CN107451611A - A kind of vehicle-mounted deep learning model update method of new energy unmanned vehicle - Google Patents
A kind of vehicle-mounted deep learning model update method of new energy unmanned vehicle Download PDFInfo
- Publication number
- CN107451611A CN107451611A CN201710629271.7A CN201710629271A CN107451611A CN 107451611 A CN107451611 A CN 107451611A CN 201710629271 A CN201710629271 A CN 201710629271A CN 107451611 A CN107451611 A CN 107451611A
- Authority
- CN
- China
- Prior art keywords
- unmanned vehicle
- vehicle
- deep learning
- learning model
- data
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Stored Programmes (AREA)
Abstract
A kind of vehicle-mounted deep learning model update method of new energy unmanned vehicle, this method include：Charging gun Connection Step, road information uploading step, model generation step, model download step.Because the application is after the charging gun access port of new energy unmanned vehicle is connected with the charging gun of charging pile, the road information of onboard sensor collection is uploaded using charging pile and optical fiber, so that unmanned vehicle is when charging, unmanned vehicle platform can regenerate deep learning model according to the road information of upload, the deep learning model regenerated is back to the vehicle-mounted hard disks of unmanned vehicle by optical fiber and charging pile, update vehicle-mounted deep learning model, compared with prior art, data transmission efficiency is higher, cost is relatively low, and deep learning model update method is more convenient, more efficient.
Description
Technical field
The present invention relates to unmanned technical field, and in particular to a kind of vehicle-mounted deep learning model of new energy unmanned vehicle is more
New method and system.
Background technology
Deep learning nerual network technique achieves huge breakthrough recent years, especially in voice and image recognition application
On have qualitative leap, need to perform deep learning program large-scale distributedly in unmanned vehicle cloud platform, generate deep learning
Model, recognition performance to environment can be lifted by being equipped with the unmanned vehicle of accurate deep learning model.And accurate deep learning
The generation of model is not easy to, it is necessary to fully analyze the magnanimity road information of onboard sensor collection.At present, how to update vehicle-mounted
Deep learning model the problem of being urgent need to resolve.
Updating vehicle-mounted deep learning model includes road information upload, model learning and model download.Wherein, it is existing
Road information method for uploading is, by unloading vehicle-mounted hard disks daily, will be stored in the magnanimity number of the sensor collection of vehicle-mounted hard disks
Be copied to computer according to artificial, then by data be uploaded to unmanned vehicle cloud platform or, by wireless communication networks, such as 4G networks,
The magnanimity road information that sensor gathers is uploaded to unmanned vehicle cloud platform in real time；And existing model download method is typically logical
Cross vehicle-mounted hard disks copy or wireless communication networks regularly update vehicle-mounted deep learning model.
It is excessive, less efficient to unload the method human intervention of vehicle-mounted hard disks upload data, and it is also easy to dismantle hard disk daily
Hard disk is caused to damage；Cordless communication network uploads data and the method for downloading deep learning model, because；Cordless communication network number
Often smaller according to bandwidth, for example, 4G network speeds only have 100Mbps, the data of magnanimity, which upload, needs longer time, and data pass
Defeated efficiency is low, moreover, failing the place of covering in cordless communication network, it is possible to cause data not upload normally, number occur
The phenomenon passed according to leakage, in addition, the data that magnanimity is uploaded using cordless communication network generally require a larger expense.
The content of the invention
The application provides a kind of vehicle-mounted deep learning model update method of new energy unmanned vehicle, in the same of unmanned vehicle charging
When, the road information that unmanned vehicle gathers is uploaded to unmanned vehicle cloud platform using charging pile and regenerates deep learning model, then
Generated deep learning model is returned into unmanned vehicle, updates vehicle-mounted deep learning model, deep learning model modification is more convenient,
It is more efficient.
There is provided a kind of new energy unmanned vehicle vehicle-mounted deep learning model update method in a kind of embodiment, what this method was applicable
The charging gun access port of new energy unmanned vehicle includes：Power injection interface and the first data-interface, correspondingly, charging gun is provided with
Corresponding electric energy output interface and the second data-interface, this method include：
Charging gun Connection Step, the charging gun access port are connected with the charging gun of charging pile, and new energy unmanned vehicle leads to
Cross the power injection interface and electric energy output interface is obtained while charging, also exported by first data-interface vehicle-mounted
Road information that sensor gathers, being stored in vehicle-mounted hard disks；
Vehicle-mounted data uploading step, charging pile obtain what first data-interface exported by second data-interface
The road information of acquisition is uploaded to unmanned vehicle cloud platform by road information, charging pile by optical fiber；
Model generation step, unmanned vehicle cloud platform regenerate deep learning model according to the road information received；
The deep learning model data of generation is transmitted through the fiber to charging by model download step, unmanned vehicle cloud platform
Stake, charging pile is again transmitted the deep learning model data regenerated to vehicle-mounted hard disks by charging gun, vehicle-mounted so as to update
Deep learning model.
In some embodiments, the model download step also includes：
The deep learning model data regenerated can be also downloaded to car by unmanned vehicle cloud platform by cordless communication network
Hard disk is carried, so as to update vehicle-mounted deep learning model.
In some embodiments, first data-interface also exports new energy unmanned vehicle number information.
In some embodiments, the road information uploading step includes：
Charging pile obtains the road information of new energy unmanned vehicle number information and the collection of new energy unmanned vehicle sensor；
The new energy unmanned vehicle number information of acquisition is uploaded to unmanned vehicle cloud platform by charging pile by optical fiber；
Unmanned vehicle cloud platform generates log-on message or inquiry log-on message according to the new energy unmanned vehicle number information,
And feed back registered information to charging pile；
After charging pile receives registered information, the road information of acquisition is uploaded to unmanned vehicle cloud by optical fiber and put down
Platform；
Unmanned vehicle cloud platform stores the road information according to the log-on message.
According to above-described embodiment, because the application is in the charging gun access port of new energy unmanned vehicle and the charging gun of charging pile
After being connected, utilize charging pile and optical fiber to upload the road information of onboard sensor collection so that unmanned vehicle when charging,
Unmanned vehicle platform can regenerate deep learning model according to the road information of upload, and the deep learning model regenerated is by light
Fine and charging pile is back to the vehicle-mounted hard disks of unmanned vehicle, updates vehicle-mounted deep learning model, compared with prior art, data transfer effect
Rate is higher, cost is relatively low, and deep learning model update method is more convenient, more efficient.
Brief description of the drawings
Fig. 1 is a kind of new energy unmanned vehicle charging gun access port schematic diagram of embodiment；
Fig. 2 is a kind of charging gun interface diagram of embodiment；
Fig. 3 is the vehicle-mounted deep learning model update method flow chart of a kind of new energy unmanned vehicle that the application provides；
Fig. 4 is the vehicle-mounted deep learning model modification view of new energy unmanned vehicle that the application provides；
Fig. 5 is a kind of vehicle-mounted deep learning model modification process schematic of new energy unmanned vehicle of embodiment.
Embodiment
The present invention is described in further detail below by embodiment combination accompanying drawing.Wherein different embodiments
Middle similar component employs associated similar element numbers.In the following embodiments, many detailed descriptions be in order to
The application is better understood.However, those skilled in the art can be without lifting an eyebrow recognize, which part feature
It is dispensed, or can be substituted by other elements, material, method in varied situations.In some cases, this Shen
Certain operations that please be related are not shown in the description or description, and this is the core in order to avoid the application by mistake
More descriptions are flooded, and to those skilled in the art, be described in detail these associative operations be not it is necessary, they
The general technology knowledge of description and this area in specification can completely understand associative operation.
In addition, feature described in this description, operation or feature can combine to form respectively in any suitable way
Kind embodiment.Meanwhile each step in method description or action can also can be aobvious and easy according to those skilled in the art institute
The mode carry out order exchange or adjustment seen.Therefore, the various orders in specification and drawings are intended merely to clearly describe a certain
Individual embodiment, necessary order is not meant to be, wherein some sequentially must comply with unless otherwise indicated.
Because new energy unmanned vehicle is in driving procedure, the data per second that will all gather magnanimity, the data of these magnanimity need
Upload to unmanned vehicle cloud platform and be used to generate out more preferable deep learning model, generated deep learning model will be returned
Unmanned vehicle is transmitted to, so as to update vehicle-mounted deep learning model.However, in the prior art, by the side for unloading vehicle-mounted hard disks daily
Formula and cordless communication network upload by way of, the problem of efficiency of transmission is relatively low all be present.Inventor when conceiving the application,
It is required for the present situation of charging daily based on new energy unmanned vehicle, there is provided a kind of vehicle-mounted deep learning model of new energy unmanned vehicle is more
New method, while being that unmanned vehicle charges using charging pile, the mass data stored in vehicle-mounted hard disks is uploaded by optical fiber
, again will be new using optical fiber and charging pile after the generated new deep learning model of unmanned vehicle cloud platform to unmanned vehicle cloud platform
Deep learning model return to unmanned vehicle, so as to update vehicle-mounted deep learning model.
Embodiment one：
A kind of vehicle-mounted deep learning model update method of new energy unmanned vehicle of the application, with reference to figure 1 and Fig. 2, this method is fitted
The charging gun access port of new energy unmanned vehicle includes：The data-interface 11 of power injection interface 12 and first, correspondingly, charging
Rifle is provided with the corresponding data-interface 31 of electric energy output interface 32 and second.In some embodiments, to prevent forceful electric power during charging
Data transfer is interfered, first screen layer 13 is additionally provided between the data-interface 11 of power injection interface 12 and first, electricity
Secondary shielding layer 33 can be additionally provided between the data-interface 31 of input interface 32 and second.
With reference to figure 3 and Fig. 4, this method includes：
Charging gun Connection Step 100, charging gun access port are connected with the charging gun of charging pile, and new energy unmanned vehicle passes through
While power injection interface 12 obtains charging, sensing stored in vehicle-mounted hard disks, vehicle-mounted is exported by the first data-interface 11
The road information of device collection；
Road information uploading step 200, after charging pile obtains the road information, the road information of acquisition is transmitted to nothing
People's car cloud platform；
Model generation step 300, unmanned vehicle cloud platform are generated according to the road information received using deep learning model
Algorithm regenerates deep learning model；
Model download step 400, unmanned vehicle cloud platform transmit the deep learning model data regenerated by optical fiber
To charging pile, charging pile is again transmitted the deep learning model data regenerated to vehicle-mounted hard disks by charging gun, so as to more
New vehicle-mounted deep learning model.
In some embodiments, the road information of onboard sensor collection includes：What unmanned vehicle was collected into the process of moving
View data, for example, drive recorder monitor video.
In some embodiments, the first data-interface 11 also exports new energy unmanned vehicle number information to charging pile.First number
The form exported according to interface 11 to the data of charging pile is：
<Number information, time, data type, annotation>
Wherein, number information is to distinguish different unmanned vehicles, and unmanned vehicle cloud platform is numbered by new energy unmanned vehicle
The data that data separation difference unmanned vehicle uploads；Time is the acquisition time of the data currently uploaded, convenient to distinguish different time
The data being collected into；Data type can be view data, text data, laser radar data, gps data etc.；Annotation is
Deep explanation to file.
In one embodiment, road information uploading step 200 includes：
Charging pile obtains the road information of new energy unmanned vehicle number information and the collection of new energy unmanned vehicle sensor；
The new energy unmanned vehicle number information of acquisition is uploaded to unmanned vehicle cloud platform by charging pile by optical fiber；
Unmanned vehicle cloud platform generates log-on message or inquiry log-on message according to the new energy unmanned vehicle number information,
And feed back registered information to charging pile；
After charging pile receives registered information, the road information of acquisition is uploaded to unmanned vehicle cloud by optical fiber and put down
Platform；
Unmanned vehicle cloud platform stores the road information according to the log-on message.
It is pointed out that same new energy unmanned vehicle number information need to only generate a log-on message, generating
After log-on message, same new energy unmanned vehicle number information uploads again, server will according to new energy unmanned vehicle number information,
Automatically inquire about and match corresponding log-on message.
In some embodiments, model generation step 300 includes：
The data uploaded are read, the data of upload mainly include unmanned vehicle number information and unmanned vehicle car in the process of moving
The view data that set sensor collects；
After the data uploaded, the feature in view data, such as point, curve etc. are extracted using convolutional network；
Reuse activation network and deactivate useful feature, reduce the quantity of feature to reduce amount of calculation；
Image is classified using useful feature, generates corresponding label；
The value and the value of default label of generation label are compared, and feedback learning is carried out to network using difference；
Above step is constantly repeated, repetition training is carried out, until the performance of neutral net no longer improves.
As shown in figure 5, be a kind of vehicle-mounted deep learning model modification process schematic of new energy unmanned vehicle of embodiment, tool
Body includes：
First, after the charging gun access port of new energy unmanned vehicle is connected with the charging gun of charging pile, new energy unmanned vehicle
While obtaining charging pile charging by power injection interface 12, also exported in vehicle-mounted hard disks and stored by the first data-interface 11
Road information to charging pile；
Secondly, charging pile will obtain road information and transmit to unmanned vehicle cloud platform after road information is obtained；
Again, unmanned vehicle cloud platform regenerates mould according to the road information received using depth model algorithm is generated
Type；
Finally, the model data regenerated is transmitted through the fiber to charging pile by unmanned vehicle cloud platform, and charging pile leads to again
Overcharge rifle transmits model data again to vehicle-mounted hard disks, so as to update vehicle-mounted deep learning model.
Due to being generally connected for the ease of charging, existing charging pile by optical fiber with computer or the server of charging
Connect, optical fiber used herein need not simultaneously be laid again, will not additionally increase cost, with existing vehicle-mounted deep learning model
Update scheme is compared, and the vehicle-mounted deep learning model update method and system data transmission of the application are more efficient, cost is relatively low.
Embodiment two：
Due to the data volume for downloading vehicle-mounted deep learning model and time that is little and regenerating deep learning model
Charging duration can be can exceed that, unmanned vehicle cloud platform does not regenerate also when completing to charge to avoid unmanned vehicle
Deep learning model, in model download step 400, unmanned vehicle cloud platform be able to will also be regenerated by cordless communication network
Model data is downloaded to vehicle-mounted hard disks, so as to update vehicle-mounted deep learning model.
In some embodiments, cordless communication network includes mobile communications network or WIFI network.
It will be understood by those skilled in the art that all or part of function of various methods can pass through in above-mentioned embodiment
The mode of hardware is realized, can also be realized by way of computer program.When all or part of function in above-mentioned embodiment
When being realized by way of computer program, the program can be stored in a computer-readable recording medium, and storage medium can
With including：Read-only storage, random access memory, disk, CD, hard disk etc., it is above-mentioned to realize that the program is performed by computer
Function.For example, by program storage in the memory of equipment, when passing through computing device memory Program, you can in realization
State all or part of function.In addition, when in above-mentioned embodiment all or part of function realized by way of computer program
When, the program can also be stored in the storage mediums such as server, another computer, disk, CD, flash disk or mobile hard disk
In, by download or copying and saving into the memory of local device, or version updating is carried out to the system of local device, when logical
When crossing the program in computing device memory, you can realize all or part of function in above-mentioned embodiment.
Use above specific case is illustrated to the present invention, is only intended to help and is understood the present invention, not limiting
The system present invention.For those skilled in the art, according to the thought of the present invention, can also make some simple
Deduce, deform or replace.
Claims (4)
- A kind of 1. vehicle-mounted deep learning model update method of new energy unmanned vehicle, it is characterised in that the applicable new energy of this method The charging gun access port of unmanned vehicle includes：Power injection interface and the first data-interface, correspondingly, charging gun are provided with corresponding Electric energy output interface and the second data-interface, this method include：Charging gun Connection Step, the charging gun access port are connected with the charging gun of charging pile, and new energy unmanned vehicle passes through institute State power injection interface and electric energy output interface is obtained while charging, also pass through first data-interface and export vehicle-mounted sensing Road information that device gathers, being stored in vehicle-mounted hard disks；Vehicle-mounted data uploading step, charging pile obtain the road of the first data-interface output by second data-interface The road information of acquisition is uploaded to unmanned vehicle cloud platform by information, charging pile by optical fiber；Model generation step, unmanned vehicle cloud platform regenerate deep learning model according to the road information received；The deep learning model data of generation is transmitted through the fiber to charging pile, filled by model download step, unmanned vehicle cloud platform Electric stake is again transmitted the deep learning model data regenerated to vehicle-mounted hard disks by charging gun, so as to update vehicle-mounted depth Practise model.
- 2. the method as described in claim 1, it is characterised in that the model download step also includes：The deep learning model data regenerated can be also downloaded to vehicle-mounted hard by unmanned vehicle cloud platform by cordless communication network Disk, so as to update vehicle-mounted deep learning model.
- 3. the method as described in claim 1, it is characterised in that first data-interface also exports new energy unmanned vehicle numbering Information.
- 4. method as claimed in claim 3, it is characterised in that the road information uploading step includes：Charging pile obtains the road information of new energy unmanned vehicle number information and the collection of new energy unmanned vehicle sensor；The new energy unmanned vehicle number information of acquisition is uploaded to unmanned vehicle cloud platform by charging pile by optical fiber；Unmanned vehicle cloud platform generates log-on message or inquiry log-on message according to the new energy unmanned vehicle number information, and to Charging pile feeds back registered information；After charging pile receives registered information, the road information of acquisition is uploaded to unmanned vehicle cloud platform by optical fiber；Unmanned vehicle cloud platform stores the road information according to the log-on message.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710629271.7A CN107451611A (en) | 2017-07-28 | 2017-07-28 | A kind of vehicle-mounted deep learning model update method of new energy unmanned vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710629271.7A CN107451611A (en) | 2017-07-28 | 2017-07-28 | A kind of vehicle-mounted deep learning model update method of new energy unmanned vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107451611A true CN107451611A (en) | 2017-12-08 |
Family
ID=60489484
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710629271.7A Withdrawn CN107451611A (en) | 2017-07-28 | 2017-07-28 | A kind of vehicle-mounted deep learning model update method of new energy unmanned vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107451611A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109141459A (en) * | 2018-09-28 | 2019-01-04 | 吉林大学 | A kind of electric car navigation system and method with Analysis of Electricity prediction |
| US10390003B1 (en) | 2016-08-29 | 2019-08-20 | Perceptln Shenzhen Limited | Visual-inertial positional awareness for autonomous and non-autonomous device |
| US10437252B1 (en) | 2017-09-08 | 2019-10-08 | Perceptln Shenzhen Limited | High-precision multi-layer visual and semantic map for autonomous driving |
| US10794710B1 (en) | 2017-09-08 | 2020-10-06 | Perceptin Shenzhen Limited | High-precision multi-layer visual and semantic map by autonomous units |
| CN112147440A (en) * | 2020-09-18 | 2020-12-29 | 吉递(中国)能源科技有限公司 | Abnormal sensing and autonomous alarm system and method for intelligent charging socket |
| US11328158B2 (en) | 2016-08-29 | 2022-05-10 | Trifo, Inc. | Visual-inertial positional awareness for autonomous and non-autonomous tracking |
| US11774983B1 (en) | 2019-01-02 | 2023-10-03 | Trifo, Inc. | Autonomous platform guidance systems with unknown environment mapping |
| US11842500B2 (en) | 2016-08-29 | 2023-12-12 | Trifo, Inc. | Fault-tolerance to provide robust tracking for autonomous and non-autonomous positional awareness |
| US11953910B2 (en) | 2016-08-29 | 2024-04-09 | Trifo, Inc. | Autonomous platform guidance systems with task planning and obstacle avoidance |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102714426A (en) * | 2009-12-21 | 2012-10-03 | 松下电器产业株式会社 | Electricity feeding device and electricity feeding system using the same |
| CN103325014A (en) * | 2013-06-24 | 2013-09-25 | 广西十方科技有限公司 | Charging pile cluster management system for detecting power grid loading in real time |
| CN104300646A (en) * | 2014-10-31 | 2015-01-21 | 国家电网公司 | Multi-frequency-band intelligent charging pile system supporting car networking |
| CN104778850A (en) * | 2014-01-06 | 2015-07-15 | 集奥数字国际有限公司 | Determining portions of a roadway model requiring updating |
| CN205230360U (en) * | 2015-10-30 | 2016-05-11 | 乐卡汽车智能科技（北京）有限公司 | Stake and intelligent transportation system charge |
| CN105575119A (en) * | 2015-12-29 | 2016-05-11 | 大连楼兰科技股份有限公司 | Road condition climate deep learning and recognition method and apparatus |
| CN105973245A (en) * | 2016-04-28 | 2016-09-28 | 百度在线网络技术（北京）有限公司 | Method and device for updating online map by using unmanned vehicle |
| CN205789202U (en) * | 2016-07-18 | 2016-12-07 | 新疆胡杨线缆制造有限公司 | A kind of charging pile special-purpose multifunctional cable |
-
2017
- 2017-07-28 CN CN201710629271.7A patent/CN107451611A/en not_active Withdrawn
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102714426A (en) * | 2009-12-21 | 2012-10-03 | 松下电器产业株式会社 | Electricity feeding device and electricity feeding system using the same |
| CN103325014A (en) * | 2013-06-24 | 2013-09-25 | 广西十方科技有限公司 | Charging pile cluster management system for detecting power grid loading in real time |
| CN104778850A (en) * | 2014-01-06 | 2015-07-15 | 集奥数字国际有限公司 | Determining portions of a roadway model requiring updating |
| CN104300646A (en) * | 2014-10-31 | 2015-01-21 | 国家电网公司 | Multi-frequency-band intelligent charging pile system supporting car networking |
| CN205230360U (en) * | 2015-10-30 | 2016-05-11 | 乐卡汽车智能科技（北京）有限公司 | Stake and intelligent transportation system charge |
| CN105575119A (en) * | 2015-12-29 | 2016-05-11 | 大连楼兰科技股份有限公司 | Road condition climate deep learning and recognition method and apparatus |
| CN105973245A (en) * | 2016-04-28 | 2016-09-28 | 百度在线网络技术（北京）有限公司 | Method and device for updating online map by using unmanned vehicle |
| CN205789202U (en) * | 2016-07-18 | 2016-12-07 | 新疆胡杨线缆制造有限公司 | A kind of charging pile special-purpose multifunctional cable |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10390003B1 (en) | 2016-08-29 | 2019-08-20 | Perceptln Shenzhen Limited | Visual-inertial positional awareness for autonomous and non-autonomous device |
| US11328158B2 (en) | 2016-08-29 | 2022-05-10 | Trifo, Inc. | Visual-inertial positional awareness for autonomous and non-autonomous tracking |
| US11842500B2 (en) | 2016-08-29 | 2023-12-12 | Trifo, Inc. | Fault-tolerance to provide robust tracking for autonomous and non-autonomous positional awareness |
| US11900536B2 (en) | 2016-08-29 | 2024-02-13 | Trifo, Inc. | Visual-inertial positional awareness for autonomous and non-autonomous tracking |
| US11953910B2 (en) | 2016-08-29 | 2024-04-09 | Trifo, Inc. | Autonomous platform guidance systems with task planning and obstacle avoidance |
| US10437252B1 (en) | 2017-09-08 | 2019-10-08 | Perceptln Shenzhen Limited | High-precision multi-layer visual and semantic map for autonomous driving |
| US10794710B1 (en) | 2017-09-08 | 2020-10-06 | Perceptin Shenzhen Limited | High-precision multi-layer visual and semantic map by autonomous units |
| CN109141459A (en) * | 2018-09-28 | 2019-01-04 | 吉林大学 | A kind of electric car navigation system and method with Analysis of Electricity prediction |
| US11774983B1 (en) | 2019-01-02 | 2023-10-03 | Trifo, Inc. | Autonomous platform guidance systems with unknown environment mapping |
| CN112147440A (en) * | 2020-09-18 | 2020-12-29 | 吉递(中国)能源科技有限公司 | Abnormal sensing and autonomous alarm system and method for intelligent charging socket |
| CN112147440B (en) * | 2020-09-18 | 2023-02-28 | 吉递(中国)能源科技有限公司 | Abnormal sensing and autonomous alarm system and method for intelligent charging socket |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107451611A (en) | A kind of vehicle-mounted deep learning model update method of new energy unmanned vehicle | |
| CN107241441A (en) | A kind of new energy unmanned vehicle vehicular map update method and system | |
| US20210291847A1 (en) | Performing actions associated with a connected vehicle | |
| US11091045B2 (en) | Information processing apparatus, motor-driven movable body, and discharge control method | |
| CN102314630B (en) | Movable law-enforcement electronic evidence management system | |
| CN105101478B (en) | A kind of charging method and device of wireless network sensor | |
| DE102019107051A1 (en) | CONTENTS DELIVERY TO VEHICLE VIA CHARGING STATION | |
| CN105702068A (en) | Mobile terminal-based advanced driving assistance system | |
| US11046186B1 (en) | Electric vehicle supply equipment (EVSE) having internal current overage protection, and associated charging methods for multi-type electric vehicles and non-electric vehicle | |
| CN106314178B (en) | A kind of battery, battery altering station and battery change method | |
| CN105515105B (en) | Information of charging pile monitoring method and system | |
| CN109004972A (en) | Data transmission method, device, system and the surface map transmission module of UAV system | |
| DE102014006960A1 (en) | Self-propelled power supply unit; Energy-Servant | |
| CN107196771A (en) | Vehicle netbios synchronization dormancy method, system and gateway controller | |
| CN107861836A (en) | Drive recorder data back up method and device | |
| CN104779682A (en) | Wireless charge system of electromobile | |
| CN108827334A (en) | A kind of automatic Pilot method | |
| CN106067889B (en) | Electronic device and its method for uploading | |
| CN204030688U (en) | A kind of vehicle mounted battery management system | |
| CN114189835B (en) | Intelligent driving big data transmission and exchange method and system for electric automobile | |
| CN106896330B (en) | A kind of data processing method and device about battery dump energy | |
| US20160127146A1 (en) | Communicating During Data Extraction Operations | |
| CN106034182A (en) | Method, device and terminal for controlling electric quantity loss | |
| CN103905096A (en) | Device and method for setting geomagnetic sensor | |
| CN106004493A (en) | Charging control method and system for electric vehicle |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20171208 |
|
| WW01 | Invention patent application withdrawn after publication |