CN109211247B - Space-time partition model and use method thereof - Google Patents
Space-time partition model and use method thereof Download PDFInfo
- Publication number
- CN109211247B CN109211247B CN201710521991.1A CN201710521991A CN109211247B CN 109211247 B CN109211247 B CN 109211247B CN 201710521991 A CN201710521991 A CN 201710521991A CN 109211247 B CN109211247 B CN 109211247B
- Authority
- CN
- China
- Prior art keywords
- space
- vehicle
- partition
- time
- information
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/025—Services making use of location information using location based information parameters
Abstract
The invention belongs to the technical field of intelligent driving, and particularly relates to a space-time partition model and a using method thereof. The method for constructing the space-time partition model comprises the steps of constructing time partitions, constructing dynamic space partitions and constructing static space partitions. The invention solves the technical problem that the data fusion between the V2X communication system and the vehicle-mounted intelligent driving system can not meet the requirements of space-time synchronization and consistency when vehicles with different intelligent driving grades are mixed on a road by the conventional V2X technology, so that the intelligent driving decision efficiency is low. By using the method of the invention, the time and space for processing the data of the intelligent driving system can be synchronized, the data processing efficiency of the intelligent driving system is improved and optimized, and the consistency of the driving condition and the fault analysis method is realized.
Description
Technical Field
The invention belongs to the technical field of intelligent driving, and particularly relates to a space-time partition model and a using method thereof.
Background
The unmanned automobile is an intelligent automobile, which can be called as a wheeled mobile robot, and mainly depends on an intelligent driver which is mainly a computer system in the automobile to realize unmanned driving. The unmanned automobile is an intelligent automobile which senses road environment through a vehicle-mounted sensing system, automatically plans a driving route and controls the automobile to reach a preset target. The vehicle-mounted sensor is used for sensing the surrounding environment of the vehicle, and the steering and the speed of the vehicle are controlled according to the road, the vehicle position and the obstacle information obtained by sensing, so that the vehicle can safely and reliably run on the road. The unmanned automobile integrates a plurality of technologies such as automatic control, a system structure, artificial intelligence, visual calculation and the like, is a product of high development of computer science, mode recognition and intelligent control technologies, is an important mark for measuring national scientific research strength and industrial level, and has wide application prospect in the fields of national defense and national economy.
The vehicle-road communication system is a V2X communication system, and includes both a vehicle-mounted system and a roadside system. Vehicle road communication is the earliest name. V2X (Vehicle to X) is a key technology of the future intelligent transportation system. It enables communication between cars, between cars and base stations, and between base stations. Therefore, a series of traffic information such as real-time road conditions, road information, pedestrian information and the like is obtained, so that the driving safety is improved, the congestion is reduced, the traffic efficiency is improved, and the vehicle-mounted entertainment information is provided. V2X is one of the core technologies for intelligent driving, and many key active safety technologies are built on the V2X technology, such as intersection collision avoidance, safety driving strategies based on traffic light signals, and so on.
According to the existing V2X technology, when vehicles of different intelligent driving grades run on a road in a mixed mode, the requirements of space-time synchronization and consistency cannot be met through data fusion between a V2X communication system and a vehicle-mounted intelligent driving system, and therefore the intelligent driving decision making efficiency is not high.
In addition to spatiotemporal synchronization, prioritization is one of the issues addressed by intelligent driving systems because V2X data employs a broadcast mode. The priority ranking and the data issuing and processing speed are also influence factors influencing the intelligent driving decision efficiency.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: according to the existing V2X technology, when vehicles of different intelligent driving grades run on a road in a mixed mode, the requirements of space-time synchronization and consistency cannot be met through data fusion between a V2X communication system and a vehicle-mounted intelligent driving system, and therefore the intelligent driving decision making efficiency is not high.
The technical scheme of the invention is as follows:
a spatio-temporal partition model construction method comprises the following steps:
step 1, constructing time partitions
Dividing the intelligent driving behavior time consumption into five grades according to the intelligent driving behavior time consumption to form a time partition; specifically, the first-level time partition, namely, the action decision-level time partition: the action takes 1-200 milliseconds; secondary time partitioning, i.e. action control level time partitioning: the action takes 0.1-2 seconds; three-stage time partitioning, namely short path decision stage time partitioning: the action takes 1-30 seconds; four-stage time partitioning, namely long-path decision-stage time partitioning: the action takes 0.5-30 minutes; five-level time partitioning, i.e., full active time domain time partitioning: the action takes more than 0.5 hour;
step 2, constructing dynamic space partition
Step 2.1, establishing a dynamic space partition coordinate system
Constructing a dynamic coordinate system by taking a vertical point from a positioning position point of the main vehicle to a center line of a lane where the main vehicle is positioned as a coordinate origin and taking the center line direction of the lane in the same direction as the driving direction of the main vehicle as an X axis;
step 2.2, establishing a primary dynamic space partition
Acquiring a minimum spatial area required to be perceived by the driving action decision of the main vehicle, wherein the minimum spatial area forms a primary dynamic spatial partition;
step 2.3, establishing secondary dynamic space partition
Acquiring primary dynamic spaces of all vehicles on the primary dynamic space partition boundary of the main vehicle, solving a union set of the primary dynamic spaces of all vehicles on the boundary, and removing a primary dynamic space area of the main vehicle from a result obtained by solving the union set to form a secondary dynamic space partition;
step 2.4, establishing three-level dynamic space partition
Acquiring a space range covered by the movement of the main vehicle due to all intelligent driving behaviors in a three-level time partition of the main vehicle, and removing a first-level dynamic space partition and a second-level dynamic space partition from the space range to form a three-level dynamic space partition;
step 3, constructing static space partitions
Dividing the high-precision road map data into road sections with the length of 50-100 meters, setting a unique identification code for each road section, and storing lane-level map data of each road section to form a static space partition; the lane-level map data for each road section contains the following: longitude and latitude coordinates, lane information, traffic rule information, road surface information, road shoulders and road side facilities; the data in the static space subarea is updated in real time through V2X roadside communication equipment according to the recorded data updating time and road situational requirements; and finishing the construction of the space-time partition model.
A method for carrying out data fusion and processing by using the space-time partition model specifically comprises the following steps:
step 1, creating dynamic space data
Constructing a dynamic coordinate system by taking a vertical point from a positioning position point of the main vehicle to a center line of a lane where the main vehicle is positioned as a coordinate origin and taking the center line direction of the lane in the same direction as the driving direction of the main vehicle as an X axis; in the dynamic coordinate system, sensing the position data of surrounding vehicles and moving objects through sensors, and matching the obtained position data into primary, secondary and tertiary dynamic spaces of the main vehicle;
acquiring lane data in the static space subarea, and mapping the lane data in the static space subarea into a dynamic space coordinate system of the main vehicle;
mapping the vehicle and moving object information in the static space in the V2X message into the dynamic space coordinate system of the host vehicle;
step 2, data fusion and data processing
Selecting data with high reliability or correcting data of multiple sources through an algorithm aiming at repeated and conflicting information redundancy of vehicles or moving objects in the subareas; the high-confidence data is data with relatively small space-time error according to the evaluation of the time error and the space error of the sensor or V2X data;
if the precision is not large, acquiring the shape parameters of the vehicle or the moving object through V2X or other ways, and calculating the position and the attitude of the vehicle or the moving object according to the shape parameters, the sensor observation angle and the positioning data so as to correct the position information of the vehicle or the moving object;
step 3, exchanging V2X information
The V2X information exchange comprises V2X information exchange of roadside equipment and V2X information exchange of a vehicle-mounted intelligent driving system;
the roadside device's V2X information exchange includes a static spatial partitioning data update service; the V2X information exchange of the road side equipment also comprises the steps of converting the received vehicle position information into vehicle information in a static space partition, summarizing the vehicle information together according to a time partition, and then releasing the vehicle information to the vehicles on the road; the V2X information exchange of the road side equipment also comprises traffic control or restriction information and early warning or alarm information;
the V2X information exchange of the vehicle-mounted intelligent driving system comprises the position, the speed, the vehicle condition and the vehicle shape parameter of the issued main vehicle and the position and the speed information of the moving object in the first-stage dynamic space-time partition sensed by the main vehicle sensor; the main vehicle information is issued by using a static space position, and the sensor information is issued by using a dynamic space position.
The invention has the beneficial effects that: the method solves the problem of time-space synchronization of data processing of the intelligent driving system, improves and optimizes the data processing efficiency of the intelligent driving system, and realizes the consistency of the driving condition and fault analysis method.
Drawings
FIG. 1 is a schematic diagram of dynamic spatial partitioning;
FIG. 2 is a diagram of two-level dynamic spatial partitioning;
FIG. 3 is a diagram of static spatial zoning.
Detailed Description
The invention solves the problem that the data fusion between a V2X communication system and a vehicle-mounted intelligent driving system can not meet the requirements of space-time synchronization and consistency by constructing a space-time partition model, and the specific steps of constructing the space-time partition model are as follows:
step 1, constructing time partitions
And dividing the intelligent driving behavior time consumption into five grades according to the intelligent driving behavior time consumption to form a time partition. Specifically, the first-level time partition, namely, the action decision-level time partition: the action takes 1-200 milliseconds; secondary time partitioning, i.e. action control level time partitioning: the action takes 0.1-2 seconds; three-stage time partitioning, namely short path decision stage time partitioning: the action takes 1-30 seconds; four-stage time partitioning, namely long-path decision-stage time partitioning: the action takes 0.5-30 minutes; five-level time partitioning, i.e., full active time domain time partitioning: the activity took more than 0.5 hours.
Step 2, constructing dynamic space partition
As shown in fig. 1, the dynamic space partition construction specifically includes the following steps:
step 2.1, establishing a dynamic space partition coordinate system
A dynamic coordinate system is established by taking a vertical point from a positioning position point of the main vehicle to a center line of a lane where the main vehicle is positioned as a coordinate origin and taking the center line direction of the lane in the same direction as the driving direction of the main vehicle as an X axis.
Step 2.2, establishing a primary dynamic space partition
And acquiring a minimum space area required to be perceived by the driving action decision of the main vehicle, wherein the minimum space area forms a primary dynamic space subarea.
Step 2.3, establishing secondary dynamic space partition
The primary dynamic space of all vehicles on the boundary of the primary dynamic space partition of the main vehicle is obtained, the primary dynamic space of all vehicles on the boundary is subjected to union, the primary dynamic space area of the main vehicle is removed from the result obtained by union, and a secondary dynamic space partition is formed, as shown in fig. 2.
Step 2.4, establishing three-level dynamic space partition
And acquiring a space range covered by the movement of the main vehicle due to all intelligent driving behaviors in the three-level time partition of the main vehicle, and removing the first-level dynamic space partition and the second-level dynamic space partition from the space range to form a three-level dynamic space partition.
Step 3, constructing static space partitions
As shown in fig. 3, the high-precision road map data is divided into segments of 50 to 100 meters long, each segment is provided with a unique identification code, and lane-level map data of each segment is stored to form static space partitions. The lane-level map data for each road section contains the following: longitude and latitude coordinates, lane information, traffic rule information, road surface information, road shoulders and road side facilities. And the data in the static space subarea is updated in real time through V2X road-side communication equipment according to the recorded data updating time and road situational requirements. And finishing the construction of the space-time partition model.
The data in the static space and the dynamic space include basic geographic information, vehicle and moving object information, and dynamically changing road driving environment information, wherein the road driving environment information includes temperature, visibility and light. The vehicle and moving object information includes a position, a speed, a moving direction, and a moving posture.
The invention also provides a method for carrying out data fusion and processing by using the space-time partition model, which specifically comprises the following steps:
step 1, creating dynamic space data
A dynamic coordinate system is established by taking a vertical point from a positioning position point of the main vehicle to a center line of a lane where the main vehicle is positioned as a coordinate origin and taking the center line direction of the lane in the same direction as the driving direction of the main vehicle as an X axis. In the dynamic coordinate system, the position data of the surrounding vehicles and moving objects are sensed through sensors, and the obtained position data are matched into the primary, secondary and tertiary dynamic spaces of the main vehicle.
And acquiring lane data in the static space subarea, and mapping the lane data in the static space subarea to a dynamic space coordinate system of the host vehicle.
The vehicle and moving object information in the static space in the V2X message is also mapped into the dynamic space coordinate system of the host vehicle.
Step 2, data fusion and data processing
For repeated and conflicting information redundancy of vehicles or moving objects within a zone, data of high confidence is selected or data of multiple sources is corrected by an algorithm. The high confidence data is data with relatively small spatio-temporal errors based on an evaluation of the temporal and spatial errors of the sensor or V2X data.
If the precision is not very different, the shape parameters of the vehicle or the moving object are obtained through V2X or other ways, and the position and the attitude of the vehicle or the moving object are calculated according to the shape parameters, the observation angle of the sensor and the positioning data, so that the position information of the vehicle or the moving object is corrected. Generally, a vehicle positioning point and a vertical point of a center line of a lane are taken as a dynamic space coordinate origin. The position of the vehicle or the moving object may be converted into coordinates of a space, and may be represented by a distance from an origin and a viewing angle.
The working condition judgment and the effect judgment are mainly used for analyzing and judging the optional action of the driving decision and the execution effect of the driving action according to the current road traffic state, and provide judgment basis for executing, correcting or changing the driving decision.
The driving decision includes a long path decision and a short path decision. In addition to path decision, driving intent may be accomplished through a combination of driving actions. The driving action comprises the control force of an accelerator, a brake and a steering wheel. In the spatiotemporal partitioning model, a long path decision is made in a tertiary or quaternary spatiotemporal partition, a short path decision is made in a secondary or tertiary spatiotemporal partition, and a driving action is made in a primary spatiotemporal partition.
Step 3, exchanging V2X information
The V2X information exchange comprises V2X information exchange of roadside equipment and V2X information exchange of an on-vehicle intelligent driving system.
The roadside device's V2X information exchange includes a static spatial partitioning data update service. The information exchange of the V2X of the road side equipment also comprises the step of converting the received vehicle position information into vehicle information in a static space subarea, summarizing the vehicle information together according to a time subarea, and then distributing the vehicle information to the vehicles on the road. The information exchange of the V2X information of the road side equipment also comprises traffic control or restriction information, and early warning or alarming information such as accident, fault and road surface information.
The V2X information exchange of the vehicle-mounted intelligent driving system mainly comprises the position, speed, vehicle condition and vehicle shape parameters of the main vehicle and the position and speed information of the moving object in the first-stage dynamic space-time partition sensed by the main vehicle sensor. The main vehicle information is issued by using a static space position, and the sensor information is issued by using a dynamic space position.
The information released during the information exchange of the V2X of the road side equipment is released in a static space position. Therefore, the sensor information of the vehicle-mounted intelligent driving system received during the information exchange of the V2X of the roadside device needs to be subjected to coordinate transformation during data fusion. On the contrary, the vehicle-mounted intelligent driving system also needs to perform coordinate conversion when receiving the V2X information of the road side equipment.
Claims (2)
1. A spatio-temporal partition model construction method is characterized by comprising the following steps:
step 1, constructing time partitions
Dividing the intelligent driving behavior time consumption into five grades according to the intelligent driving behavior time consumption to form a time partition; specifically, the first-level time partition, namely, the action decision-level time partition: the action takes 1-200 milliseconds; secondary time partitioning, i.e. action control level time partitioning: the action takes 0.1-2 seconds; three-stage time partitioning, namely short path decision stage time partitioning: the action takes 1-30 seconds; four-stage time partitioning, namely long-path decision-stage time partitioning: the action takes 0.5-30 minutes; five-level time partitioning, i.e., full active time domain time partitioning: the action takes more than 0.5 hour;
step 2, constructing dynamic space partition
Step 2.1, establishing a dynamic space partition coordinate system
Constructing a dynamic coordinate system by taking a vertical point from a positioning position point of the main vehicle to a center line of a lane where the main vehicle is positioned as a coordinate origin and taking the center line direction of the lane in the same direction as the driving direction of the main vehicle as an X axis;
step 2.2, establishing a primary dynamic space partition
Acquiring a minimum spatial area required to be perceived by the driving action decision of the main vehicle, wherein the minimum spatial area forms a primary dynamic spatial partition;
step 2.3, establishing secondary dynamic space partition
Acquiring primary dynamic spaces of all vehicles on the primary dynamic space partition boundary of the main vehicle, solving a union set of the primary dynamic spaces of all vehicles on the boundary, and removing a primary dynamic space area of the main vehicle from a result obtained by solving the union set to form a secondary dynamic space partition;
step 2.4, establishing three-level dynamic space partition
Acquiring a space range covered by the movement of the main vehicle due to all intelligent driving behaviors in a three-level time partition of the main vehicle, and removing a first-level dynamic space partition and a second-level dynamic space partition from the space range to form a three-level dynamic space partition;
step 3, constructing static space partitions
Dividing the high-precision road map data into road sections with the length of 50-100 meters, setting a unique identification code for each road section, and storing lane-level map data of each road section to form a static space partition; the lane-level map data for each road section contains the following: longitude and latitude coordinates, lane information, traffic rule information, road surface information, road shoulders and road side facilities; the data in the static space subarea is updated in real time through V2X roadside communication equipment according to the recorded data updating time and road situational requirements; and finishing the construction of the space-time partition model.
2. A method for performing data fusion and processing by using the spatio-temporal partition model constructed by the spatio-temporal partition model construction method of claim 1 is characterized by comprising the following steps:
step 1, creating dynamic space data
Constructing a dynamic coordinate system by taking a vertical point from a positioning position point of the main vehicle to a center line of a lane where the main vehicle is positioned as a coordinate origin and taking the center line direction of the lane in the same direction as the driving direction of the main vehicle as an X axis; in the dynamic coordinate system, sensing the position data of surrounding vehicles and moving objects through sensors, and matching the obtained position data into primary, secondary and tertiary dynamic spaces of the main vehicle;
acquiring lane data in the static space subarea, and mapping the lane data in the static space subarea into a dynamic space coordinate system of the main vehicle;
mapping the vehicle and moving object information in the static space in the V2X message into the dynamic space coordinate system of the host vehicle;
step 2, data fusion and data processing
Selecting data with high reliability or correcting data of multiple sources through an algorithm aiming at repeated and conflicting information redundancy of vehicles or moving objects in the subareas; the high-confidence data is data with relatively small space-time error according to the evaluation of the time error and the space error of the sensor or V2X data;
if the space-time error is within the acceptable range, acquiring the shape parameters of the vehicle or the moving object through V2X or other ways, and calculating the position and the posture of the vehicle or the moving object according to the shape parameters, the sensor observation angle and the positioning data so as to correct the position information of the vehicle or the moving object;
step 3, exchanging V2X information
The V2X information exchange comprises V2X information exchange of roadside equipment and V2X information exchange of a vehicle-mounted intelligent driving system;
the roadside device's V2X information exchange includes a static spatial partitioning data update service; the V2X information exchange of the road side equipment also comprises the steps of converting the received vehicle position information into vehicle information in a static space partition, summarizing the vehicle information together according to a time partition, and then releasing the vehicle information to the vehicles on the road; the V2X information exchange of the road side equipment also comprises traffic control or restriction information and early warning or alarm information;
the V2X information exchange of the vehicle-mounted intelligent driving system comprises the position, the speed, the vehicle condition and the vehicle shape parameter of the issued main vehicle and the position and the speed information of the moving object in the first-stage dynamic space-time partition sensed by the main vehicle sensor; the main vehicle information is issued by using a static space position, and the sensor information is issued by using a dynamic space position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710521991.1A CN109211247B (en) | 2017-06-30 | 2017-06-30 | Space-time partition model and use method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710521991.1A CN109211247B (en) | 2017-06-30 | 2017-06-30 | Space-time partition model and use method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109211247A CN109211247A (en) | 2019-01-15 |
| CN109211247B true CN109211247B (en) | 2022-02-01 |
Family
ID=64977106
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710521991.1A Active CN109211247B (en) | 2017-06-30 | 2017-06-30 | Space-time partition model and use method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109211247B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110006440B (en) * | 2019-04-12 | 2021-02-05 | 北京百度网讯科技有限公司 | Map relation expression method and device, electronic equipment and storage medium |
| CN112053592A (en) * | 2020-04-28 | 2020-12-08 | 上海波若智能科技有限公司 | Road network dynamic data acquisition method and road network dynamic data acquisition system |
| CN113012429B (en) * | 2021-02-23 | 2022-07-15 | 云控智行(上海)汽车科技有限公司 | Vehicle road multi-sensor data fusion method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102710796A (en) * | 2012-06-20 | 2012-10-03 | 张�林 | Area data downloading method and device based on multi-level partition network |
| CN103544065A (en) * | 2013-11-05 | 2014-01-29 | 中国航空工业集团公司西安飞机设计研究所 | Avionics system partition window scheduling method under ARINC653 standard |
| CN104112363A (en) * | 2014-07-04 | 2014-10-22 | 西安交通大学 | Multi-sensing-data space-time synchronization method and road multi-sensing-data vehicle-mounted acquisition system |
| CN106885601A (en) * | 2017-01-09 | 2017-06-23 | 北京理工大学 | Unmanned vehicle multi-sensor data synchronous |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7024481B2 (en) * | 2001-11-01 | 2006-04-04 | Microsoft Corporation | Method and framework for processing network communication protocol timers |
-
2017
- 2017-06-30 CN CN201710521991.1A patent/CN109211247B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102710796A (en) * | 2012-06-20 | 2012-10-03 | 张�林 | Area data downloading method and device based on multi-level partition network |
| CN103544065A (en) * | 2013-11-05 | 2014-01-29 | 中国航空工业集团公司西安飞机设计研究所 | Avionics system partition window scheduling method under ARINC653 standard |
| CN104112363A (en) * | 2014-07-04 | 2014-10-22 | 西安交通大学 | Multi-sensing-data space-time synchronization method and road multi-sensing-data vehicle-mounted acquisition system |
| CN106885601A (en) * | 2017-01-09 | 2017-06-23 | 北京理工大学 | Unmanned vehicle multi-sensor data synchronous |
Non-Patent Citations (1)
| Title |
|---|
| 车联网环境下交通信息分发与处理关键技术研究;莫元富;《中国博士学位论文全文数据库·工程科技Ⅱ辑》;20170315;第C034-20页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109211247A (en) | 2019-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111240328B (en) | Vehicle driving safety monitoring method and device and unmanned vehicle | |
| US11027751B2 (en) | Reinforcement and model learning for vehicle operation | |
| EP3526737B1 (en) | Neural network system for autonomous vehicle control | |
| US11106218B2 (en) | Adaptive mapping to navigate autonomous vehicles responsive to physical environment changes | |
| CN109641589B (en) | Route planning for autonomous vehicles | |
| CN111292540B (en) | Method, control device and system for determining specific state information | |
| US11702070B2 (en) | Autonomous vehicle operation with explicit occlusion reasoning | |
| US20170248964A1 (en) | Autonomous vehicle fleet service and system | |
| US11891087B2 (en) | Systems and methods for generating behavioral predictions in reaction to autonomous vehicle movement | |
| CN113692373B (en) | Retention and range analysis for autonomous vehicle services | |
| CN109211247B (en) | Space-time partition model and use method thereof | |
| CN109808684A (en) | False anticollision warning is reduced to the maximum extent | |
| US11697429B2 (en) | System, method, and computer program product for topological planning in autonomous driving using bounds representations | |
| JP2022041923A (en) | Vehicle path designation using connected data analysis platform | |
| GB2600188A (en) | Metric back-propagation for subsystem performance evaluation | |
| EP3945737A1 (en) | Vehicle management system, management method, and program | |
| KR20220073472A (en) | Cross section integrated information providing system and method based on V2X | |
| JP7167732B2 (en) | map information system | |
| CN116257058A (en) | Intelligent local planning method for automatic driving logistics trolley in park | |
| Amudha | ACDS—Assisted Cooperative Decision-Support for reliable interaction based navigation assistance for autonomous vehicles | |
| US20230080281A1 (en) | Precautionary observation zone for vehicle routing | |
| US20220413510A1 (en) | Targeted driving for autonomous vehicles | |
| CN114442596A (en) | Vehicle testing method and system | |
| Worrall et al. | A probabilistic method for detecting impending vehicle interactions | |
| JP2021152853A (en) | Traffic control system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |