CN114043997A - Automatic driving intelligent decision-making method based on high-sensitivity sensor - Google Patents
Automatic driving intelligent decision-making method based on high-sensitivity sensor Download PDFInfo
- Publication number
- CN114043997A CN114043997A CN202210034202.2A CN202210034202A CN114043997A CN 114043997 A CN114043997 A CN 114043997A CN 202210034202 A CN202210034202 A CN 202210034202A CN 114043997 A CN114043997 A CN 114043997A
- Authority
- CN
- China
- Prior art keywords
- processing unit
- execution
- signal
- comparison
- acquiring
- 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.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
- B60W50/029—Adapting to failures or work around with other constraints, e.g. circumvention by avoiding use of failed parts
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/0098—Details of control systems ensuring comfort, safety or stability not otherwise provided for
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention discloses an automatic driving intelligent decision-making method based on a high-sensitivity sensor, belongs to the field of automatic driving, relates to an intelligent decision-making technology, and is used for solving the problem that an existing decision-making processor is often arranged in a vehicle, and huge loss is easily caused when the processor is in a fault crash.
Description
Technical Field
The invention belongs to the field of automatic driving, relates to an intelligent decision-making technology, and particularly relates to an automatic driving intelligent decision-making method based on a high-sensitivity sensor.
Background
In automatic driving, the complex decision problem is usually solved by the existing knowledge and an artificial intelligence method by a computer, but one processor for generating the decision is usually arranged in a vehicle, and when the processor crashes due to a fault, huge loss is usually caused, but two processors are arranged to supplement each other and also two processors are crashed due to the same data, so that the safety of automatic driving is ensured by arranging three processors to supplement each other, wherein one processor is different from other processor frameworks and processing methods.
Disclosure of Invention
The invention aims to provide an automatic driving intelligent decision-making method based on a high-sensitivity sensor, which is used for solving the problem that one processor for generating decisions is often arranged in a vehicle, and when the processor crashes due to faults, huge losses are often caused.
The purpose of the invention can be realized by the following technical scheme:
an automatic driving intelligent decision-making method based on a high-sensitivity sensor comprises the following steps:
acquiring running data of an automobile during automatic driving;
the direct connection processing unit generates a decision based on the operation data, and the decision is decomposed into different execution signals by different actuators in the automobile;
synchronizing the operation data acquired by the directly-connected processing unit into a second processing unit and a third processing unit, wherein the processing frames and the processing methods of the second processing unit and the directly-connected processing unit are the same, and the processing frames and the processing methods of the third processing unit and the directly-connected processing unit are different;
when the direct connection processing unit reports an error, recording an error reporting time node, and acquiring an execution signal correspondingly generated by the second processing unit and the third processing unit under the corresponding time node;
if the second processing unit reports an error or a fault under the corresponding time node and does not generate an execution signal, outputting the execution signal correspondingly generated by the third processing unit for execution;
if the second processing unit and the third processing unit generate execution signals under the corresponding time node, performing reliability comparison on the execution signals generated by the second processing unit and the execution signals generated by the third processing unit, and if the comparison result meets a comparison threshold value, outputting the execution signals generated by the second processing unit for execution;
if the comparison result does not meet the comparison threshold, acquiring the actual values of the second processing unit and the third processing unit within the preset processing times;
comparing the actual values of the second processing unit and the third processing unit, selecting the selected unit with the maximum value higher than the actual threshold value, and outputting and executing the execution signal of the selected unit;
and if the reliability values of the second processing unit and the third processing unit are both smaller than the actual threshold value, selecting execution signals generated by the second processing unit and the third processing unit, outputting and executing the execution signals, and simultaneously finishing the automatic driving.
Further, the decision is decomposed into different execution signals by different actuators in the automobile, and the different execution signals comprise:
obtaining parameters of an automobile, and constructing a simulation model through a convolutional neural network;
inputting a plurality of decisions into the simulation model, and recording the execution action of an actuator of the automobile;
and corresponding the decision, the actuator and the execution action one by one to obtain an execution signal.
Further, the performing the confidence level comparison includes:
comparing the number of execution signals of the second processing unit and the third processing unit;
if the number of the execution signals generated by the second processing unit is the same as that of the execution signals generated by the third processing unit, performing weight comparison;
if the weight comparison meets the comparison threshold, the comparison result meets the comparison threshold, otherwise, the comparison result does not meet the comparison threshold;
and if the quantity of the execution signals generated by the second processing unit is different from the quantity of the execution signals generated by the third processing unit, acquiring a difference value between the quantity of the execution signals generated by the second processing unit and the quantity of the execution signals generated by the third processing unit, wherein when the difference value is greater than a comparison threshold value, the comparison result does not meet the comparison threshold value, and otherwise, the comparison result meets the comparison threshold value.
Further, the performing the weight comparison includes:
classifying the types of actuators in the simulation model, wherein the type classification comprises a first type of actuator and a second type of actuator;
the first type of actuator is used for controlling the automobile to run and comprises a throttle wire, an oil injection electromagnetic valve, a brake hydraulic pump and a power-assisted steering pump;
the second type of actuator is an actuator for assisting the automobile to run and comprises an air conditioner controller and a temperature controller;
acquiring execution signals generated by the second processing unit corresponding to the first type of actuator, marking the execution signals as second signals, acquiring the number of the second signals, and marking the number as second number;
acquiring execution signals generated by the third processing unit corresponding to the first type of actuator, marking the execution signals as third signals, acquiring the number of the third signals, and marking the number as third number;
if the difference between the second quantity and the third quantity meets the comparison threshold, the comparison result meets the comparison threshold, otherwise, the comparison result does not meet the comparison threshold.
Further, the obtaining of the actual values of the second processing unit and the third processing unit within the preset processing times includes:
acquiring an execution signal generated by the direct connection processing unit based on the operation data within a preset time period, marking the execution signal as a standard signal, and marking the generation time of the standard signal as an audit node;
acquiring an execution signal generated by a second processing unit in a preset time period, and marking the execution signal corresponding to the auditing node as a second verification signal;
acquiring an execution signal generated by a third processing unit in a preset time period, and marking the execution signal corresponding to the auditing node as a third verification signal;
and respectively comparing the fitting degrees of the second checking signal and the third checking signal with the standard signal, and multiplying the fitting degrees by the number of the execution signals in the standard signal to obtain a reliable value.
Further, the selecting the execution signals generated by the second processing unit and the third processing unit and outputting the execution signals to execute includes:
acquiring a second signal generated by a second processing unit and a third signal generated by a third processing unit under a corresponding time node;
and extracting the execution signal which is the same as the execution signal of the executor in the second important signal and the third important signal and has the same execution action, and outputting and executing the execution signal.
Furthermore, the automobile driving system further comprises a plurality of sensors, and the sensors are used for acquiring the running data of the automobile during automatic driving.
Compared with the prior art, the invention has the beneficial effects that:
by arranging the second processing unit and the third processing unit, the situation that no processing unit performs decision analysis after a direct connection processing unit generating a decision crashes to cause unmanned driving failure can be avoided, and meanwhile, the processing frames and the processing methods of the second processing unit and the third processing unit are different from each other, so that the situation that the direct processing unit cannot run due to the fact that the second processing unit is duplicated incorrectly under the same processing frame and the same processing method is avoided, and further the safety of automatic driving is guaranteed.
Drawings
Fig. 1 is a schematic block diagram of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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.
Examples
Conventionally, a processor for generating a decision is often arranged in a vehicle, and when the processor is crashed due to a fault, huge loss is often caused.
In view of the above technical problems, the present application provides an automatic driving intelligent decision method based on a high-sensitivity sensor, which includes:
the method comprises the steps of obtaining operation data of an automobile during automatic driving, specifically, collecting the operation data through a plurality of sensors arranged on the automobile, and more specifically, adopting high-sensitivity sensors as the sensors.
The direct connection processing unit generates a decision based on the operation data, and the decision is decomposed into different execution signals by different actuators in the automobile;
synchronizing the operation data acquired by the directly-connected processing unit into a second processing unit and a third processing unit, wherein the processing frames and the processing methods of the second processing unit and the directly-connected processing unit are the same, and the processing frames and the processing methods of the third processing unit and the directly-connected processing unit are different;
when the direct connection processing unit reports an error, recording an error reporting time node, and acquiring an execution signal correspondingly generated by the second processing unit and the third processing unit under the corresponding time node;
if the second processing unit reports an error or a fault under the corresponding time node and does not generate an execution signal, outputting the execution signal correspondingly generated by the third processing unit for execution;
if the second processing unit and the third processing unit generate execution signals under the corresponding time node, performing reliability comparison on the execution signals generated by the second processing unit and the execution signals generated by the third processing unit, and if the comparison result meets a comparison threshold value, outputting the execution signals generated by the second processing unit for execution;
if the comparison result does not meet the comparison threshold, acquiring the actual values of the second processing unit and the third processing unit within the preset processing times;
comparing the actual values of the second processing unit and the third processing unit, selecting the selected unit with the maximum value higher than the actual threshold value, and outputting and executing the execution signal of the selected unit;
and if the reliability values of the second processing unit and the third processing unit are both smaller than the actual threshold value, selecting execution signals generated by the second processing unit and the third processing unit, outputting and executing the execution signals, and simultaneously finishing the automatic driving.
By arranging the second processing unit and the third processing unit, the situation that no processing unit performs decision analysis after a direct connection processing unit generating a decision crashes and unmanned driving fails is avoided, and meanwhile, the processing frames and the processing methods of the second processing unit and the third processing unit are different, so that the situation that the direct connection processing unit cannot run due to the fact that the second processing unit under the same processing frame and the same processing method is duplicated incorrectly is avoided, and the safety of automatic driving is further guaranteed.
The above process is described in detail with reference to specific examples.
In specific implementation, parameters of an automobile are obtained, a simulation model is constructed through a convolutional neural network (refer to published patents CN110837697A and CN 113655732A), more specifically, the parameters of the automobile include all hardware information and connection information of the automobile, a plurality of decisions are input into the simulation model, and execution actions of an actuator of the automobile are recorded, wherein the decisions are obtained through a direct connection processing unit, more specifically, the direct connection processing unit obtains the decisions through a simulation environment, and the decisions, the actuator and the execution actions are in one-to-one correspondence to obtain execution signals, and specifically, each execution signal corresponds to one actuator and one execution action.
All execution signals are stored in an automobile ECU, and when an automobile runs, corresponding execution signals can be found in the ECU only by directly connecting a processing unit to generate a decision;
in specific implementation, the second processing unit and the third processing unit are added, the processing frames and the processing methods of the second processing unit and the direct connection processing unit are the same, and the processing frames and the processing methods of the third processing unit and the direct connection processing unit are different, so that when the direct connection processing unit is halted, the second processing unit and the third processing unit can both generate decisions to enable automatic driving to continue, meanwhile, the second processing unit adopts the frames and the processing methods which are the same as those of the direct connection processing unit, so that the direct connection processing unit and the second processing unit can acquire the same operation data to generate the same operation result, after the direct connection processing unit is halted, if the second processing unit acquires the same operation data without halting, the same execution signals as those of the direct connection processing unit can be generated, and the driving safety is ensured, meanwhile, the processing frames and the processing methods of the third processing unit and the direct connection processing unit are different, so that the third processing unit with different structures is used for processing and generating execution signals after the second processing unit is halted when the second processing unit obtains the same operation data, and the driving safety is ensured.
More specifically, the present invention is to provide a novel,
when the direct connection processing unit reports an error, recording an error reporting time node, and acquiring an execution signal correspondingly generated by the second processing unit and the third processing unit under the corresponding time node;
if the second processing unit reports an error or a fault under the corresponding time node and does not generate an execution signal, outputting the execution signal correspondingly generated by the third processing unit for execution;
if the second processing unit and the third processing unit generate execution signals under the corresponding time node, performing reliability comparison on the execution signals generated by the second processing unit and the execution signals generated by the third processing unit, and if the comparison result meets a comparison threshold value, outputting the execution signals generated by the second processing unit for execution;
wherein the confidence level comparison comprises:
comparing the number of execution signals of the second processing unit and the third processing unit;
if the number of the execution signals generated by the second processing unit is the same as that of the execution signals generated by the third processing unit, performing weight comparison;
if the weight comparison meets the comparison threshold, the comparison result meets the comparison threshold, otherwise, the comparison result does not meet the comparison threshold;
if the number of the execution signals generated by the second processing unit is different from the number of the execution signals generated by the third processing unit, acquiring a difference value between the number of the execution signals generated by the second processing unit and the number of the execution signals generated by the third processing unit, wherein when the difference value is greater than a comparison threshold value, the comparison result does not meet the comparison threshold value, otherwise, the comparison result meets the comparison threshold value;
performing the weight comparison includes:
classifying the types of actuators in the simulation model, wherein the type classification comprises a first type of actuator and a second type of actuator;
the first type of actuator is used for controlling the automobile to run and comprises a throttle wire, an oil injection electromagnetic valve, a brake hydraulic pump and a power-assisted steering pump;
the second type of actuator is an actuator for assisting the automobile to run and comprises an air conditioner controller and a temperature controller;
acquiring execution signals generated by the second processing unit corresponding to the first type of actuator, marking the execution signals as second signals, acquiring the number of the second signals, and marking the number as second number;
acquiring execution signals generated by the third processing unit corresponding to the first type of actuator, marking the execution signals as third signals, acquiring the number of the third signals, and marking the number as third number;
if the difference between the second quantity and the third quantity meets the comparison threshold, the comparison result meets the comparison threshold, otherwise, the comparison result does not meet the comparison threshold.
If the comparison result does not meet the comparison threshold, acquiring the actual values of the second processing unit and the third processing unit within the preset processing times;
comparing the actual values of the second processing unit and the third processing unit, selecting the selected unit with the maximum value higher than the actual threshold value, and outputting and executing the execution signal of the selected unit;
specifically, obtaining the actual values of the second processing unit and the third processing unit within the preset processing times includes:
acquiring an execution signal generated by the direct connection processing unit based on the operation data within a preset time period, marking the execution signal as a standard signal, and marking the generation time of the standard signal as an audit node;
acquiring an execution signal generated by a second processing unit in a preset time period, and marking the execution signal corresponding to the auditing node as a second verification signal;
acquiring an execution signal generated by a third processing unit in a preset time period, and marking the execution signal corresponding to the auditing node as a third verification signal;
and respectively comparing the fitting degrees of the second checking signal and the third checking signal with the standard signal, and multiplying the fitting degrees by the number of the execution signals in the standard signal to obtain a reliable value.
Wherein the degree of fitting is represented by the formula
Wherein, K isDTo a degree of fitting, AI1For the number of signals to be performed in the second or third check signal, AI2For the number of signals performed within the standard signal, 0.1 is the conversion factor.
And if the reliability values of the second processing unit and the third processing unit are both smaller than the actual threshold value, selecting execution signals generated by the second processing unit and the third processing unit, outputting and executing the execution signals, and simultaneously finishing the automatic driving.
Specifically, a second signal generated by a second processing unit and a third signal generated by a third processing unit under a corresponding time node are obtained;
and extracting the execution signal which is the same as the execution signal of the executor in the second important signal and the third important signal and has the same execution action, and outputting and executing the execution signal.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the technical principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (7)
1. An automatic driving intelligent decision-making method based on a high-sensitivity sensor is characterized by comprising the following steps:
acquiring running data of an automobile during automatic driving;
the direct connection processing unit generates a decision based on the operation data, and the decision is decomposed into different execution signals by different actuators in the automobile;
synchronizing the operation data acquired by the directly-connected processing unit into a second processing unit and a third processing unit, wherein the processing frames and the processing methods of the second processing unit and the directly-connected processing unit are the same, and the processing frames and the processing methods of the third processing unit and the directly-connected processing unit are different;
when the direct connection processing unit reports an error, recording an error reporting time node, and acquiring an execution signal correspondingly generated by the second processing unit and the third processing unit under the corresponding time node;
if the second processing unit reports an error or a fault under the corresponding time node and does not generate an execution signal, outputting the execution signal correspondingly generated by the third processing unit for execution;
if the second processing unit and the third processing unit generate execution signals under the corresponding time node, performing reliability comparison on the execution signals generated by the second processing unit and the execution signals generated by the third processing unit, and if the comparison result meets a comparison threshold value, outputting the execution signals generated by the second processing unit for execution;
if the comparison result does not meet the comparison threshold, acquiring the actual values of the second processing unit and the third processing unit within the preset processing times;
comparing the actual values of the second processing unit and the third processing unit, selecting the selected unit with the maximum value higher than the actual threshold value, and outputting and executing the execution signal of the selected unit;
and if the reliability values of the second processing unit and the third processing unit are both smaller than the actual threshold value, selecting execution signals generated by the second processing unit and the third processing unit, outputting and executing the execution signals, and simultaneously finishing the automatic driving.
2. The method of claim 1, wherein the decision is decomposed into different execution signals by different actuators in the vehicle, and the method comprises:
obtaining parameters of an automobile, and constructing a simulation model through a convolutional neural network;
inputting a plurality of decisions into the simulation model, and recording the execution action of an actuator of the automobile;
and corresponding the decision, the actuator and the execution action one by one to obtain an execution signal.
3. The method of claim 2, wherein the performing a confidence comparison comprises:
comparing the number of execution signals of the second processing unit and the third processing unit;
if the number of the execution signals generated by the second processing unit is the same as that of the execution signals generated by the third processing unit, performing weight comparison;
if the weight comparison meets the comparison threshold, the comparison result meets the comparison threshold, otherwise, the comparison result does not meet the comparison threshold;
and if the quantity of the execution signals generated by the second processing unit is different from the quantity of the execution signals generated by the third processing unit, acquiring a difference value between the quantity of the execution signals generated by the second processing unit and the quantity of the execution signals generated by the third processing unit, wherein when the difference value is greater than a comparison threshold value, the comparison result does not meet the comparison threshold value, and otherwise, the comparison result meets the comparison threshold value.
4. The method according to claim 3, wherein the performing the weight comparison comprises:
classifying the types of actuators in the simulation model, wherein the type classification comprises a first type of actuator and a second type of actuator;
the first type of actuator is used for controlling the automobile to run and comprises a throttle wire, an oil injection electromagnetic valve, a brake hydraulic pump and a power-assisted steering pump;
the second type of actuator is an actuator for assisting the automobile to run and comprises an air conditioner controller and a temperature controller;
acquiring execution signals generated by the second processing unit corresponding to the first type of actuator, marking the execution signals as second signals, acquiring the number of the second signals, and marking the number as second number;
acquiring execution signals generated by the third processing unit corresponding to the first type of actuator, marking the execution signals as third signals, acquiring the number of the third signals, and marking the number as third number;
if the difference between the second quantity and the third quantity meets the comparison threshold, the comparison result meets the comparison threshold, otherwise, the comparison result does not meet the comparison threshold.
5. The method according to claim 4, wherein the obtaining of the actual values of the second processing unit and the third processing unit within the preset processing times comprises:
acquiring an execution signal generated by the direct connection processing unit based on the operation data within a preset time period, marking the execution signal as a standard signal, and marking the generation time of the standard signal as an audit node;
acquiring an execution signal generated by a second processing unit in a preset time period, and marking the execution signal corresponding to the auditing node as a second verification signal;
acquiring an execution signal generated by a third processing unit in a preset time period, and marking the execution signal corresponding to the auditing node as a third verification signal;
and respectively comparing the fitting degrees of the second checking signal and the third checking signal with the standard signal, and multiplying the fitting degrees by the number of the execution signals in the standard signal to obtain a reliable value.
6. The method for intelligent decision making for automatic driving based on high-sensitivity sensor according to claim 5, wherein the selecting the execution signals generated by the second processing unit and the third processing unit and outputting the execution signals comprises:
acquiring a second signal generated by a second processing unit and a third signal generated by a third processing unit under a corresponding time node;
and extracting the execution signal which is the same as the execution signal of the executor in the second important signal and the third important signal and has the same execution action, and outputting and executing the execution signal.
7. The automatic driving intelligent decision making method based on the high-sensitivity sensor is characterized by further comprising a plurality of sensors, wherein the sensors are used for acquiring running data of an automobile during automatic driving.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210034202.2A CN114043997B (en) | 2022-01-13 | 2022-01-13 | Automatic driving intelligent decision-making method based on high-sensitivity sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210034202.2A CN114043997B (en) | 2022-01-13 | 2022-01-13 | Automatic driving intelligent decision-making method based on high-sensitivity sensor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114043997A true CN114043997A (en) | 2022-02-15 |
| CN114043997B CN114043997B (en) | 2022-04-12 |
Family
ID=80196394
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210034202.2A Active CN114043997B (en) | 2022-01-13 | 2022-01-13 | Automatic driving intelligent decision-making method based on high-sensitivity sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114043997B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103399546A (en) * | 2013-07-26 | 2013-11-20 | 杭州和利时自动化有限公司 | Method and system for controlling triple redundancy |
| US20140277608A1 (en) * | 2013-03-14 | 2014-09-18 | GM Global Technology Operations LLC | Fault Tolerant Control System |
| CN104417394A (en) * | 2013-09-11 | 2015-03-18 | 通用汽车环球科技运作有限责任公司 | Controller for an electric motor, and a method thereof |
| CN108196547A (en) * | 2018-01-08 | 2018-06-22 | 北京图森未来科技有限公司 | A kind of automated driving system |
| CN109634097A (en) * | 2018-12-12 | 2019-04-16 | 上海航天控制技术研究所 | A kind of triple redundance interface circuit and synchronous method |
| US20190250611A1 (en) * | 2018-02-13 | 2019-08-15 | Nvidia Corporation | Sharing sensor data between multiple controllers to support vehicle operations |
| CN110192185A (en) * | 2017-01-23 | 2019-08-30 | Zf 腓德烈斯哈芬股份公司 | The processor architecture of redundancy |
| CN110682920A (en) * | 2019-12-09 | 2020-01-14 | 吉利汽车研究院（宁波）有限公司 | Automatic driving control system, control method and equipment |
| US20200164892A1 (en) * | 2018-11-22 | 2020-05-28 | Robert Bosch Gmbh | Operating Method for a Redundant Sensor Arrangement of a Vehicle System, and Corresponding Redundant Sensor Arrangement |
| CN112638739A (en) * | 2020-05-20 | 2021-04-09 | 华为技术有限公司 | Redundant electronic control system and equipment |
-
2022
- 2022-01-13 CN CN202210034202.2A patent/CN114043997B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140277608A1 (en) * | 2013-03-14 | 2014-09-18 | GM Global Technology Operations LLC | Fault Tolerant Control System |
| CN103399546A (en) * | 2013-07-26 | 2013-11-20 | 杭州和利时自动化有限公司 | Method and system for controlling triple redundancy |
| CN104417394A (en) * | 2013-09-11 | 2015-03-18 | 通用汽车环球科技运作有限责任公司 | Controller for an electric motor, and a method thereof |
| CN110192185A (en) * | 2017-01-23 | 2019-08-30 | Zf 腓德烈斯哈芬股份公司 | The processor architecture of redundancy |
| CN108196547A (en) * | 2018-01-08 | 2018-06-22 | 北京图森未来科技有限公司 | A kind of automated driving system |
| US20190250611A1 (en) * | 2018-02-13 | 2019-08-15 | Nvidia Corporation | Sharing sensor data between multiple controllers to support vehicle operations |
| US20200164892A1 (en) * | 2018-11-22 | 2020-05-28 | Robert Bosch Gmbh | Operating Method for a Redundant Sensor Arrangement of a Vehicle System, and Corresponding Redundant Sensor Arrangement |
| CN109634097A (en) * | 2018-12-12 | 2019-04-16 | 上海航天控制技术研究所 | A kind of triple redundance interface circuit and synchronous method |
| CN110682920A (en) * | 2019-12-09 | 2020-01-14 | 吉利汽车研究院（宁波）有限公司 | Automatic driving control system, control method and equipment |
| CN112638739A (en) * | 2020-05-20 | 2021-04-09 | 华为技术有限公司 | Redundant electronic control system and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114043997B (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110262463B (en) | Rail transit platform door fault diagnosis system based on deep learning | |
| CN110231156B (en) | Service robot motion system fault diagnosis method and device based on time sequence characteristics | |
| CN111294341B (en) | Vehicle-mounted system intrusion detection method based on self-encoder and recurrent neural network | |
| CN109308522B (en) | GIS fault prediction method based on recurrent neural network | |
| Fan et al. | A hybrid FDD strategy for local system of AHU based on artificial neural network and wavelet analysis | |
| CN101980225B (en) | Method for implementing testability analysis and diagnosis decision system for electronic products | |
| CN109902564B (en) | Abnormal event detection method based on structural similarity sparse self-coding network | |
| CN108108622A (en) | Leakage location based on depth convolutional network and controlling stream graph | |
| CN114239377A (en) | Method and system for evaluating health state of urban rail electromechanical equipment and storage medium | |
| CN112101431A (en) | Electronic equipment fault diagnosis system | |
| CN113188807B (en) | Automatic abs result judging algorithm | |
| WO2021027052A1 (en) | Interlayer parsing-based input instance verfication method for neural network model | |
| CN104986347A (en) | Real-time detection method for civil aircraft airline pilot operation errors | |
| CN114856811B (en) | Diesel engine air system health assessment method | |
| CN112861071B (en) | High-speed rail traction system anomaly detection method based on depth self-coding | |
| CN112947385B (en) | Aircraft fault diagnosis method and system based on improved Transformer model | |
| CN112985830A (en) | Abs result automatic judging algorithm | |
| CN116520806A (en) | Intelligent fault diagnosis system and method for industrial system | |
| CN114043997B (en) | Automatic driving intelligent decision-making method based on high-sensitivity sensor | |
| CN110727669B (en) | Electric power system sensor data cleaning device and cleaning method | |
| KR101926257B1 (en) | Fault Signal Recovery System and Method | |
| CN117877256A (en) | Vehicle fault prediction method and system based on digital twin | |
| CN105445581A (en) | Fault detection system based on Modelica model and method | |
| CN116560341A (en) | Industrial robot fault diagnosis model and fault diagnosis method | |
| CN108548669B (en) | Fault diagnosis method and system for transmission system of engineering equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |