CN116985803B - Self-adaptive speed control system and method for electric scooter - Google Patents
Self-adaptive speed control system and method for electric scooter Download PDFInfo
- Publication number
- CN116985803B CN116985803B CN202311243409.1A CN202311243409A CN116985803B CN 116985803 B CN116985803 B CN 116985803B CN 202311243409 A CN202311243409 A CN 202311243409A CN 116985803 B CN116985803 B CN 116985803B
- Authority
- CN
- China
- Prior art keywords
- data
- obstacle
- road condition
- model
- module
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000004927 fusion Effects 0.000 claims abstract description 49
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 238000001514 detection method Methods 0.000 claims description 32
- 239000011159 matrix material Substances 0.000 claims description 25
- 230000033001 locomotion Effects 0.000 claims description 20
- 230000008859 change Effects 0.000 claims description 14
- 230000003044 adaptive effect Effects 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000007726 management method Methods 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 10
- 230000000694 effects Effects 0.000 claims description 9
- 230000001360 synchronised effect Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 230000035945 sensitivity Effects 0.000 claims description 5
- 230000003993 interaction Effects 0.000 claims description 4
- 238000010223 real-time analysis Methods 0.000 claims description 3
- 238000007499 fusion processing Methods 0.000 claims description 2
- 230000001133 acceleration Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 10
- 230000004888 barrier function Effects 0.000 description 7
- 230000007613 environmental effect Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004836 empirical method Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000005355 Hall effect Effects 0.000 description 1
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 239000010426 asphalt Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000011449 brick Substances 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/14—Adaptive cruise control
- B60W30/143—Speed control
-
- 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
- B60W2552/00—Input parameters relating to infrastructure
-
- 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
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/40—Coefficient of friction
-
- 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
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/50—Barriers
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/72—Electric energy management in electromobility
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of automatic control, in particular to a speed self-adaptive control system and method for an electric scooter. Comprising the following steps: road condition data are collected by using a road surface sensor and an environment sensor, and the collected data are processed and analyzed to obtain current road condition information and a recommended safe speed range; based on the front image and obstacle data from the camera and the radar, detecting the front obstacle by using an object recognition algorithm to obtain obstacle information, and further predicting a moving track in a short time; integrating road condition and obstacle data by using an optimized data fusion algorithm containing dynamic weight adjustment based on road condition information and recommended safety speed range and obstacle data, and generating intelligent driving strategy advice according to the fusion data; based on the intelligent driving strategy suggestion, the motor output of the scooter is adjusted. The technical problems of insufficient real-time performance and poor accuracy in the speed self-adaptive control of the electric scooter in the prior art are solved.
Description
Technical Field
The invention relates to the technical field of automatic control, in particular to a speed self-adaptive control system and method for an electric scooter.
Background
Electric scooters have received widespread attention and are used extensively throughout the world, particularly as vehicles in the last mile of the city. Due to portability and operational simplicity, more and more users choose to use electric scooters for short distance travel. However, safety problems of electric scooters during running are also becoming a concern. Limitations of the prior art: the single speed is set, the environment perception is lacked, the manual control is mainly performed, and the driving experience is limited; thus, an adaptive speed control system is needed. In this way, the scooter may automatically adjust its speed to prevent accidents when driving in crowded or unstable environments.
There are many control methods for electric scooter, and the application number of the electric scooter control system proposed by Qian Jing et al is CN 202210696749.9, which mainly includes: the LCD controller comprises a main controller, an LCD central controller, an integrated trigger and a functional component at least comprising a driving motor, wherein the integrated trigger comprises a dial piece, a Hall sensing assembly, functional keys and a key driving circuit board; the Hall sensing assembly is connected with the master controller to form speed regulation information; the integrated control chip presets a program, the program is displayed on an LCD display screen and control information is sent to the master controller; the function keys at least comprise a start key, an adjusting key and a mode key, and the function keys are pressed to send key information to the integrated control chip through the key driving circuit board so as to control a program to form control information; the master controller receives the speed regulation information of the Hall sensing assembly and the control information of the integrated control chip and sends an execution instruction to the corresponding functional component so as to realize the control of the electric scooter; the system has the advantages of simple circuit and convenient operation, and simultaneously increases the interest.
However, the above technology has at least the following technical problems: the technical problems of insufficient real-time performance and poor accuracy in the process of performing speed self-adaptive control on the electric scooter.
Disclosure of Invention
According to the speed self-adaptive control system and method for the electric scooter, the technical problems that in the prior art, real-time performance and accuracy are poor when the speed self-adaptive control of the electric scooter is carried out are solved, and the technical effect of realizing the self-adaptive control of the speed of the electric scooter with accurate speed safety is achieved.
The application provides an electric scooter speed self-adaptive control system and method, specifically comprising the following technical scheme:
electric scooter speed self-adaptation control system includes:
the road condition sensing module, the front obstacle detection and track prediction module, the power adjustment module, the data synchronization and management module, the road condition and obstacle data fusion module and the dynamic weight adjustment module;
the output of the road condition sensing module is sent to the power adjustment module and the road condition and obstacle data fusion module; the output of the front obstacle detection and track prediction module is also sent to the power adjustment module and the road condition and obstacle data fusion module; the power adjustment module adjusts power and speed according to the road condition and obstacle data fusion module and the dynamic weight adjustment module; the dynamic weight adjustment module can dynamically adjust the weight according to the output of the road condition and obstacle data fusion module; the data of all modules are synchronized and managed by the data synchronization and management module.
Preferably, the method further comprises:
the road condition sensing module captures road surface and meteorological data through a ground sensor and an environment sensor, and recognizes the current road condition through real-time analysis of the road surface and the meteorological data; predicting the friction change of the road surface according to the meteorological data; further, providing current road condition information and a recommended safe speed range;
the front obstacle detection and track prediction module is used for capturing front images and obstacle data by using a camera and a radar, detecting and analyzing the front obstacle in real time, and predicting the moving track of the obstacle at the same time;
the power adjustment module is used for adjusting the power output of the scooter in real time according to the data of road conditions and front obstacles, so that the speed of the scooter is ensured to be always kept within a recommended safe speed range;
the data synchronization and management module ensures that the data interaction among all modules is synchronous and stable, and is also responsible for storing and managing the data from each module, thereby ensuring the real-time performance of the data;
the road condition and obstacle data fusion module synthesizes the road condition and the front obstacle data, and carries out fusion processing to obtain intelligent driving strategy advice;
The dynamic weight adjustment module dynamically adjusts the weight in the data fusion algorithm according to the real-time environment and the intelligent driving strategy suggestion, so as to ensure that the intelligent driving strategy is always optimal.
The speed self-adaptive control method of the electric scooter comprises the following steps:
s1, road condition data acquisition is carried out by using a road surface sensor and an environment sensor, and the acquired road surface data and meteorological data are processed and analyzed to obtain current road condition information and a recommended safe speed range;
s2, detecting a front obstacle by using an object recognition algorithm based on front images and obstacle data from a camera and a radar to obtain obstacle information, and further predicting a movement track in a short time;
s3, integrating road condition and obstacle data by using an optimized data fusion algorithm containing dynamic weight adjustment based on road condition information and recommended safety speed range and obstacle data, and generating intelligent driving strategy advice according to the fusion data;
s4, based on the intelligent driving strategy suggestion, adjusting the motor output of the scooter to achieve the speed and direction of the strategy suggestion.
Preferably, the step S1 specifically includes:
road condition data are acquired by using a road surface sensor and an environment sensor, and the acquired road surface data and meteorological data are processed and analyzed to obtain current road condition information and a recommended speed range.
Preferably, in the step S1, the method further includes:
in the process of processing and analyzing the acquired pavement data and the acquired meteorological data to obtain a recommended speed range, defining a mathematical calculation model: friction model, gradient influence model, meteorological factor model.
Preferably, in the step S1, the method further includes:
calculating friction and gradient effects by using the mathematical calculation model, and introducing dynamically adjusted parametersTo simulate the influence of wind resistance and obtain a recommended safe speed range.
Preferably, in the step S1, the method further includes:
the recommended safe speed range is considered to be limited by battery endurance and performance of a driving motor, and a battery endurance influence model and a motor performance influence model are constructed.
Preferably, in the step S2, the method further includes:
when detecting the front obstacle, setting a model based on the image and radar data to obtain an image model and a radar model, and fusing the two models to avoid false detection and omission of the single model.
Preferably, in the step S2, the method further includes:
when detecting the front obstacle, when the sensor data are inconsistent and noise exists, the data of the image model and the radar model can be inconsistent and deviate from the actual conditions, and the data fusion can lead to the false detection and omission of the individual small and transparent obstacles; and data optimization is performed by utilizing the concepts of matrix operation and limitation.
Preferably, in the step S2, the method further includes:
when predicting the moving track of the obstacle, taking a basic physical model of the obstacle movement and a complex physical model of the obstacle into consideration, taking errors of the basic physical model in continuous curve movement into consideration, introducing a weight factor to fuse the two models, taking the weight factor into consideration to make the model more sensitive to recent dynamic changes, and introducing a threshold matrixTo reduce the sensitivity of the prediction.
The beneficial effects are that:
the technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
1. according to the method, a mathematical calculation model is utilized, a plurality of models such as dynamic conditions, gradients and meteorological factors are combined, a relatively accurate recommended speed range can be obtained, so that safe running of the electric scooter under various conditions is guaranteed, possible influences of environmental factors on road conditions are predicted by combining meteorological data and road condition historical data, adjustment is performed in advance, and running stability of the electric scooter is guaranteed;
2. the method and the system allow the system to find the optimal balance between the camera and the radar data by using a model fusion strategy, so that false detection and missing detection caused by a single data source are reduced, and the system can dynamically adapt to different environments and barrier characteristics by calculating and adjusting various parameters (such as weight factors) in real time; based on the physical model and the data fusion strategy, the system not only can detect the position and the relative speed of the obstacle, but also can predict the future movement track of the obstacle, and provides more information for real-time decision; the concept of matrix operation and limitation is introduced to perform data optimization, so that the system has better robustness to noise and other uncertain factors;
3. The method and the device can more accurately predict the potential risk in front by fusing multidimensional data of road conditions (R), obstacles (O), environments (E) and scooter states (Z) in real time, so that safer driving suggestions are provided for users. In addition, the angle, the distance and other factors between the scooter and the obstacle are optimized, so that potential collision with the obstacle can be avoided, and the driving safety is further improved; the adoption of the dynamic weight adjustment mechanism can ensure that the system adjusts the weight matrix M according to the latest driving environment all the time, so that the intelligent driving strategy can adapt to various road condition changes in real time, and the timeliness and the accuracy of the intelligent driving strategy are ensured.
4. According to the technical scheme, the technical problems that the speed self-adaptive control of the electric scooter is not real-time enough and the accuracy is poor can be effectively solved, a relatively accurate recommended speed range can be obtained by combining a mathematical calculation model with various models such as dynamic conditions, gradients and meteorological factors, so that the safe running of the electric scooter under various conditions is ensured, the possible influence of environmental factors on road conditions is predicted by combining meteorological data and road condition historical data, and therefore adjustment is performed in advance, and the running stability of the electric scooter is ensured; the system is allowed to find the optimal balance between the camera and the radar data by utilizing a model fusion strategy, so that false detection and missing detection caused by a single data source are reduced, and the system can dynamically adapt to different environments and barrier characteristics by calculating and adjusting various parameters (such as weight factors) in real time; based on the physical model and the data fusion strategy, the system not only can detect the position and the relative speed of the obstacle, but also can predict the future movement track of the obstacle, and provides more information for real-time decision; the concept of matrix operation and limitation is introduced to perform data optimization, so that the system has better robustness to noise and other uncertain factors; through fusing the multidimensional data of road conditions (R), obstacles (O), environments (E) and scooter states (Z) in real time, the potential risks in front can be predicted more accurately, and therefore safer driving suggestions are provided for users. In addition, the angle, the distance and other factors between the scooter and the obstacle are optimized, so that potential collision with the obstacle can be avoided, and the driving safety is further improved; the adoption of the dynamic weight adjustment mechanism can ensure that the system adjusts the weight matrix M according to the latest driving environment all the time, so that the intelligent driving strategy can adapt to various road condition changes in real time, and the timeliness and the accuracy of the intelligent driving strategy are ensured.
Drawings
FIG. 1 is a block diagram of a speed adaptive control system for an electric scooter according to the present application;
FIG. 2 is a flow chart of a speed adaptive control method for an electric scooter according to the present application;
Detailed Description
According to the speed self-adaptive control system and method for the electric scooter, the technical problems that in the prior art, real-time performance and accuracy are poor when the speed self-adaptive control of the electric scooter is carried out are solved, and the overall thinking is as follows:
the speed self-adaptive control system of the electric scooter comprises a road condition sensing module, a front obstacle detection and track prediction module, a power adjustment module, a data synchronization and management module, a road condition and obstacle data fusion module and a dynamic weight adjustment module; the output of the road condition sensing module is sent to the power adjustment module and the road condition and obstacle data fusion module; the output of the front obstacle detection and track prediction module is also sent to the power adjustment module and the road condition and obstacle data fusion module; the power adjustment module adjusts power and speed according to the road condition and obstacle data fusion module and the dynamic weight adjustment module; the dynamic weight adjustment module can dynamically adjust the weight according to the output of the road condition and obstacle data fusion module; the data of all modules are synchronized and managed by the data synchronization and management module, so that the consistency and accuracy of the data are ensured; by utilizing a mathematical calculation model and combining a plurality of models such as dynamic conditions, gradients, meteorological factors and the like, a relatively accurate recommended speed range can be obtained, so that safe running of the electric scooter under various conditions is ensured, and the possible influence of environmental factors on road conditions is predicted by combining meteorological data and road condition historical data, so that adjustment is performed in advance, and running stability of the electric scooter is ensured; the system is allowed to find the optimal balance between the camera and the radar data by utilizing a model fusion strategy, so that false detection and missing detection caused by a single data source are reduced, and the system can dynamically adapt to different environments and barrier characteristics by calculating and adjusting various parameters (such as weight factors) in real time; based on the physical model and the data fusion strategy, the system not only can detect the position and the relative speed of the obstacle, but also can predict the future movement track of the obstacle, and provides more information for real-time decision; the concept of matrix operation and limitation is introduced to perform data optimization, so that the system has better robustness to noise and other uncertain factors; through fusing the multidimensional data of road conditions (R), obstacles (O), environments (E) and scooter states (Z) in real time, the potential risks in front can be predicted more accurately, and therefore safer driving suggestions are provided for users. In addition, the angle, the distance and other factors between the scooter and the obstacle are optimized, so that potential collision with the obstacle can be avoided, and the driving safety is further improved; the adoption of the dynamic weight adjustment mechanism can ensure that the system adjusts the weight matrix M according to the latest driving environment all the time, so that the intelligent driving strategy can adapt to various road condition changes in real time, and the timeliness and the accuracy of the intelligent driving strategy are ensured.
In order to better understand the above technical solutions, the following detailed description will refer to the accompanying drawings and specific embodiments.
Referring to fig. 1, the speed adaptive system of the electric scooter disclosed by the application comprises the following parts:
the road condition sensing module, the front obstacle detection and track prediction module, the power adjustment module, the data synchronization and management module, the road condition and obstacle data fusion module and the dynamic weight adjustment module;
the road condition sensing module captures road surface and meteorological data through a ground sensor and an environment sensor, and recognizes the current road condition through real-time analysis of the data; predicting the friction change of the road surface according to meteorological conditions; further, providing current road condition information and a recommended safe speed range;
the front obstacle detection and track prediction module is used for capturing front images and obstacle data by using a camera and a radar, detecting and analyzing the front obstacle in real time, and predicting the moving track of the obstacle at the same time;
the power adjustment module is used for adjusting the power output of the scooter in real time according to the road condition and the data of the front obstacle, so that the speed of the scooter is ensured to be always kept within a recommended safe speed range;
The data synchronization and management module ensures that the data interaction among all modules is synchronous and stable, and is also responsible for storing and managing the data from each module, thereby ensuring the real-time performance of the data;
the road condition and obstacle data fusion module ensures that the data interaction among all modules is synchronous and stable, and is also responsible for storing and managing the data from each module and ensuring the real-time performance of the data;
the dynamic weight adjustment module dynamically adjusts the weight in the data fusion algorithm according to the real-time environment and the intelligent driving strategy suggestion, so as to ensure that the intelligent driving strategy is always optimal;
the connection between the modules is as follows:
the output of the road condition sensing module is sent to the power adjustment module and the road condition and obstacle data fusion module;
the output of the front obstacle detection and track prediction module is also sent to the power adjustment module and the road condition and obstacle data fusion module;
the power adjustment module adjusts power and speed according to the road condition and obstacle data fusion module and the dynamic weight adjustment module;
the dynamic weight adjustment module can dynamically adjust the weight according to the output of the road condition and obstacle data fusion module;
The data of all modules are synchronized and managed by the data synchronization and management module, so that the consistency and accuracy of the data are ensured;
the modules cooperate with each other to ensure that the electric scooter can realize self-adaptive speed under various road conditions, and a safe and comfortable driving experience is provided for users.
Referring to fig. 2, the speed adaptive control method of the electric scooter disclosed by the application comprises the following steps:
s1, road condition data acquisition is carried out by using a road surface sensor and an environment sensor, and the acquired road surface data and meteorological data are processed and analyzed to obtain current road condition information and a recommended safe speed range;
s11, recommending a speed range;
firstly, acquiring pavement data and meteorological data by using sensors, wherein the pavement data comprise friction force and gradient force; the meteorological data such as humidity, temperature; the sensor data is used for acquiring friction coefficient between the scooter and the road surfaceRoad gradient->Ambient temperature->Moisture->And air pressure->The method comprises the steps of carrying out a first treatment on the surface of the There is also the battery status->And motor status->；
The acquired sensor data may have noise and data synchronization problems among sensors, and the sensor data is filtered by adopting a time sequence analysis and a moving average algorithm to reduce the noise and ensure the synchronization among the sensors;
Defining a mathematical calculation model:
friction model: friction is caused by contact between two objects and relative movement between them. The friction force is usually given by the formulaHowever, as the electric scooter may be affected by dynamic factors in movement, dynamic condition factors are introduced:
，
wherein,is the coefficient of friction, from experimental data or manufacturer, < ->Is the friction coefficient between the scooter tyre and the ground affected by humidity and temperature; />Is the normal force between the scooter and the ground and is generally equal tom⋅gWhereinmIs the mass of the scooter,gis the acceleration of gravity; />Is an extra normal force due to dynamic conditions (such as acceleration);aandbis an empirically derived adjustment factor;
slope influence model: the gradient affects the gravitational component to which the object is subjected, and in order to take this effect into account, a gradient-based model is introduced:
，
wherein,is the mass of the scooter; />Is the acceleration of gravity; />Is a gradient angle and is obtained through an inclination angle sensor of the scooter; />Is the friction angle with the slope from manufacturer or experimental data; />Is a gradient adjustment coefficient for correcting the influence of gradient, and is obtained by an empirical method;
weather factor model: ambient humidity and temperature affect the coefficient of friction between scooter tires and the ground:
，
Wherein,the temperature is obtained by an environment sensor; />The humidity is obtained by an environment sensor; />The air pressure is obtained through an environment sensor; />Is a weather adjustment coefficient, and is obtained based on an empirical method; />Representing the nonlinear relation between humidity and temperature, which can capture the change of the influence of humidity on the friction coefficient when the temperature changes;
calculating frictional force using the above mathematical modelGradient influence->Introducing a dynamically adjusted parameter +.>To simulate the effects of other forces, such as wind resistance:
，
wherein the method comprises the steps of，pAndqis an adjustment index, based on experimental results,dynamically adjusted parameters:
，
wherein,the actual speed of the scooter is obtained through a speed sensor; />Is the theoretical speed calculated by the model; />Is an adjustment coefficient obtained through long-term monitoring;
based on the above process, a recommended safe speed range is obtained：
，
，
Wherein,is the maximum speed of the scooter specified by the manufacturer; />Is a small positive bias value for creating upper and lower limits on speed;
further, considering that the recommended safe speed range is limited by battery endurance and performance of a driving motor, a battery endurance influence model is constructed:
，
wherein,is the state of the battery, and represents the ratio of the current electric quantity to the maximum electric quantity of the battery; β 、γIs based on the adjustment coefficient obtained by the test;
motor performance impact model:
，
wherein,the rotation speed of the motor is obtained through a motor sensor; />The motor performance adjustment coefficient is obtained based on an empirical method; />Is the maximum speed of the motor, from manufacturer data;
in summary, a final recommended speed range may be obtained;
s12, obtaining road condition information;
further, analyzing the current road condition information, arranging a camera at the bottom of the electric scooter, scanning the road surface in real time, and collecting image data; training a machine learning model (such as a convolutional neural network) on a data set deployed and marked on the electric scooter, so that the electric scooter can identify different road surface types such as asphalt, gravel and bricks; a gyroscope and an acceleration sensor are deployed on the electric scooter, vibration and inclination of the scooter are monitored in real time, vibration data are analyzed through Fourier transformation, and the unevenness of a road surface is identified; in cooperation with the online map service negotiation, real-time traffic data is acquired, the online map data is utilized to evaluate the traffic conditions of the current area, such as traffic flow and pedestrian flow, by combining with the traditional traffic flow algorithm, and possible traffic events, such as accidents and roadblocks, are predicted based on historical data and a machine learning model; combining meteorological data and road condition history data, and predicting possible influence of environmental factors on road conditions by using a statistical analysis or machine learning method; through the scheme, the road conditions passed by the electric scooter can be accurately identified in real time, and powerful support is provided for subsequent speed adjustment;
According to the method, a mathematical calculation model is utilized, a plurality of models such as dynamic conditions, gradients and meteorological factors are combined, a relatively accurate recommended speed range can be obtained, so that safe running of the electric scooter under various conditions is guaranteed, possible influences of environmental factors on road conditions are predicted by combining meteorological data and road condition historical data, adjustment is performed in advance, and running stability of the electric scooter is guaranteed;
s2, detecting a front obstacle by using an object recognition algorithm based on front images and obstacle data from a camera and a radar to obtain obstacle information, and further predicting a movement track in a short time;
firstly, installing and calibrating a camera and a radar, selecting a proper position to install the camera and the radar at the front part of a scooter, and considering optical parameters to ensure a wide field of view; setting proper focal length, definition and visual angle for the camera to meet the actual road condition requirement, and calibrating the direction and range for the radar so that the detected object is a front obstacle; then, the real-time acquisition of the data, the camera continuously captures the front image data, and the radar sends electromagnetic wavesWave, calculate the distance of obstacle according to the echo data received, get real-time image data and distance data of obstacle ；
，
Wherein,is the distance of the obstacle and the distance of the obstacle,/>is the speed of electromagnetic waves in air, +.>Is the time of radar transmission to reception.
Further, object recognition and obstacle detection are performed;
first, in performing object recognition and obstacle detection, a single model may cause false detection or false omission. For example, transparent objects may be ignored in the image model and detected in the radar model;
performing model setting based on the image and radar data to obtain an image model and a radar model;
image model: optimization based on local characteristics of the image, including color, depth and illumination conditions of the image, first considers a simplified modelTo add information of pixel position +.>Introducing an attenuation factorFinally, obtaining a model through integration;
，
wherein,is the pixel coordinates of the image, ">Representing depth or pixel value, < >>Is the brightness and contrast parameter of the image; />Representing coordinates of the center of the image; />Representing adjustment parameters for balancing the influence of pixel values; />、/>Is the integral range of x, representing the width of the image; />、/>Is the integral range of y, representing the height of the image; this model describes how well the color of a location in the image matches a predetermined obstacle feature;
Radar model: the method comprises the steps of obtaining time-distance return data of a radar and the relative speed of an obstacle, firstly considering the time and the distance of the radar return, describing the relation of the time and the distance through a logarithmic function and a constant, adding the relative speed of the obstacle, and finally introducing weight to complete model setting;
，
wherein,is the distance of the obstacle, derived from radar, < >>Is the relative speed of the obstacle, derived from radar, < >>Is a weight factor obtained by experiment, < >>The time of the return of the radar signal is derived from the radar; />Is the propagation constant of radar signals, comes from equipment specifications; the formula combines radar data and dynamic data to describe the relationship between the distance of an obstacle and the propagation time and the relative speed of the radar signal;
to avoid false detection or missing detection, two models are fused:
，
wherein,、/>is a weight for adjusting the contribution of each model;
，
，
wherein,is an integral variable;
when the sensor data are inconsistent or noise exists, the data of the two models can be inconsistent or deviate from the actual conditions, and certain small or transparent barriers can be detected by mistake or ignored when the data are fused; data optimization is performed by utilizing the concepts of matrix operation and limitation:
Defining a state vectorRepresenting all sensor data at a certain moment; capturing high frequency noise or transient changes in very small time by concept of limits>State vector change within:
，
to take account of the dynamics of the environment, a state vector is calculatedOver time->Is a variable rate of (a):
，
a relative speed is defined taking into account the movement of the obstacle and the possible high speed variationsTo describe this dynamic situation, the speed is based on the above-mentioned state vector change and other parameters (e.g. weight factor +.>) Calculating to obtain;
，
wherein,is a state matrix of the obstacle; />Is a relative velocity matrix of the obstacle; />Is the logarithmic value of the change rate of the state vector and represents the change trend of the data; />Is time->Is enhanced by the data change over a short time interval versus relative speed>The influence of data changes over a long time interval on the relative speed is reduced>Is a function of (1); />Is a weight factor used for adjusting the influence degree of the data; />Acceleration, which represents the distance of an obstacle, is another parameter describing its motion characteristics, for describing the dynamics of the obstacle and ensuring that it is able to respond in a rapidly changing scene;
To sum up, obtain the position of the obstacleSize->Distance->And relative speed->；
Further predicting the moving track of the obstacle;
first, considering a basic physical model of obstacle movement, the future position of an object is represented by a function consisting of its current position, velocity and acceleration:
，
this formula is derived from a basic kinematic formula, wherein,is a small time interval; />Representing the position of an obstacle at time t, and deriving positioning data of the radar and the camera; />Representing the speed of the obstacle at time t, derived from successive position data differences; />The acceleration of the obstacle at time t is represented and is obtained through continuous speed data difference;
further, the method comprises the steps of,
，
considering the complex physical characteristics of an obstacle, its future position can also be predicted from the current position, velocity, acceleration, direction angle and angular velocity, according to the basic principle of matrix rotation:
，
wherein,is at the time +.>Position change in->Is a rotation matrix:
，
the direction angle of the obstacle at time t is deduced by image identification data provided by a camera; thus, the predicted position is:
，
meanwhile, the change in direction of the obstacle may be represented by an angular velocity:
，
wherein, Angular velocity of the obstacle at time t is represented, and is obtained through continuous direction angle data difference;
considering that the basic physical model may have errors in continuous curve motion, the two models of the basic physical model and the complex physical model are fused:
，
wherein,is a weight factor;
，
wherein,indicating that the obstacle is at time +>The internal direction angle changes.
The weight factors make the model more sensitive to recent dynamic changes, and a threshold matrix is introducedThe sensitivity of the prediction is reduced and,
，
、/>is an empirically selected threshold;
model sensitivityS(t) Can be defined asw(t) Absolute value of difference from its past value, ifw(t) There is a large change in the short time, and we can consider the model to be particularly sensitive at this point in time.
，
If it isS(t) Greater thanThe model is considered too sensitive to time response and in order to reduce this sensitivity the weighting is modified using the following methodFactor (2):
，
here, the current will bew(t) And its past value are weighted by a weighted averageDetermining;w′(t) The adjusted weighting factor, which reflects the dynamic response after accounting for model sensitivity;
the method and the system allow the system to find the optimal balance between the camera and the radar data by using a model fusion strategy, so that false detection and missing detection caused by a single data source are reduced, and the system can dynamically adapt to different environments and barrier characteristics by calculating and adjusting various parameters (such as weight factors) in real time; based on the physical model and the data fusion strategy, the system not only can detect the position and the relative speed of the obstacle, but also can predict the future movement track of the obstacle, and provides more information for real-time decision; the concept of matrix operation and limitation is introduced to perform data optimization, so that the system has better robustness to noise and other uncertain factors;
S3, integrating road condition and obstacle data by using an optimized data fusion algorithm containing dynamic weight adjustment based on road condition information and recommended safety speed range and obstacle data, and generating intelligent driving strategy advice according to the fusion data;
the road condition information is such as road surface type and road surface state; the obstacle data information such as an obstacle type, an obstacle distance, an obstacle size, and a predicted movement trajectory;
before processing these data, they need to be preprocessed; all data were in the range 0-1 by normalization;
firstly, multidimensional data fusion is required, which requires the road condition to be @, andR) The obstacle isO) Environment isE) And scooter stateZ) Is fused into an intelligent driving model;
to integrate these information, a predetermined weight matrix is usedIs introduced, wherein each weight initial value is obtained empirically:
，
the weight matrix is used for reconciling different input parameters, the sum of the weights is 1, and the comprehensive informationObtained by the following steps:
，
next, the fused data is to be securedCan accurately generate intelligent driving strategies>A polynomial regression equation is introduced:
，
Wherein,、/>、/>、/>、/>representing weight parameters, and determining through expert experience; />Is the optimal speed to be found; />Is the angle between the scooter and the obstacle; />Is the distance between the scooter and the obstacle;
for dynamic environments, dynamically adjusting the weight matrixIs necessary to reflect the most recent driving situation. For this purpose, a gradient descent algorithm is used to minimize a loss function +.>：
，
Is a loss function->Weight matrix->Gradient of->Is a loss function, and a mean square error can be used;is the learning rate;
finally, to ensure intelligent driving strategyIs introduced into the scoring formula +.>：
，
Wherein,is a regulating factor; />Is the maximum speed of the scooter, from manufacturer data; />Is the recent average speed; />Is the standard deviation of the velocity;
to sum up, intelligent driving strategy suggestions with scores can be obtained, wherein the intelligent driving strategy suggestions can have speed and confidence (scores);
the method and the device can more accurately predict the potential risk in front by fusing multidimensional data of road conditions (R), obstacles (O), environments (E) and scooter states (Z) in real time, so that safer driving suggestions are provided for users. In addition, the angle, the distance and other factors between the scooter and the obstacle are optimized, so that potential collision with the obstacle can be avoided, and the driving safety is further improved; the adoption of the dynamic weight adjustment mechanism can ensure that the system adjusts the weight matrix M according to the latest driving environment all the time, so that the intelligent driving strategy can adapt to various road condition changes in real time, and the timeliness and the accuracy of the intelligent driving strategy are ensured.
S4, based on intelligent driving strategy suggestion, adjusting motor output of the scooter to achieve speed and direction of the strategy suggestion;
firstly, receiving intelligent driving strategy suggestions from the step S3, including recommended speed, whether to slow down, accelerate or keep the current speed and the like;
to achieve this, first an intelligent driving strategy recommendation is received from step S3 using an embedded processor or microcontroller. Then, analyzing the received data to obtain specific driving suggestions, such as recommended speed, direction change and the like;
then, a speed difference is calculated from the parsed suggested speed and the current speed. This difference is processed by a PID control algorithm (or other suitable control algorithm) to generate a corresponding motor control signal. These signals are received and interpreted via a motor driver or a motor control module. According to the control signal, the motor of the scooter can adjust the voltage or Pulse Width Modulation (PWM) signal thereof, thereby achieving the purpose of accelerating, decelerating or maintaining the current speed;
if the driving strategy suggests that a change in direction is required, a directional controller or servo motor may be activated to adjust the heading of the scooter. To ensure that the speed always matches the recommended speed, scooters use a speed sensor (e.g. hall effect sensor or photoelectric encoder) to continuously monitor their real-time speed. When the real-time speed detected by the speed sensor deviates from the recommended speed, the motor control signal is correspondingly adjusted to match the recommended speed;
In order to ensure riding safety, when the speed exceeds the recommended safe speed range or large acceleration or deceleration suddenly occurs, an emergency braking or acceleration limiting function is started;
finally, the system outputs the real-time speed of the scooter through the speed sensor, and simultaneously, outputs the advancing direction of the scooter through the position information of the direction controller or the servo motor.
In summary, the speed adaptive control system and method for the electric scooter are completed.
The technical scheme in the embodiment of the application at least has the following technical effects or advantages:
1. according to the method, a mathematical calculation model is utilized, a plurality of models such as dynamic conditions, gradients and meteorological factors are combined, a relatively accurate recommended speed range can be obtained, so that safe running of the electric scooter under various conditions is guaranteed, possible influences of environmental factors on road conditions are predicted by combining meteorological data and road condition historical data, adjustment is performed in advance, and running stability of the electric scooter is guaranteed;
2. the method and the system allow the system to find the optimal balance between the camera and the radar data by using a model fusion strategy, so that false detection and missing detection caused by a single data source are reduced, and the system can dynamically adapt to different environments and barrier characteristics by calculating and adjusting various parameters (such as weight factors) in real time; based on the physical model and the data fusion strategy, the system not only can detect the position and the relative speed of the obstacle, but also can predict the future movement track of the obstacle, and provides more information for real-time decision; the concept of matrix operation and limitation is introduced to perform data optimization, so that the system has better robustness to noise and other uncertain factors;
3. The method and the device can more accurately predict the potential risk in front by fusing multidimensional data of road conditions (R), obstacles (O), environments (E) and scooter states (Z) in real time, so that safer driving suggestions are provided for users. In addition, the angle, the distance and other factors between the scooter and the obstacle are optimized, so that potential collision with the obstacle can be avoided, and the driving safety is further improved; the adoption of the dynamic weight adjustment mechanism can ensure that the system adjusts the weight matrix M according to the latest driving environment all the time, so that the intelligent driving strategy can adapt to various road condition changes in real time, and the timeliness and the accuracy of the intelligent driving strategy are ensured.
Effect investigation:
4. the technical scheme of the system and the method can effectively solve the technical problems of poor real-time performance and poor accuracy when the speed self-adaptive control of the electric scooter is carried out, and through a series of effect investigation, a relatively accurate recommended speed range can be obtained by combining a plurality of models such as dynamic conditions, gradients and meteorological factors by utilizing a mathematical calculation model, so that the safe running of the electric scooter under various conditions is ensured, the possible influence of environmental factors on road conditions is predicted by combining meteorological data and road condition history data, and the running stability of the electric scooter is ensured by adjusting in advance; the system is allowed to find the optimal balance between the camera and the radar data by utilizing a model fusion strategy, so that false detection and missing detection caused by a single data source are reduced, and the system can dynamically adapt to different environments and barrier characteristics by calculating and adjusting various parameters (such as weight factors) in real time; based on the physical model and the data fusion strategy, the system not only can detect the position and the relative speed of the obstacle, but also can predict the future movement track of the obstacle, and provides more information for real-time decision; the concept of matrix operation and limitation is introduced to perform data optimization, so that the system has better robustness to noise and other uncertain factors; through fusing the multidimensional data of road conditions (R), obstacles (O), environments (E) and scooter states (Z) in real time, the potential risks in front can be predicted more accurately, and therefore safer driving suggestions are provided for users. In addition, the angle, the distance and other factors between the scooter and the obstacle are optimized, so that potential collision with the obstacle can be avoided, and the driving safety is further improved; the adoption of the dynamic weight adjustment mechanism can ensure that the system adjusts the weight matrix M according to the latest driving environment all the time, so that the intelligent driving strategy can adapt to various road condition changes in real time, and the timeliness and the accuracy of the intelligent driving strategy are ensured.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (9)
1. Electric scooter speed self-adaptation control system, its characterized in that includes following part:
the road condition sensing module, the front obstacle detection and track prediction module, the power adjustment module, the data synchronization and management module, the road condition and obstacle data fusion module and the dynamic weight adjustment module;
the output of the road condition sensing module is sent to the power adjustment module and the road condition and obstacle data fusion module; the road condition and obstacle data fusion module synthesizes the road condition and the front obstacle data, and carries out fusion processing to obtain intelligent driving strategy advice; the output of the front obstacle detection and track prediction module is also sent to the power adjustment module and the road condition and obstacle data fusion module; the power adjustment module adjusts the power output of the scooter in real time according to the road condition and the data of the front obstacle, ensures that the speed of the scooter is always kept within the recommended safe speed range, and adjusts the power and the speed according to the road condition and the obstacle data fusion module and the dynamic weight adjustment module; the dynamic weight adjustment module can dynamically adjust the weight according to the output of the road condition and obstacle data fusion module; the data of all modules are synchronized and managed by the data synchronization and management module.
2. The electric scooter speed adaptive control system as claimed in claim 1, further comprising:
the road condition sensing module captures road surface and meteorological data through a road surface sensor and an environment sensor, and recognizes the current road condition through real-time analysis of the road surface and the meteorological data; predicting the friction change of the road surface according to the meteorological data; further, providing current road condition information and a recommended safe speed range;
the front obstacle detection and track prediction module is used for capturing front images and obstacle data by using a camera and a radar, detecting and analyzing the front obstacle in real time, and predicting the moving track of the obstacle at the same time;
the data synchronization and management module ensures that the data interaction among all modules is synchronous and stable, and is also responsible for storing and managing the data from each module, thereby ensuring the real-time performance of the data;
the dynamic weight adjustment module dynamically adjusts the weight in the data fusion algorithm according to the real-time environment and the intelligent driving strategy suggestion, so as to ensure that the intelligent driving strategy is always optimal.
3. The speed self-adaptive control method for the electric scooter is characterized by comprising the following steps of:
S1, road condition data acquisition is carried out by using a road surface sensor and an environment sensor, and the acquired road surface data and meteorological data are processed and analyzed to obtain current road condition information and a recommended safe speed range;
s2, detecting a front obstacle by using an object recognition algorithm based on front images and obstacle data from a camera and a radar to obtain obstacle information, and further predicting a movement track in a short time;
s3, integrating road condition and obstacle data by using an optimized data fusion algorithm containing dynamic weight adjustment based on road condition information and recommended safety speed range and obstacle data, and generating intelligent driving strategy advice according to the fusion data;
s4, based on the intelligent driving strategy suggestion, adjusting the motor output of the scooter to achieve the speed and direction of the strategy suggestion.
4. The speed adaptive control method of an electric scooter according to claim 3, wherein in the step S1, specifically comprising:
in the process of processing and analyzing the acquired pavement data and the acquired meteorological data to obtain a recommended speed range, defining a mathematical calculation model: friction model, gradient influence model, meteorological factor model.
5. The speed adaptive control method of an electric scooter according to claim 4, further comprising, in the step S1:
calculating friction and gradient effects by using the mathematical calculation model, and introducing dynamically adjusted parametersTo simulate the influence of wind resistance and obtain a recommended safe speed range.
6. The electric scooter speed adaptive control method according to claim 5, further comprising, in the step S1:
the recommended safe speed range is considered to be limited by battery endurance and performance of a driving motor, and a battery endurance influence model and a motor performance influence model are constructed.
7. The electric scooter speed adaptive control method according to claim 3, further comprising, in the step S2:
when detecting the front obstacle, setting a model based on the image and radar data to obtain an image model and a radar model, and fusing the two models to avoid false detection and omission of the single model.
8. The electric scooter speed adaptive control method according to claim 7, further comprising, in the step S2:
when detecting the front obstacle, when the sensor data are inconsistent and noise exists, the data of the image model and the radar model can be inconsistent and deviate from the actual conditions, and the data fusion can lead to the false detection and omission of the individual small and transparent obstacles; and data optimization is performed by utilizing the concepts of matrix operation and limitation.
9. The electric scooter speed adaptive control method according to claim 3, further comprising, in the step S2:
when predicting the moving track of the obstacle, taking a basic physical model of the obstacle movement and a complex physical model of the obstacle into consideration, taking errors of the basic physical model in continuous curve movement into consideration, introducing a weight factor to fuse the two models, taking the weight factor into consideration to make the model more sensitive to recent dynamic changes, and introducing a threshold matrixTo reduce the sensitivity of the prediction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311243409.1A CN116985803B (en) | 2023-09-26 | 2023-09-26 | Self-adaptive speed control system and method for electric scooter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311243409.1A CN116985803B (en) | 2023-09-26 | 2023-09-26 | Self-adaptive speed control system and method for electric scooter |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116985803A CN116985803A (en) | 2023-11-03 |
| CN116985803B true CN116985803B (en) | 2023-12-29 |
Family
ID=88521650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311243409.1A Active CN116985803B (en) | 2023-09-26 | 2023-09-26 | Self-adaptive speed control system and method for electric scooter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116985803B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117475806B (en) * | 2023-12-28 | 2024-03-29 | 深圳康荣电子有限公司 | Display screen self-adaptive response method and device based on multidimensional sensing data feedback |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101975951A (en) * | 2010-06-09 | 2011-02-16 | 北京理工大学 | Field environment barrier detection method fusing distance and image information |
| CN207198663U (en) * | 2017-09-30 | 2018-04-06 | 徐工集团工程机械股份有限公司 | Road roller and road roller control system |
| CN109677402A (en) * | 2018-11-13 | 2019-04-26 | 顺丰科技有限公司 | The security protection system and method for automatic Pilot tool |
| CN113420687A (en) * | 2021-06-29 | 2021-09-21 | 三一专用汽车有限责任公司 | Method and device for acquiring travelable area and vehicle |
| CN113779705A (en) * | 2021-09-28 | 2021-12-10 | 中国科学技术大学先进技术研究院 | Intelligent grade assessment method and system for automatic driving automobile |
| CN114528040A (en) * | 2022-01-26 | 2022-05-24 | 高新兴科技集团股份有限公司 | Environment self-adaption method, device, medium and roadside perception and calculation system |
| CN114872670A (en) * | 2022-07-11 | 2022-08-09 | 徐工集团工程机械股份有限公司道路机械分公司 | Control method for self-adaptive adjustment of braking force of hydraulic braking road roller |
| WO2023286917A1 (en) * | 2021-07-16 | 2023-01-19 | 한국건설기술연구원 | System and method for detecting both road surface damage and obstacles by using deep neural network, and recording medium in which computer-readable program for executing same method is recorded |
| CN115793665A (en) * | 2022-12-23 | 2023-03-14 | 东风悦享科技有限公司 | Vehicle road cooperative obstacle avoidance method and system based on unmanned truck-mounted remote driving system and storage medium |
-
2023
- 2023-09-26 CN CN202311243409.1A patent/CN116985803B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101975951A (en) * | 2010-06-09 | 2011-02-16 | 北京理工大学 | Field environment barrier detection method fusing distance and image information |
| CN207198663U (en) * | 2017-09-30 | 2018-04-06 | 徐工集团工程机械股份有限公司 | Road roller and road roller control system |
| CN109677402A (en) * | 2018-11-13 | 2019-04-26 | 顺丰科技有限公司 | The security protection system and method for automatic Pilot tool |
| CN113420687A (en) * | 2021-06-29 | 2021-09-21 | 三一专用汽车有限责任公司 | Method and device for acquiring travelable area and vehicle |
| WO2023286917A1 (en) * | 2021-07-16 | 2023-01-19 | 한국건설기술연구원 | System and method for detecting both road surface damage and obstacles by using deep neural network, and recording medium in which computer-readable program for executing same method is recorded |
| CN113779705A (en) * | 2021-09-28 | 2021-12-10 | 中国科学技术大学先进技术研究院 | Intelligent grade assessment method and system for automatic driving automobile |
| CN114528040A (en) * | 2022-01-26 | 2022-05-24 | 高新兴科技集团股份有限公司 | Environment self-adaption method, device, medium and roadside perception and calculation system |
| CN114872670A (en) * | 2022-07-11 | 2022-08-09 | 徐工集团工程机械股份有限公司道路机械分公司 | Control method for self-adaptive adjustment of braking force of hydraulic braking road roller |
| CN115793665A (en) * | 2022-12-23 | 2023-03-14 | 东风悦享科技有限公司 | Vehicle road cooperative obstacle avoidance method and system based on unmanned truck-mounted remote driving system and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116985803A (en) | 2023-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109213126B (en) | Automatic driving automobile test system and method | |
| CN109884916B (en) | Automatic driving simulation evaluation method and device | |
| US10518783B2 (en) | Automatic driving control device | |
| US20200209874A1 (en) | Combined virtual and real environment for autonomous vehicle planning and control testing | |
| US20240144748A1 (en) | Systems and Methods to Obtain Feedback in Response to Autonomous Vehicle Failure Events | |
| CN112700470B (en) | Target detection and track extraction method based on traffic video stream | |
| JP2020524632A (en) | System and method for obtaining occupant feedback in response to an autonomous vehicle driving event | |
| CN109100155A (en) | A kind of unmanned vehicle is in ring high-speed simulation test macro and method | |
| KR102167291B1 (en) | System and method for providing road status information | |
| CN116985803B (en) | Self-adaptive speed control system and method for electric scooter | |
| EP3676147B1 (en) | Autonomous driving apparatus and method for autonomous driving of a vehicle | |
| CN109190488B (en) | Front vehicle door opening detection method and device based on deep learning YOLOv3 algorithm | |
| US20160318520A1 (en) | Method, System, and Computer Program Product for Monitoring a Driver of a Vehicle | |
| CN109191788B (en) | Driver fatigue driving judgment method, storage medium, and electronic device | |
| CN111152792A (en) | Device and method for determining the level of attention demand of a vehicle driver | |
| CN115907250A (en) | Learning-based commenter for adjusting a motion planner of an autonomously driven vehicle | |
| CN113342701A (en) | Method and device for interaction between unmanned simulation system and tested unmanned software | |
| CN110660141B (en) | Road surface condition detection method and device, electronic equipment and readable storage medium | |
| US11327878B2 (en) | Method for rating a software component of an SiL environment | |
| CN112319505A (en) | Automatic driving lane change judgment method, device, equipment and storage medium | |
| CN114024997B (en) | Intelligent equipment based on automatic driving and AIOT Internet of things platform method | |
| KR102519715B1 (en) | Road information providing system and method | |
| CN115017824A (en) | Method, medium, and electronic device for evaluating autonomous driving module | |
| KR102354734B1 (en) | Method and system for predicting, analyzing and judging accidental hazard of car and object having relative high variations | |
| CN117601859B (en) | Early warning system and method for preventing vehicle from collision |
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 |