254results about How to "Realize autonomous driving" patented technology

The invention discloses an automatic automobile driving method and device and relates to the technical field of intelligent automobile control. According to the automatic automobile driving method, an automobile driving environment risk model is established based on a field theory. Thus, a driving environment risk field is utilized to completely reflect an automobile driving environment, and automatic driving in different road environments can be achieved. Furthermore, an automatic automobile driving model is trained according to the driving environment risk field and driver operation to learn experience of excellent human drivers, and personalized automatic driving is achieved.

This invention relates to an automatic driving system of a road vehicle, especially to a system which providing automatic driving information indication for traveling vehicles and realizing vehicle automatic driving through the vehicle automatic control system, which is characterized by comprising: fixing markers at interval along a road travelling line, receiving information feedback by the fixed markers through a set relay information station and forming the vehicle and road information on the road, and constantly supplying the road and vehicle information of the road where the vehicle is to a vehicle automatic receiving processor after the received GPS(Global Position System) information and the vehicle and road information on the road are overall treated, installing an automatic driving software in a vehicle-mounted computer which can receive and treat relevant information of the relay information station at any time, constantly sending operation instructions to a vehicle automatic controller so as to keep the vehicle travelling information direction line consistent with the vehicle driving speed direction line, and sending instructions to the vehicle automatic controller according to the selected mode by a driver so as to realize vehicle automatic driving.

The invention discloses a system for planning and controlling train travelling speed. The system comprises ground equipment which is approached during travelling of a train, and vehicle-carried equipment arranged on the train. The vehicle-carried equipment comprises a speed meter, a human-computer interface, a ground equipment answering unit, a train automatic protecting unit, a speed control unit and a traction / brake unit, wherein the train automatic protecting unit is respectively connected with the speed meter, the human-computer interface, the ground equipment answering unit and the speed control unit; the ground equipment answering unit is respectively connected with the ground equipment and the train automatic protecting unit; and the speed control unit is respectively connected with the train automatic protecting unit and the traction / brake unit. The system receives information including railway condition, line limit speed, travelling authority and the like, through a ground answerer; the comfort of passengers, the time accuracy and the energy conservation of train travelling are considered at the same time to plan the optimal distance-speed-based target speed running curve; and real-time tracking on the target speed is realized by outputting a proper traction / brake instruction.

The invention discloses an automatic-driving intelligent vehicle trajectory tracking control strategy based on deep reinforcement learning. For an intelligent vehicle automatic-driving task, accordingto an action-critics structure in a deterministic policy gradient (DDPG) algorithm, a double-action network is adopted to output a steering wheel angle command and a vehicle speed command. A main reviewer network is designed to guide the updating process of the double-action network, and the stragety specifically comprises the steps of describing an automatic driving task as a Markov decision process: < st,at,Rt, st +1 >; initializing a'double-action 'network in the improved DDPG algorithm by adopting a behavior cloning algorithm; pre-training a'reviewer 'network in the deep reinforcement learning DDPG algorithm; designing a training road containing various driving scenes to carry out reinforcement learning online training; and setting a new road to test the trained deep reinforcement learning (DRL) model. The control strategy is designed by simulating the human driving learning process, and automatic driving of the intelligent vehicle in the simple road environment is achieved.

The invention discloses a roadside sensing system based on vehicle-road cooperation and a vehicle control method using the same. The system comprises intelligent roadside equipment, the intelligent roadside equipment comprises a roadside sensing module, a roadside processing module and a roadside communication module, the roadside sensing module comprises a sensor and is used for collecting surrounding environment information of a target vehicle, the roadside processing module is used for carrying out fusion processing on the collected surrounding environment information to form road environment information, the roadside communication module is used for sending the road environment information to the target vehicle, the target vehicle comprises a driving behavior decision module, and the driving behavior decision module is used for carrying out path planning according to the road environment information and carrying out automatic driving according to a path planning result. Therefore,a common vehicle on a road can realize automatic driving by interacting with the intelligent roadside equipment, the whole vehicle cost of configuring a sensing system on the vehicle is effectively reduced, and the cost of an intelligent traffic system is effectively reduced.

The invention discloses an intelligent network connection traffic management system facing mobile sharing. The system is used to realize the automatic driving, operation and control of an intelligentnetwork connection vehicle on a road for a shared mobile service provider. The system provides specific personalized information and a time-sensitive control command to the intelligent network connection vehicle to assist the vehicle to complete an automatic driving task, and simultaneously, provides operations and maintenance services to a vehicle owner and / or the shared mobile service provider of the vehicle. The vehicle is a full time control or partial time control vehicle. The driving task comprises one or more of the following contents: vehicle following, lane changing, and path navigation.

The invention provides an automatic driving system which not only can realize the automatic driving of a single vehicle, but also can control the running of other vehicles. The automatic driving system comprises a main vehicle system arranged on a main vehicle, and a following vehicle system arranged on a following vehicle, wherein induction units, control units, execution units and information transmission units are arranged in both the main vehicle system and the following vehicle system, the induction unit comprises a vehicle speed sensor, a corner sensor and an external environment sensor, and the execution unit comprises an auxiliary steering mechanism, a throttle control device, a gear control device and an auxiliary brake body. The main vehicle control unit obtains the road information by the external environment sensor and realizes the automatic driving by controlling the execution unit, and the following vehicle utilizes the information of the main vehicle to control the running state thereof, so both of the main vehicle and the following vehicle do not need drivers. The automatic driving system is particularly suitable for the long-distance running of motorcades for combined self-driving tour and the like, relieves the fatigue strength of the driver of the following vehicle, and improves the safety and the comfort of running.

The invention belongs to the field of high-voltage transmission line operation inspection and particularly relates to a transmission line unmanned aerial vehicle automatic driving inspection method. The method comprises the steps that S1, according to the model, range, opening angle and communication distance of a laser radar, the area of a scanning region of the laser radar is calculated; S2, RTKlaser radar unmanned aerial vehicle base station positioning is performed through Qianxun precise positioning service; S3, a horizontal distance value maintained between a transmission line center and an unmanned aerial vehicle, a vertical distance theoretical value maintained between the unmanned aerial vehicle and a horizontal ground and a designed height value between the unmanned aerial vehicle and the horizontal ground are calculated; S4, unmanned aerial vehicle manual flight laser modeling is performed, and an automatic driving air route of the unmanned aerial vehicle is planned; and S5, according to a transmission line laser point cloud entity model obtained through laser radar modeling, an intelligent inspection automatic driving air route of the unmanned aerial vehicle is generated. Through the method, flight air route planning, automatic driving, refined inspection and laser radar data collection of the unmanned aerial vehicle in a strong electromagnetic field are realized,and transmission line modeling and inspection quality is greatly improved.

The utility model discloses a self-steering control mode and system for the large-sized engineering truck. The tag line is made as the vehicle moving track along the road; the vehicle is equipped with a kinetic control system and a camera chain; the kinetic control system controls the moving forward of the vehicle. In the course of moving forward, the tag line is shot by the video camera in the camera chain, so that the computer in the camera chain can make the analysis according to the tag line-related real time video image, so as to work out the vehicle bias data which are transferred to the kinetic control system. As per the bias data, the kinetic control system can follow the existing moving direction or correct the moving direction. The method achieves the self-steering and the automatic guide of the large-sized engineering truck, so as to improve the work efficiency for the large-sized cargo transportation and the reliability in the transportation process.

The invention discloses a punctual train control system in a CBTC (Communication-based Train Control) fault mode and a control method of the punctual train control system in the CBTC fault mode. The punctual train control system comprises an ATS (Automatic Train Supervision) system, an axle counting system, an interlocking system, a trackside ATO (Automatic Train Operation) part, a trackside ATP (Automatic Train Protection) part, a trackside radio station, a vehicle-mounted radio station and a target controller, and particularly comprises a signal machine, a signal machine beacon, an advance announcing beacon and a vehicle-mounted ATC, wherein the ATS system is used for sensing various control commands; the axle counting system is used for monitoring the train positions; the interlocking system and the trackside ATO part are used for receiving the control commands from the ATS system; the trackside ATP part is used for building train moving authority; the trackside ratio station is used for sending the moving authority information of the trackside ATP part; the vehicle-mounted ration station is used for receiving information of the trackside ratio station; the target controller is used for collecting the trackside equipment state information; and the vehicle-mounted ATC comprises a database. The punctual train control system has the function of punctual ATC automatic driving, and also has the functions of double-red-lamp protection, overspeed protection, train precise station stop and the like at the same time.

The invention discloses an auxiliary driving system and method for rapid passing of a vehicle in a crossing. The system comprises an information collection module, a vehicle positioning module, a barrier identification module, a database module, a signal lamp information module, a vehicle auxiliary decision module and an automobile power system. According to technical features of road traffics and physical features of drivers, a method including guiding information through which each crossing can be passed rapidly and smoothly and a vehicle in front can be overtaken is provided for the driver in the driving process, the guiding information including whether to overtake, the concrete driving speed and the like, and thus, when the vehicle is driven according to the guiding speed and manner, the crossing can be passed without stop, and core technical support is provided for development of Internet of vehicles and automatic driving technologies.

The invention discloses an autonomous vehicle deciding system under a complicated working condition and a track planning method thereof. The autonomous vehicle deciding system mainly comprises an environment sensing unit, a real-time deciding unit, a track planning unit and a control unit. During a driving process of a vehicle, the environment sensing unit is used for transmitting sensed surrounding vehicle moving information to the real-time deciding unit and deciding the optimal driving behavior of an autonomous vehicle under a current state; after the driving behavior is decided, the trackplanning unit is used for carrying out dual planning on a path and the speed of the vehicle through the set track planning method and obtaining the optimal track under the current state and inputtingcorresponding control signals to an execution mechanism through an ECU (Electronic Control Unit) so as to ensure safe and reliable driving of the vehicle. According to the autonomous vehicle decidingsystem and the track planning method, disclosed by the invention, a safe and collision-free track can be planned for the vehicle in real time under the complicated condition with multiple lanes and multiple barrier vehicles, and automatic driving of the vehicle can be realized.

The invention discloses an edge computing station and an automatic driving method based on the edge computing station. The edge computing station comprises a sensing device used for obtaining positioning, environmental information and planning information of autonomous vehicles within a coverage area; an autonomous vehicle access interface pool for automatically connecting the autonomous vehiclesthrough an agreed network protocol; a computation module used for finishing computation of the accessed autonomous vehicles and giving corresponding driving decision information; a storage module forstoring all of the data information; and a network module used for connecting the edge computing station and a cloud end to finish upload of information stored in the storage module and download of cloud end information. Compared with the prior art, the edge computing station and the automatic driving method based on the edge computing station can solve the problem of application demand of autonomous vehicles in occasions of expressways, fixed parks and urban public transportation and the like, which require specific routes, and is high in practicality.

The invention provides a detection system for detecting targets around a vehicle and application of the detection system. The detection system includes a vehicle front forward direction sensor (1), a vehicle roof forward direction sensor (2), a right front sensor (3), a left front sensor (4), a right rear sensor (5), a left rear sensor (6), a rear sensor (7), a left side sensor (8), a right side sensor (9) and target selection modules (10), wherein the target selection modules (10) include a forward direction target selection module (11) and a side direction and backward direction target selection module (12), wherein the forward direction target selection module is configured to select targets at least four positions in front of the vehicle as vehicle front side tracking targets based on received target motion information, and the side direction and backward direction target selection module is configured to select targets at the side direction and backward direction of the vehicle as vehicle side direction and backward direction tracking targets according to received target motion information.

The present invention relates to an automatic driving system of locomotive. A signal information collection module is configured to collect locomotive information required by automatic driving of thelocomotive, transmit the locomotive information to a train ATO system and send the locomotive information through a man-machine interaction module to a train driver for monitoring and control; the train ATO system is configured to calculate and obtain an optimal console shift sequence of the locomotive control according to the locomotive information sent by the signal information collection module, send the locomotive control and console instruction sequence to the man-machine interaction module, and the man-machine interaction module notifies the train driver of manual / automatic operation forsafe switching according to the locomotive control instruction sequence; and the train ATO system is configured to receive the train driver's instruction through the man-machine interaction module and perform setting of a manual / automatic switch according to the instruction. The train ATO system has good fusion with a current vehicle system to obtain the optimal locomotive control and console sequence and achieve automatic driving of the locomotive according to the locomotive control and console sequence.

The invention discloses a train automatic driving control method and system. The method comprises the steps of obtaining the real-time information of train operation and road condition information ofa road section within a preset distance in front of a train; dividing the road section within the front preset distance into a plurality of scenes according to the road condition information of the road section within the front preset distance; adopting the real-time information of train operation, the information of the train and the control rule of each scene as constraint conditions, adopting aplurality of preset targets as optimization targets to calculate a target curve of the train running on a road section within a preset distance in front, and the target curve comprises working condition information required by the train running in each scene and the target speed of the train; and generating a control instruction for indicating to control the train according to the target curve tocontrol the train to automatically drive according to the target curve. According to the train automatic driving control method and system, automatic driving of the train is achieved, the operation safety of the train is improved, and the transportation efficiency is improved.

The invention relates to an automatic driving system based on relative-entropy deep and inverse reinforcement learning. The system comprises a client, a driving basic data collection sub-system and astorage module, wherein the client displays a driving strategy; the driving basic data collection sub-system collects road information; the storage module is connected with the client and the drivingbasic data collection sub-system and stores the road information collected by the driving basic data collection sub-system. The driving basic data collection sub-system collects the road information and transmits the road information to the client and the storage module; the storage module receives the road information, stores a piece of continuous road information into a historical route, conducts analysis and calculation according to the historical route so as to simulate the driving strategy, and transmits the driving strategy to the client so that a user can select the driving strategy; the client receives the road information and implements automatic driving according to the selection of the user. In the automatic driving system, the relative-entropy deep and inverse reinforcement learning algorithm is adopted, so that automatic driving under the model-free condition is achieved.

The invention discloses a track planning method for lane centering auxiliary self-adaptive cruise, which comprises the following steps of: fitting lane lines according to acquired lane line data to obtain a lane line equation, and generating a region of interest of a vehicle; performing cost calculation on obstacles in the region of interest to obtain target obstacle information; calculating the road center line of the current lane according to the left and right lane line data, namely the optimal driving path; and carrying out longitudinal speed planning of the vehicle is carried out according to the target obstacle information in combination with the vehicle state information of the vehicle, obtaining a vehicle longitudinal speed curve, and completing the track planning, wherein the target obstacle information comprises the relative position of an obstacle and the vehicle and the speed information of the vehicle. When no RTK signal exists or the signal is lost, a transverse and longitudinal speed planning curve is obtained based on camera feedback data and millimeter wave data, transverse and longitudinal decoupling control is finally completed, and automatic driving of a low-cost hardware architecture under a structured road is achieved.

The invention discloses an intelligent networked automatic driving system suitable for a minibus. The system comprises an environment sensing device, a positioning and navigation combination device, aV2X communication device, a motion control device and a man-machine interaction device which are connected with an intelligent networked automatic driving domain controller, wherein the controller isused for calculation and control, and comprises a central processing unit and a domain controller interface; the environment sensing device is used for obtaining the environment of a vehicle and surrounding environment information of vehicle driving; the positioning and navigation integrated device comprises an INS inertial navigation unit, a four-frequency double-antenna RTK satellite navigationreceiver and a 5G differential module; the motion control device comprises a transverse control device and a longitudinal control device; and the man-machine interaction device is used for information interaction of vehicles. The system can be applied to cities with richer application scenes, an intelligent network connection function is realized, the weighting distribution coefficient is introduced to realize longitudinal and transverse cooperative motion control of the whole vehicle, and the safety is greatly improved.

The invention discloses an automatic measuring system for the inclination of a transmission line tower and a measuring method thereof. The measuring method comprises the following steps: acquiring thecoordinates of the transmission line tower, the height of the tower and the size of a crossbar, and transmitting data to an intelligent control terminal by an unmanned aerial vehicle to form a KML file of a tower path; planning an unmanned aerial vehicle autopilot modeling route in conjunction with the scanning area of a laser radar, the coordinates of transmission line tower, the height of the tower and the maximum length of the crossbar; flying according to the autopilot modeling route to build a laser point cloud model of the transmission line tower; and performing coordinate transformation and data fitting on POS data and IMU data to generate point cloud las data, extracting the spatial coordinates of ten points, including a tower center point, base datum positioning points and connecting points of a tower material, and calculating the tower inclination by using a ten-point measurement method for tower inclination. The automatic measuring system and method can automatically measure the inclination of the tower, have the advantages of high accuracy, easiness in operation and high efficiency, and are applicable to the field of inclination measurement of the transmission line tower.

The invention relates to an automatic driving system and method based on a monocular camera and the raspberry pie. The automatic driving system comprises a data collecting unit, a data preprocessing unit, a deep convolutional neural network and a control unit connected in sequence. The data collecting unit is used for collecting a data set. The data preprocessing unit is used for preprocessing thecollected data set. The deep convolutional neural network is used for training the preprocessed data set to obtain a mature model. The control unit is used for training the obtained mature model to enable the model vehicle to run automatically on a model lane. According to the invention, the expensive hardware like the complicated deep network model and radar are abandoned; automatic driving under conditions of low computing power and poor hardware condition is realized; and thus the unmanned driving is realized by using an end-to-end neural network and relying on the pure visual recognitionwith low costs while only the monocular camera and the raspberry pie are used.

The invention discloses an automatic driving system based on 5G vehicle-road cooperation. The system comprises: an automatic driving system used for obtaining vehicle attitude information, vehicle sensing environment information and a driving intention through a plurality of sensors disposed on a vehicle body, carrying out interaction with a roadside system and a cloud platform, and controlling the operation of the vehicle; the roadside system comprising a sensor group, an edge calculation unit and a roadside unit, wherein the sensor group is used for acquiring road information and meteorological data of a local scene, the edge calculation unit is used for receiving and processing the sensing data of sensors and acquiring map information and road condition information of the local scene, and the roadside unit is used for uploading the map information and the road condition information, and issuing a business task and a cooperative scheduling instruction to the automatic driving system; and the cloud platform used for globally carrying out decision planning on the road and vehicle operation in the local scene. According to the invention, automatic driving is reliably realized, and the dependence of the passenger car on a high-precision sensor is effectively reduced.

The invention discloses a blind aid system based on infrared sensing geometrical characteristic recognition, comprising a trolley body, a singlechip, an infrared sensor module, a voice prompt module, a power module and a manual control module, wherein the infrared sensor module is used for detecting the distance between the trolley bottom and the ground, distinguishing a striped go-ahead blind sidewalk and a dot-shaped prompt blind sidewalk according to the compared feedback information of an obtained result and transmitting the result to the singlechip; the singlechip is used for processing the blind sidewalk surface geometrical characteristic information detected by the sensor module so as to recognize the prompt blind sidewalk and the go-ahead blind sidewalk, and then dynamically adjusting the motion state of the trolley according to the recognized prompt blind sidewalk and go-ahead blind sidewalk result; the voice prompt module is used for carrying out voice prompt on the condition of the trolley keeping moving straight or reaching to the prompt blind sidewalk; and the manual control module is used for manually controlling the motion state of the trolley. The invention can better provide convenience for the disabled, such as the blind, and the like, thereby improving the life quality of the disabled.

The invention provides a storage battery powered train and a train network control system. A main transmission system of the train comprises a power storage battery, a traction converter cabinet and a traction motor. The power storage battery is connected with the input end of the traction converter cabinet, and the traction motor is connected with the output end of the traction converter cabinet. The control system comprises that a train automatic driving system is connected with a train control module, and a storage battery management system is connected with the CAN gateway module in each train carriage. An event recorder, a display, an analog input module, a first door controller, a second door controller, a train control module, a digital input and output module, a CAN gateway module, a traction control unit, a brake control unit and an air conditioning control unit are connected to a communication bus, and the communication bus is connected to a MVB repeater. The storage battery powered train has a special network control system.

The invention provides a container truck automatic driving system and method. The system comprises a remote monitoring device which is used for generating a transportation task and a transportation route through a preset container transportation plan and the map of the port where a container is located, and a vehicle-mounted automatic driving device which is arranged on a container truck, and is used for receiving the transportation task and route issued by the remote monitoring device and controlling the container truck to travel based on the transportation route to complete the transportation task. According to the invention, the port ground and other infrastructure are free of large-scale transformation; and the problems of low transport efficiency and poor job reliability due to manual container truck driving are solved.

The invention discloses an unmanned scout car. The unmanned scout car comprises a drive-by-wire chassis and a main controller in communication connection with the drive-by-wire chassis and used for generating a control command to drive the unmanned scout car to travel autonomously. The main controller is connected with an environment sensing system used for collecting surrounding environment parameters of the unmanned scout car. The unmanned scout car further comprises a power supply system used for supplying power to the unmanned scout car, and is further provided with a scout system for scouting surrounding targets of the unmanned scout car. As the environment sensing system is adopted to collect the surrounding environment parameters of a car body and the main controller generates the control command to the drive-by-wire chassis according to the collected environment parameters, autonomous traveling of the unmanned scout car is achieved; and besides, the unmanned scout car is provided with the scout system, the purpose of replacing manpower to perform automatic patrol and guard on important places can be achieved, and the unmanned scout car has the broad application and popularization value.

The present disclosure relates to an automatically driven electric scooter comprising: a positioning module, a task instruction module, an environment sensing module, a decision and control module, apower module, an execution module, and a ride module. The positioning module is configured to determine the location of the scooter itself. The task instruction module is configured to receive the task instruction of a user, and complete path planning. The environment sensing module is configured to collect and process the information of a surrounding environment. The decision and control module is used for making a decision and issuing a control instruction. The power module is used for providing power. The execution module provides two driving modes, automatically switches to a driver operating mode when the scooter carries the user, and automatically switches to an automatic driving mode when the scooter does not carry the user. The ride module is used for the riding of the user. The automatically driven electric scooter can automatically drive to the user's position, automatically switches to the driver operating mode after the user rides the electric scooter and then is driven bythe user to a destination.

The invention discloses an active vehicle continuous tracking and positioning system and method based on multi-data fusion. A vehicle tracking detection sensor of the system performs tracking detection on a vehicle; collected information is sent to a roadside service platform to be processed, so that vehicle preliminary data information is obtained; the vehicle preliminary data information is fused with regional map data, so that vehicle real-time dynamic information and a unique ID number can be generated; the vehicle enters a license plate snapshot triggering area; a vehicle feature recognition device acquires feature information of the vehicle, sends the feature information to the roadside service platform and calls a vehicle type and three-dimensional contour dimension data corresponding to the feature information, wherein the vehicle type and three-dimensional contour dimension data are pre-stored in a database; and the roadside service platform fuses the real-time dynamic information and the feature information of the vehicle and the Beidou\GPS clock time service information to generate complete vehicle identity information, starts physical space attributes to perform trajectory correction, and continuously outputs vehicle tracking and positioning data. According to the system and method of the invention, the vehicle running on the road can be continuously tracked and positioned without installing positioning equipment on the vehicle.

Provided are a modularized automatic driving control device for a paddy planter and a control method thereof. The modularized automatic driving control device includes an operation management terminalsystem, a navigation positioning system, a main control system, a wireless communication management system, a steering control and execution system, a speed control and execution system and a gear control and execution system. The device facilitates flexible configuration and selection by users according to actual conditions, the paddy planter can automatically generate a walking path without inputting the size of sown land in a complex paddy field environment, and centimeter-level precise straight line, curve and turning, forward and backward automatic driving and automatic operations are provided according to a predetermined track. The paddy planter can automatically walk, steer and operate in complex paddy field environments with different terrains and landforms in 24 hours.

The embodiment of the invention presents a driving planning method and device based on a road side unit, a road side unit and a storage medium. The method comprises the following steps: determining apre-selected path for a target vehicle according to the vehicle information of the target vehicle, wherein the target vehicle is a vehicle within the communication range of a road side unit; acquiringobstacle information corresponding to the pre-selected path according to the sensing data of sensors, and generating a dynamic map for the target vehicle according to the pre-selected path and the obstacle information; carrying out path planning and speed planning for the target vehicle according to the dynamic map to generate planned trajectory information; and determining the target trajectoryinformation of the target vehicle according to the planned trajectory information. According to the method in the embodiment of the invention, the path and speed of the target vehicle are planned based on the road side unit, and the information of obstacles such as pedestrians is considered in the planning process and added to the dynamic map, so that automatic driving of the target vehicle can berealized or driving decision service can be provided for the driver of the target vehicle.