the present invention, the fused data is divided into three layers: static data and its semantics, dynamic data and its semantics, predictive data and its semantics.
Wherein, static data and semantics thereof are: the static data mainly refers to road topology provided by a high-definition map, lane reference lines, boundaries and other data which exist in a static form in the physical world. Static semantics refers to a more abstract expression obtained by processing the static data to a certain extent, such as narrowing or widening of a front lane;
dynamic data and its semantics: the dynamic data mainly refers to data which can sense and input obstacles, traffic lights, road signs and the like in a certain range around the vehicle and keep dynamic change. The dynamic semantic information is a higher-level abstract expression obtained by processing dynamic data, such as traffic flow of a lane, whether the lane is congested or not and lane safety factors;
prediction data and its semantics: the prediction data mainly refers to the track of the obstacle provided by the prediction module in a future period of time. The predicted semantic information refers to intention information comprehensively given by a prediction module according to the historical track of the obstacle and a predicted line, such as left lane change of a vehicle, straight going or crossing of a pedestrian.
As shown in fig. 4, for the steps of constructing a static data model and a dynamic data model and predicting the data model according to the embodiment of the present invention, a modeling process will be described below by taking a common multi-lane road structure as an example.
The multi-lane road structure, as shown in fig. 3, assumes that the own vehicle (green polygon) is in the middle (current) lane of five lanes, and then the left and right lanes thereof, and the left lane (left and right) of the left and right lanes thereof are easily determined according to the topological relation of the map.
Wherein constructing the static data model comprises:
step S11: determining the surrounding lane relation according to the position of the vehicle;
it should be noted that the relationship of the surrounding lanes is determined according to the position of the own vehicle, including determining the lane where the own vehicle is located, the left lane and the right lane, the relationship between the preceding lane and the subsequent lane, and the like;
step S12: a lane reference line is formed according to the lane relation determined at step S11.
It should be noted that, a forward path and a backward path with a certain length are respectively combined according to the relationship between the current left lane and the current right lane and the relationship between the current left lane and the current right lane, so as to form a three-lane reference line.
Step S13: associating the road equipment and the identification information to the lane reference line formed at step S12, thereby obtaining static data;
it should be noted that, the road facilities and the identification information (speed bump, intersection position, traffic light position, etc.) within a certain length of the current lane are associated with the reference line of the current lane, and the left lane and the right lane are processed in the same manner, so as to finally obtain three-lane static data based on the own vehicle position.
Step S14: and (5) performing static semantic analysis on the static data obtained in the step (S13), and overlaying the analysis result on the static data, so as to complete the construction of the whole static data model.
In a preferred embodiment, when performing lane diversion, the process of constructing the static data model further includes: when lane diversion is carried out, if the own vehicle is in front of a diversion point, the left lane of the own vehicle comprises a route where the own vehicle is located in front of the diversion point and a diversion route; if the self-vehicle is behind the diversion point, when the self-vehicle is on the main road, the diversion road is the left lane of the self-vehicle, and the barrier on the diversion road is brought into the range of the concerned barrier; when the vehicle is on the diversion road, the main road is the right lane of the vehicle, and the obstacles on the main road are brought into the range of the concerned obstacles.
It should be noted that: as shown in fig. 7, 8 and 9, the vehicle diversion scenario is divided into two cases: the own vehicle is before the diversion point and after the diversion point.
For the situation that the own vehicle is before the diversion point (fig. 7), it should be noted that in the static data construction process, the left lane of the own vehicle is formed by combining the route where the own vehicle is located before the diversion point and the diversion route, and the construction mode of other parts is not changed.
The situation that the self-vehicle is behind the diversion point (fig. 8 and 9) is divided into two scenes that the self-vehicle is on the main road and the diversion road. When the own vehicle is on the main road (fig. 8), the diversion road needs to be regarded as the left lane of the own vehicle, so that the obstacles on the diversion road can be taken into the range of the obstacles. When the host vehicle is on the diversion road (fig. 9), it can be known from the previous thought that the diversion road is the current lane of the host vehicle, the main road needs to be regarded as the right lane of the host vehicle, and the obstacle on the main road is brought into the range of the concerned obstacle, so as to deal with the obstacle which may change to the diversion road on the main road.
Further, constructing the dynamic data model comprises the following steps:
step S21: projecting each obstacle onto a high-precision map to determine the position of the obstacle;
step S22: judging whether the obstacle conflicts with a current lane reference line or not, and selecting an attention obstacle; specifically, the combination of the prediction information of the current lane and the obstacle can determine whether the obstacle and the reference line of the current lane conflict. The judgment conditions are as follows: obstacles on a lane of a self-vehicle and left and right lanes need to be set as attention obstacles (the self-vehicle can change lanes, and left and right vehicles can cut into the lane of the self-vehicle at any time), only the obstacles on the left or right lanes of the self-vehicle need to pay attention (the obstacles kept by the left or right lanes do not directly conflict with the self-vehicle, and the obstacles cut into the vehicle can continuously and circularly run twice can conflict with each other).
Step S23: associating the obstacle of interest selected in step S22 to a lane reference line, thereby obtaining dynamic data; the method comprises the following specific steps: and sequentially associating the concerned obstacles to the current reference line. And then, carrying out two times of simulation, respectively assuming that the left lane reference line and the right lane reference line are current reference lines of the vehicle, respectively selecting the concerned obstacles according to the judgment conditions, and respectively associating the obstacles with the left reference line and the right reference line of the lane.
Step S24: and finally, comprehensively analyzing the dynamic data of the three lanes to output dynamic semantic information, and performing information superposition to complete the dynamic data modeling process.
As shown in fig. 5 and 6, when performing lane merging, the process of constructing the dynamic data model further includes:
for the situation that the self-vehicle is on the main road, firstly, the current lane and the left and right lanes are determined according to the map, static data are established according to the method described in the previous part, when dynamic data are processed, other obstacles on the lanes to be merged need special processing, in the scheme, the obstacles are described as the concept of free cut-in, the method of the free cut-in point is given to be associated to the right lane, the association method of other obstacles is not changed, and the predicted information processing method is also as described in the previous description;
for the condition that the self-vehicle is on the lane to be merged, the static data and the prediction data flow are unchanged, but in the condition, the self-vehicle only has one current lane, and other obstacles on the main road are associated by two conditions: one is that there is a point of intersection with the merging lane on the road structure, such obstacles are related to the current lane of the vehicle in a way of free entry point; the other type is that the road structure and the current lane of the own vehicle have no intersection, but due to the intersection of the lane change track of the obstacle and the future road of the own vehicle, the obstacle is described as the concept of forced cut and is included in the obstacle concerned in the current lane of the own vehicle by means of the forced cut point.
As shown in fig. 10, 11 and 12, the process of constructing the dynamic data model when the intersection travels further includes:
for the scene that the self vehicle runs straight at the intersection, an obstacle turning to the left of the opposite lane needs to be considered in the dynamic data building process, the two roads have overlapping passing areas on the road topology, which is the special situation of the intersection, and in order to express the situation, the obstacle turning to the left is still converted into a form of forced entry point to be taken into the attention range. Similarly, for the obstacle which is converged to the current lane of the self-vehicle at the right turn, the obstacle is projected to the current lane in a free entry point mode. The construction mode of other layer data is unchanged.
For a scene that a vehicle turns left at an intersection, obstacles which turn left and go straight to a lane need to be considered in the dynamic data building process, the obstacles overlap with passing areas of the vehicle lane on road topology, and the obstacles in the situation are converted into a form of forced entry points to be brought into the attention range. And for the obstacles which are converged to the current lane of the own vehicle at the right turn, the obstacles are projected to the current lane in a mode of giving free entry points of the obstacles. The construction mode of other layer data is unchanged.
For a scene that a vehicle turns right at an intersection, a left-turning obstacle of an opposite lane needs to be considered in the dynamic data building process, the two roads are overlapped in a traffic area on road topology, and the two roads are converted into a form of a forced entry point and are brought into a range of attention. And for the obstacles which go straight to the current lane of the self-vehicle, the obstacles are projected to the current lane in a mode of giving free entry points. The construction mode of other layer data is unchanged.
Further, constructing the predictive data model includes:
step S31: associating the predicted obstacle track with the corresponding dynamic obstacle, and superposing the obstacle track on static data;
step S32: and associating the predicted semantic information of the obstacle with the corresponding dynamic obstacle, and superposing the semantic information of the obstacle on the static data.
It should be noted that the predicted obstacle trajectory and the intention are associated with the corresponding dynamic obstacle and are superimposed on the static data, so as to complete the modeling process of the predicted data.
The construction of the multi-lane model is completed through the three steps, model data with different layers are obtained, and the data are provided for a downstream module for use after certain data integration and interface conversion. Meanwhile, according to different use emphasis points of different modules, data of different levels can be selected and obtained as required, and the quick and clear use of downstream modules is facilitated.
As shown in fig. 13, corresponding to the above method, an embodiment of the present invention provides a road environment modeling apparatus, which includes a data receiving unit and a model constructing unit,
the data receiving unit is used for receiving upstream input data and internal historical data;
the model construction unit is used for performing data fusion and data reconstruction based on the received upstream input data and the internal historical data, and respectively constructing a static data model, a dynamic data model and a prediction data model.
For the functional role and implementation of the data receiving unit and the model building unit, reference is made to the above description of the method, which is not described in detail here.
In addition, an embodiment of the present invention provides a storage medium, where at least one instruction, at least one program, a code set, or an instruction set is stored in the storage medium, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the road environment modeling method.
In addition, an embodiment of the present invention provides a terminal device, where the terminal device includes a processor and a memory, where the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the road environment modeling method. The terminal device includes, but is not limited to, a computer device.
The storage medium and the computer device are further described below mainly in connection with application scenarios.
It should be apparent to those skilled in the art that the embodiments of the present invention may be provided as a method, apparatus (device or system), or computer device, storage medium. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention 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 invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices or systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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.
In a typical configuration, a computer device includes one or more processors (CPUs), memory, input/output interfaces, network interfaces, and memory. The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that 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 an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention 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.
In addition, the embodiment of the invention provides mobile equipment comprising the terminal equipment.
It should be noted that the mobile device referred to in the present application may include, but is not limited to, vehicles with six automatic driving skill levels, such as L0-L5, established by Society of automatic engineers International, SAE International, or national standard Automotive automation classification.
In some possible implementations, the mobile device may be a vehicle device or a robotic device having various functions as follows:
(1) manned functions, such as home cars, buses, and the like;
(2) cargo carrying functions, such as common trucks, van trucks, dump trailers, enclosed trucks, tank trucks, flat vans, container vans, dump trucks, special structure vans and the like;
(3) tool functions such as logistics distribution vehicles, Automated Guided Vehicles (AGV), patrol vehicles, cranes, excavators, bulldozers, forklifts, road rollers, loaders, off-road vehicles, armored vehicles, sewage treatment vehicles, sanitation vehicles, dust suction vehicles, ground cleaning vehicles, watering vehicles, sweeping robots, food delivery robots, shopping guide robots, lawn mowers, golf carts, etc.;
(4) entertainment functions, such as recreational vehicles, casino automatic drives, balance cars, and the like;
(5) special rescue functions, such as fire trucks, ambulances, electrical power rush-repair trucks, engineering rescue vehicles and the like.
Finally, it should be noted that: the foregoing examples are provided for illustration and description of the invention and are not intended to limit the invention to the described examples. Furthermore, it will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that many variations and modifications may be made in accordance with the teachings of the present invention, all of which are within the scope of the present invention as claimed.
Claims (12)
1. A method of modeling a road environment, comprising:
receiving upstream input data and internal history data;
and performing data fusion and data reconstruction based on the received upstream input data and the internal historical data, and respectively constructing a static data model, a dynamic data model and a prediction data model.
2. The road environment modeling method of claim 1, wherein constructing the static data model comprises:
step S11: determining the surrounding lane relation according to the self-parking position;
step S12: forming a lane reference line according to the lane relation determined in the step S11;
step S13: associating the road equipment and the identification information to the lane reference line formed at step S12, thereby obtaining static data;
step S14: and performing static semantic analysis on the static data obtained in the step S13, and overlaying the analysis result on the static data.
3. The method of claim 2, wherein the process of constructing the static data model during lane diversion further comprises:
when lane diversion is carried out, if the own vehicle is in front of a diversion point, the left lane of the own vehicle comprises a route where the own vehicle is located in front of the diversion point and a diversion route;
if the vehicle is behind the diversion point, when the vehicle is on the main road, the diversion road is the left lane of the vehicle, and the barrier on the diversion road is brought into the range of the concerned barrier; when the vehicle is on the diversion road, the main road is the right lane of the vehicle, and the obstacles on the main road are brought into the range of the concerned obstacles.
4. The road environment modeling method of claim 1,
the construction of the dynamic data model comprises the following steps:
step S21: projecting an obstacle onto a high-precision map to determine its location;
step S22: judging whether the obstacle conflicts with a current lane reference line or not, and selecting an attention obstacle;
step S23: associating the obstacle of interest selected in step S22 to a lane reference line, thereby obtaining dynamic data;
step S24: and performing dynamic semantic analysis on the dynamic data obtained in the step S23, and superimposing the analysis result on the dynamic data.
5. The method of claim 4, wherein the process of constructing the dynamic data model when performing lane merging further comprises:
if the self-vehicle is on the main road, the obstacles on the lane to be merged are related to the right side or the left side lane in a manner of giving a free entry point;
if the self-vehicle is on the lane to be merged, the obstacles on the main road are divided into two situations to be associated: one is that there is a point of intersection on the road structure and the current lane of the self-vehicle, the barrier is related to the current lane of the self-vehicle in a mode of freely entering the point; the other is that the intersection point does not exist on the road structure and the current lane of the self-vehicle, the intersection point exists with the future road of the self-vehicle, and the barrier is brought into the concerned barrier of the current lane of the self-vehicle in a forced entry point mode.
6. The method of claim 4, wherein the process of constructing the dynamic data model while traveling at an intersection further comprises:
if the vehicle goes straight at the crossroad, the barrier turning to the left is brought into the range of the concerned barrier in the form of a forced entry point; projecting the barrier of the right turn confluence to the current lane of the self-vehicle into the current lane of the self-vehicle in a free entry point mode;
if the vehicle turns left at the crossroad, the obstacles turning left and going straight to the lane are brought into the range of the concerned obstacles in the form of forced entry points; projecting the barrier of the right turn confluence to the current lane of the self-vehicle into the current lane of the self-vehicle in a free entry point mode;
if the self-vehicle turns right at the crossroad, the barrier turning left on the opposite lane is brought into the range of the barrier concerned in the form of a forced entry point; and projecting the obstacles which go straight to the current lane of the self-vehicle into the current lane of the self-vehicle in the form of free entry points.
7. The method of modeling a road environment of claim 1, wherein constructing the predictive data model comprises:
step S31: associating the predicted obstacle track with the corresponding dynamic obstacle, and superposing the obstacle track on static data;
step S32: and associating the predicted semantic information of the obstacle with the corresponding dynamic obstacle, and superposing the semantic information of the obstacle on the static data.
8. The road environment modeling method of claim 1, wherein the upstream input data includes data information provided by a high-precision map, a positioning device, a perception device, a business layer module, a vehicle floor module, and a prediction module;
the internal historical data comprises the historical frame data of the environment modeling module, the historical decision behavior of the decision module and the local path issued by the planning module.
9. A road environment modeling device is characterized by comprising a data receiving unit and a model building unit,
the data receiving unit is used for receiving upstream input data and internal historical data;
the model construction unit is used for performing data fusion and data reconstruction based on the received upstream input data and the internal historical data, and respectively constructing a static data model, a dynamic data model and a prediction data model.
10. A storage medium having stored therein at least one instruction, at least one program, a set of codes, or a set of instructions, which is loaded and executed by a processor to implement a road environment modeling method as claimed in any one of claims 1 to 8.
11. A terminal device, characterized in that it comprises a processor and a memory, in which at least one instruction, at least one program, set of codes or set of instructions is stored, which is loaded and executed by the processor to implement the road environment modeling method according to any one of claims 1 to 8.
12. A mobile device characterized in that it comprises a terminal device according to claim 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210497193.0A CN115098989A (en) | 2022-05-09 | 2022-05-09 | Road environment modeling method and device, storage medium, terminal and mobile device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210497193.0A CN115098989A (en) | 2022-05-09 | 2022-05-09 | Road environment modeling method and device, storage medium, terminal and mobile device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115098989A true CN115098989A (en) | 2022-09-23 |
Family
ID=83287325
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210497193.0A Pending CN115098989A (en) | 2022-05-09 | 2022-05-09 | Road environment modeling method and device, storage medium, terminal and mobile device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115098989A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109815555A (en) * | 2018-12-29 | 2019-05-28 | 百度在线网络技术（北京）有限公司 | The environmental modeling capability assessment method and system of automatic driving vehicle |
| CN111750886A (en) * | 2020-05-12 | 2020-10-09 | 北京智行者科技有限公司 | Local path planning method and device |
| CN111982143A (en) * | 2020-08-11 | 2020-11-24 | 北京汽车研究总院有限公司 | Vehicle and vehicle path planning method and device |
| CN111994090A (en) * | 2020-09-02 | 2020-11-27 | 中国科学技术大学 | Method and system for identifying lane-changing cut-in intention of driver based on hybrid strategy game |
| CN112277952A (en) * | 2020-11-05 | 2021-01-29 | 吉林大学 | Method for screening key obstacles under structured road |
| CN112762951A (en) * | 2018-03-20 | 2021-05-07 | 御眼视觉技术有限公司 | System and method for navigating a vehicle |
| CN114139329A (en) * | 2020-09-03 | 2022-03-04 | 华为技术有限公司 | Virtual test scene construction method and device |
| US20220081002A1 (en) * | 2020-09-16 | 2022-03-17 | Shenzhen Guo Dong Intelligent Drive Technologies Co., Ltd | Autonomous driving vehicle and dynamic planning method of drivable area |
-
2022
- 2022-05-09 CN CN202210497193.0A patent/CN115098989A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112762951A (en) * | 2018-03-20 | 2021-05-07 | 御眼视觉技术有限公司 | System and method for navigating a vehicle |
| CN109815555A (en) * | 2018-12-29 | 2019-05-28 | 百度在线网络技术（北京）有限公司 | The environmental modeling capability assessment method and system of automatic driving vehicle |
| CN111750886A (en) * | 2020-05-12 | 2020-10-09 | 北京智行者科技有限公司 | Local path planning method and device |
| CN111982143A (en) * | 2020-08-11 | 2020-11-24 | 北京汽车研究总院有限公司 | Vehicle and vehicle path planning method and device |
| CN111994090A (en) * | 2020-09-02 | 2020-11-27 | 中国科学技术大学 | Method and system for identifying lane-changing cut-in intention of driver based on hybrid strategy game |
| CN114139329A (en) * | 2020-09-03 | 2022-03-04 | 华为技术有限公司 | Virtual test scene construction method and device |
| US20220081002A1 (en) * | 2020-09-16 | 2022-03-17 | Shenzhen Guo Dong Intelligent Drive Technologies Co., Ltd | Autonomous driving vehicle and dynamic planning method of drivable area |
| CN112277952A (en) * | 2020-11-05 | 2021-01-29 | 吉林大学 | Method for screening key obstacles under structured road |
Non-Patent Citations (1)
| Title |
|---|
| 杨阿灵: "城市环境下无人驾驶车辆行车安全仿真研究", 《中国优秀硕士学位论文全文数据库》, 15 April 2022 (2022-04-15), pages 035 - 307 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11487296B2 (en) | Method and system for deterministic trajectory selection based on uncertainty estimation for an autonomous agent | |
| Singh et al. | Autonomous cars: Recent developments, challenges, and possible solutions | |
| Dokic et al. | European roadmap smart systems for automated driving | |
| González et al. | Continuous curvature planning with obstacle avoidance capabilities in urban scenarios | |
| CN114822008B (en) | Coordination of dispatch and maintenance of fleet of autonomous vehicles | |
| CN110118661B (en) | Method and device for processing driving simulation scene and storage medium | |
| CN108292473A (en) | Adaptive self vehicle planner logic | |
| Lattarulo et al. | Urban Motion Planning Framework Based on N‐Bézier Curves Considering Comfort and Safety | |
| JP2022084758A (en) | Vehicle monitoring method, device, electronic apparatus, storage medium, computer program, cloud control platform, and vehicle load cooperation system | |
| CN112710317A (en) | Automatic driving map generation method, automatic driving method and related product | |
| CN114964286A (en) | Trajectory planning information generation method and device, electronic equipment and storage medium | |
| Viktor et al. | Safety of the Introduction of Self-driving Vehicles in a Logistics Environment | |
| Hamid | Autonomous, connected, electric and shared vehicles: Disrupting the automotive and mobility sectors | |
| US11613269B2 (en) | Learning safety and human-centered constraints in autonomous vehicles | |
| CN115098989A (en) | Road environment modeling method and device, storage medium, terminal and mobile device | |
| Sarmento et al. | The autonomous vehicle challenges for emergent market | |
| Chen et al. | Task planning for highly automated driving | |
| AU2020103161A4 (en) | An novel method for a smart car - artificial intelligence based autonomous steering control system with voice assistance | |
| Karnati et al. | Artificial Intelligence in Self Driving Cars: Applications, Implications and Challenges | |
| Saberi et al. | On the impact of early design decisions on quality attributes of automated driving systems | |
| Chang et al. | Interaction-based driving scenario classification and labeling | |
| Dokur et al. | Internet of Vehicles-Based Autonomous Vehicle Platooning | |
| Björsell et al. | Future impacts of self-driving vehicles: A case study on the supply chain of e-commerce to identify important factors for the transport administrators of Sweden | |
| Amendola et al. | D1. 4-Final Release Of The Smart City Use Case | |
| Barbier et al. | Functional discretization of space using gaussian processes for road intersection crossing |
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: Room 2602, 22nd Floor, Building 4, Yard 8, Wenhuayuan West Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing 102600 Applicant before: Beijing Idriverplus Technology Co.,Ltd. |