1685 results about "Smart vehicle" patented technology

An on-board intelligent vehicle system includes a sensor assembly to collect data and a processor to process the data to determine the occurrence of at least one event. The data may be collected from existing standard equipment such as the vehicle communication bus or add-on sensors. The data may be indicative of conditions relating to the vehicle, roadway infrastructure, and roadway utilization, such as vehicle performance, roadway design, roadway conditions, and traffic levels. The detection of an event may signify abnormal, substandard, or unacceptable conditions prevailing in the roadway, vehicle, or traffic. The vehicle transmits an event indicator and correlated vehicle location data to a central facility for further management of the information. The central facility sends communications reflecting event occurrence to various relevant or interested users. The user population can include other vehicle subscribers (e.g., to provide rerouting data based on location-relevant roadway or traffic events), roadway maintenance crews, vehicle manufacturers, and governmental agencies (e.g., transportation authorities, law enforcement, and legislative bodies).

Devices, systems, and methods are disclosed for identifying a driver versus a passenger within a smart vehicle. This involves a determination of the relative positions of the wireless communication devices within the smart vehicle using near-field communication (NFC) or GPS, AGPS, etc. The wireless communication device detected closest to the driver seat is assumed to be the device owned by the driver. Once identified, the driver can be billed for tolls and other road services, based on the location of the smart vehicle. For instance, as the smart vehicle approaches a toll, a notification can be sent to all of the wireless communication devices. A response from a particular wireless communication device will result in the corresponding user's account being billed for the toll. Further, the smart vehicle can communicate with near-field transceivers placed, for instance, alongside a High-Occupancy Vehicle (HOV) lane. A driver of the vehicle can be billed, fined, or ticketed based upon a determination of an absence of passengers in the smart vehicle.

The invention discloses an intelligent vehicle passable area detection method based on multi-source information fusion, and the method comprises the steps: S100, collecting obstacle target informationaround a vehicle detected by a vehicle-mounted sensor, and outputting a static obstacle target library; S200, receiving obstacle target information around the vehicle, carrying out time-space synchronization on the obstacle target information detected by the vehicle-mounted sensor, carrying out single-frame target fusion on all detected obstacle information around the vehicle, carrying out continuous inter-frame multi-target tracking by utilizing motion prediction and multi-frame target association, and outputting a dynamic obstacle target library; And S300, receiving the static obstacle target library and the dynamic obstacle target library output in the step S200, and updating the dynamic obstacle target library according to the information of the static obstacle target library to formreal-time obstacle target information and generate a passable area. The position, scale, category and motion information of the obstacle around the vehicle and the binarization rasterized map can be accurately obtained in the vehicle driving process, the motion track of multiple targets is tracked, and the intelligent vehicle passable area including the binarization rasterized map and dynamic obstacle information real-time updating is formed.

Provided is an integrated telematics service system that may operate as an essential network interoperating gateway in a smart vehicle appropriate for a ubiquitous environment, and that includes: a network interface unit that receives a user input to process the user input based on an ontology modeling for the integrated telematics service, and interoperates with an external network of the smart vehicle; a knowledge based management unit that interoperates with the network interface unit to manage a policy and a schedule for a telematics service, an event occurring in the smart vehicle, and a schedule of a user; and a service unit that converts information associated with a navigation service or a multimedia service to a form suitable for an internal device of the smart vehicle, to perform a one-source-multi-use function.

A vehicle sun visor system with a touch screen display is configured to display video feed from one or more cameras. A front facing polarized and / or photochromic camera shows the area of view which is normally blocked by the deployed sun visor, allowing the user to view traffic lights, road signs, etc. without the distraction of glare. Software image processing may also be used to reduce glare and improve visibility. In addition, the sun visor system also has a “see-me” camera which allows the user to use the screen as a mirror, and one or more rear-view cameras which can be used to see the passenger area of a vehicle through the touch-screen display. Any of the cameras may be used to take photos or videos, which may be viewed on the display and transmitted wirelessly to other electronic devices or cloud storage.

The present invention provides a local trajectory planning method and apparatus for a smart vehicle, pre-acquiring path planning information from a starting location to a destination; the method comprising: determining a target lane; sampling alternative curves from a current location of the smart vehicle to a target lane according to the path planning information; performing speed planning for the sampled alternative curves according to a current travel environment; selecting one of the alternative curves after the speed planning is performed as a target trajectory. Local trajectory planning of the smart vehicle is achieved through the present invention.

An emotive advisory system for use by one or more occupants of an automotive vehicle includes a computer configured to receive input indicative of an operating state of the vehicle. The computer determines at least one of a need to provide owner's manual (or maintenance) information to an occupant based on the operating state of the vehicle and a request to provide owner's manual (or maintenance) information to the occupant. The computer generates (i) data representing an avatar having an appearance and (ii) data representing a spoken statement for the avatar. The spoken statement provides owner's manual (or maintenance) information to the occupant in spoken dialog based on at least one of the need and the request. The data representing the avatar is output for visual display, and the data representing the statement for the avatar is output for audio play.

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 relates to an obstacle identification method for smart vehicles. The obstacle identification method includes the following steps that: 1) data points of original scanning point cloud three-dimensional laser radar of surrounding environment of the vehicles under a spherical coordinate system are obtained, and obstacle points are screened out from all the data points; 2) the obstacle points are grouped according to the horizontal azimuth angles of the obstacle points and the radial distances of the obstacle points relative to a three-dimensional laser radar sensor; and 3) each group of obstacle points correspond to one obstacle, and the categories of the obstacles can be obtained according to the relative position relationships of the obstacle points in each group. Compared with the prior art, and according to the obstacle identification method for the smart vehicles of the invention, the intrinsic unity of the measurement principles of the a three-dimensional laser radar and a point cloud data spherical coordinate representation method is utilized; it is point cloud data that are analyzed based on spherical coordinates, and the Cartesian coordinates of the point cloud data are not analyzed, and therefore, high efficiency can be realized; and at the same time, the original data of point cloud are directly analyzed, and grid division is not needed to perform on the point cloud, and therefore, processing efficiency can be improved.

The invention belongs to the field of deep learning and intelligent vehicle road detection, and specifically relates to a vehicle detection method based on improved YOLOv3. The method comprises the following steps: redesigning a convolutional neural network structure between a Darknet layer and three yolo layers, and designing a YOLO-TN network by referring to an idea of TridentNet weight sharing;carrying out model pruning on the YOLO-TN convolutional neural network; constructing a vehicle detection data set, and labeling vehicle position information in the data set; respectively training vehicle detection models based on the YOLO-TN and the YOLOv3, completing a vehicle detection task, and comparing detection results of the YOLO-TN and the YOLOv3. The method has high average precision while guaranteeing real-time detection, and is lower in omission ratio and more accurate in positioning when used for detecting distant vehicles and small-scale targets.

The invention makes a request of protecting an intelligent vehicle automatic driving system and method in cooperation with an intelligent parking lot. Intelligent vehicle-mounted equipment comprises a communication module, a vehicle positioning and path planning module, and a detection module. A background service center consists of a communication module and a data management module. The communication module includes a dispatcher part and a service Handler part. A user mobile terminal sends request information of driving into or driving out of a parking lot to the background service center; the background service center sends a parking lot map and a designated terminal position to the vehicle-mounted equipment; the vehicle-mounted equipment carries out global path planning, collects vehicle station and environment information for positioning, plans a local path to control an intelligent vehicle to drive to a terminal point automatically, and sends terminal point arrival information to the background service center; and the background service center sends the terminal point arrival information to the user mobile terminal.

Presented are intelligent vehicle systems and control logic for predictive charge planning and powertrain control of electric-drive vehicles, methods for manufacturing / operating such systems, and electric-drive vehicles with smart charge planning and powertrain control capabilities. Systems and methods of AI-based predictive charge planning for smart electric vehicles use machine-learning (ML) driver models that draws on available traffic, location, and roadway map information to estimate vehicle speed and propulsion torque requirements to derive a total energy consumption for a given trip. Systems and methods of AI-based predictive powertrain control for smart hybrid vehicles use ML driver models with deep learning techniques to derive a drive cycle profile defined by a preview route with available traffic, geopositional, geospatial, and map data. ML-generated driver models are developed with collected data to replicate driver behavior and predict the drive cycle profile, including predicted vehicle speed, propulsion torque, and accelerator / brake pedal positions for a preview route.

The present invention relates to a smart vehicle identification device that has means to determine the identity of vehicles on city streets and highways. The smart vehicle identification device comprises of 1) an interrogator in the form of a radiofrequency (RF) reader; 2) wireless transceiver, modem and communication ports that serve as communication means; 3) a central processing unit comprising of a processor and memory chip that determines and controls the functioning of the smart vehicle identification device. A multitude of smart vehicle identification devices are placed strategically along highways and city streets; and each smart vehicle identification device communicates with a central control station to form a network. Transponders; comprising of radiofrequency (RF) tags; are mounted on vehicles and contain vehicle identification information. The RF reader of each smart vehicle identification device has means to interrogate the RF tag of vehicles passing through its corresponding interrogation zone on highways and city streets. Vehicle identification information thus obtained is transmitted to the central control station. Suspect vehicle identification information is entered into the computer system at the central control station; which has means to match the entered suspect vehicle identification information with the vehicle identification information obtained from the smart vehicle identification devices in its network; and determine if a suspect vehicle has been identified by a smart vehicle identification device in its network. Law enforcement officials are alerted if a suspect vehicle is identified.

The invention relates to the safe auxiliary driving and intelligent control filed and discloses an automatic control system and a method for preventing side-slipping and side-turnover in a curve road. A vehicle-mounted automatic control system is adopted to control an intelligent vehicle. At first, information about curve road curvature is obtained; secondly, the information about curve road curvature is converted into digital signals and input into a vehicle-mounted micro-processor, curve road critical safe driving speed is calculated by a safe driving speed calculation module and current driving speed is measured by a vehicle-mounted sensor; then the current driving speed and the critical safe driving speed are judged by a safe condition judging module; and finally a system automatic control module is used to control the intelligent vehicle to pass through the curve road smoothly. The automatic control system and the method for preventing side-slipping and side-turnover in the curve road overcome the shortcoming that trajectory tracking is achieved by only using a vehicle kinematics controller, a designed vehicle dynamics controller guarantees straightaway automatic deceleration and practicability and instantaneity of maintenance in the curve road, and calculation accuracy of safe driving speed is improved. By means of dynamics control principles including equivalent control and switching control, the system chattering phenomenon can be restrained effectively and influence of external disturbances can be overcome.

Devices, systems, and methods are disclosed for identifying a driver within a vehicle using short range wireless communication in order to ticket or alert the driver in response to a traffic infraction by the driver. In exemplary embodiments, a short range wireless communication device registers drivers of vehicles at a certain location. The registration captures a unique identifier for each driver at the location from the driver's wireless communication device. When a vehicle commits a traffic infraction, the unique identifier is used to reference a database to determine the identity and address of the driver. The driver may then be sent a notification of the infraction as well as payment options. This notification may be sent directly to the wireless communication device of the driver. In embodiments of the present invention, a smart vehicle acts as a proxy to capture the unique identifier from the driver's wireless communication device and communicates with the short range wireless communication device.

The invention provides a road traffic sign automatic identification and management system based on deep learning, wherein the system is used for the field of environment perception technology of a smart vehicle. The system comprises a traffic sign acquisition module, a traffic sign identification module and a traffic sign management module. The traffic sign acquisition module acquires a video which comprises the traffic sign and performs matching on each image frame and latitude-and-longitude of equipment in acquiring the image. The traffic sign identification module performs functions of processing the input image, performing positioning detection on the traffic sign, acquiring a candidate area which comprises the traffic sign, and performing classification identification on the traffic sign. The traffic sign management module transmits traffic sign and latitude-and-longitude information to a traffic management department, thereby determining whether placement of the traffic sign is reasonable and performing corresponding adjustment. The road traffic sign automatic identification and management system has advantages of large number of kinds of identified traffic signs, high precision, high real-time performance, etc. The road traffic sign automatic identification and management system further has beneficial effects of reducing effect of factors such as illumination change to image identification, improving interference resistance, and obtaining high identification accuracy and low error identification rate.

The invention discloses an intelligent automobile trace tracking control system and method based on active safety, and belongs to the field of intelligent automobile automatic driving. The control system comprises a trace tracking control unit based on model predictive control and a steer-by-wire unit with the active safety function; the trace tracking control unit can obtain the accurate position of an automobile and the steering angle of a steering wheel in real time, so that the attitude information of the automobile is obtained; the target front wheel steering angle of the automobile is calculated by combination with the target trace parameters, and the steer-by-wire unit achieves accurate control over a steering execution motor according to the target front wheel steering angle; and at the same time, the possible rollover risk of the automobile is predicted, active front wheel steering angle compensation control is conducted, and finally the trace tracking control over the automobile is achieved. By combination with a model predictive control theory and a steer-by-wire technology based on active safety, reliability of the intelligent automobile is ensured, and trace tracking control over the intelligent automobile during high-speed driving is achieved.

The invention discloses a distributed vision-based parking lot-vehicle cooperative intelligent parking system and method. The system comprises a parking lot service center, a vehicle-mounted device of an intelligent vehicle and a user mobile terminal, wherein the parking lot service center comprises a vehicle tracking module, a path planning module, a data management module and a communication module. The vehicle tracking module detects a vehicle object in a parking lot, obtains the accurate position of the vehicle object, and comprises a visual sensor set, a local tracker corresponding to each visual sensor and a global tracker. The path planning module plans the driving path according to the current position and the terminal point of the intelligent vehicle. The vehicle-mounted device comprises a vehicle control module and a communication module, wherein the vehicle control module controls the intelligent vehicle to automatically drive to the terminal point according to the received path planned by the service center. The user mobile terminal is used for sending request information about driving in / out of the parking lot to the parking lot service center. Automatic and intelligent driving in / out of a parking lot is realized.

The invention discloses a method for parking a shared bicycle and a system for locking the same. The method includes guiding users to park the shared bicycle in specified regions when the bicycle is returned by the users; monitoring the safety of the shared bicycle after the shared bicycle is parked; triggering a communication device and a GPS (global positioning system) to work by the aid of a vibration sensor; uploading state information to a data center; starting an alarm device to expel perpetrators who infringe the shared bicycle if the data center confirms that the shared bicycle is infringed at the moment via parking area equipment. The system for locking the bicycle comprises four-party equipment including the data center of cloud, user APP (application), a lock, a communication module and the parking area equipment. The user APP is arranged on a mobile phone of a user side, and the lock and the communication module are arranged on the shared bicycle. The method and the system have the advantages that the shared bicycle can be assuredly parked in place by the four-party equipment, and the safety of the parked shared bicycle can be guaranteed.

The invention belongs to the technical field of vehicle testing, and discloses a digital simulation testing device for an intelligent vehicle. The device is provided with computers, a simulation vehicle, a display, a network interface and a physical interface, wherein the simulation vehicle is connected to one computer through one interface, display equipment is electrically connected to one computer, the computers are connected to a network system through interfaces, and the intelligent vehicle can be subjected to simulation testing in a laboratory environment by utilizing the device. According to the device, the intelligent vehicle can be subjected to simulation testing in the laboratory environment in a non-operating environment, the emission of tail gas is avoided, and the device has the advantages of being accurate, fast, safe, repeatable, economical and environmentally friendly and has an irreplaceable effect in research, development, verification, test and inspection of the intelligent vehicle.

Presented are vehicle charging systems and control logic for provisioning vehicle grid integration (VGI) activities, methods for making / using such charging systems, and electric-drive vehicles with intelligent vehicle charging and VGI capabilities. A method of controlling charging operations of electric-drive vehicles includes a vehicle controller detecting if a vehicle is coupled to an electric vehicle supply equipment (EVSE), and determining if the vehicle's current mileage exceeds a calibrated mileage threshold. Responsive to the vehicle being connected to the EVSE and the vehicle's current mileage exceeding the calibrated mileage threshold, the controller determines the current remaining life of the vehicle's traction battery pack and the current time in service of the vehicle. The vehicle controller determines if the current remaining battery life exceeds a predicted remaining battery life corresponding to the current time in service. If so, the vehicle controller enables the traction battery pack to transmit electrical power to the EVSE.

A method of operation of a navigation system includes: identifying a first-device location for representing a smart vehicle; identifying a unintelligent-vehicle location associated with the first-device location, the unintelligent-vehicle location for representing an unintelligent vehicle; determining a smart vehicle data for representing the smart vehicle data from an environmental sensors of the smart vehicle; and generating with a vehicle control circuit, an area profile for the unintelligent-vehicle location, based on the smart vehicle data for representing geographic relationship between the unintelligent vehicle and the smart vehicle, a further vehicle, or a combination thereof.

The invention discloses an urban traffic scene image understanding and multi-view crowd intelligent optimization method, which utilizes intersection driving path prior modeling of road layout random variables and a road surface semantic prior modeling method based on an FCN learning network to improve the cognitive precision of an intersection driving path and a road surface and the semantic understanding degree of the whole scene. Cognitive-driven priori model and data-driven two-dimensional model Candidate box semantic features of three-dimensional space transformation are combined with a deep neural network to realize complex traffic scene three-dimensional target detection and recognition; The method comprises the following steps of: estimating and describing a three-dimensional sceneflow for a complex road environment such as an intersection traffic scene by cooperatively considering a vehicle position posture and driving track prior model, and comprehensively characterizing theposture and motion trend of a traffic participant in the scene; Aiming at the urban complex intersection road section environment, the holographic understanding of the traffic scene is realized through multi-view crowd-sourcing optimization, the traffic environment understanding is effective and easy to realize, and a decision basis is provided for the autonomous control of the intelligent vehicle.

The invention provides a split-screen display method and electronic equipment. The invention relates to the fields of human-computer interaction, equipment screen projection, intelligent vehicle-mounted systems and the like. The method comprises the steps that the electronic equipment displays a first display interface of a first application, wherein the first application has a navigation function; the electronic equipment controls the vehicle-mounted system to display a first display interface of the first application; the electronic equipment detects a first input operation; the electronic equipment responds to the first input operation, switches the first application to the background for running, and displays a second interface; and the electronic equipment controls the vehicle-mountedsystem to perform split-screen display, so that a first display area on a display screen of the vehicle-mounted system displays a first display interface of the first application, and a second display area on the display screen displays a second interface. In the scheme of the invention, if the application (such as the map application) with the navigation function on the electronic equipment is switched to the background, the foreground of the vehicle-mounted system can still display the map application for a driver to check, so that the driving safety is improved.

The invention discloses a system and method for monitoring and early warning of high-threat vehicles, and belongs to the field of smart vehicle safety early warning. The system comprises an information identification module, a data communication module, an information processing and determining module and an early warning prompting module. The existence of high-threat vehicles is determined by real-time monitoring license plate number information, vehicle speed information and vehicle distance information of front and trailing vehicles to notify the vehicle drivers to decelerate and avoid high-threat vehicles, reducing traffic accidents. Vehicle driving habit information, such as regulation violation historical information, accident processing historical information and vehicle model information, can be obtained according to identified license plate number information. Whether vehicles in the surrounding are high-threat vehicles is comprehensively determined in combination with vehicle speed and vehicle distance information. The determination method is simple and easy to realize, thereby advancing the early-warning time, and lowering accident occurrence probability.

The invention provides an intelligent vehicle-mounted communication informatization system based on a 3-generation (3G) technology and a cloud system. The intelligent vehicle-mounted communication informatization system comprises a master control module, a wireless communication module, a positioning module, a sensor module and other functional modules, wherein the master control module comprises an advanced Risc machine (ARM)-based micro controller which is used for coordinatively controlling other modules of the system, and an intelligent embedded operating system; the wireless communication module is a wireless access module for accessing the system to the Internet based on various 3G technologies and is electrically connected with the master control module; the positioning module is a module for supplying a positioning function to the system based on positioning systems, such as a global positioning system (GPS), a beidou positioning system and the like, and is electrically connected with the master control module; the sensor module is a module for supplying a theftproof function based on an ultrasonic sensing technology and is electrically connected with the master control module; and other functional modules are modules for realizing main functions of the system. The invention also provides a communication method applied to the system. The system has the characteristics that: the GPS navigation speed is higher, the cloud system can be widely applied, and the whole vehicle-mounted system is higher in intelligentization level.

The invention provides a method for establishing a smart vehicle control model and a smart vehicle control method and device. The method for establishing a smart vehicle control model comprises steps of: acquiring sample data including steering wheel turning angles corresponding to various driving environments; extracting a vehicle state characteristic and a road condition from the sample data; training a neural network model from the extracted characteristic to obtain the smart vehicle control model. The smart vehicle control method comprises steps of: extracting the vehicle state characteristic and the road condition of a vehicle to be controlled; inputting the extracted characteristic into the smart vehicle control model to obtain the steering wheel turning angle; and controlling the vehicle to be controlled by using the steering wheel turning angle. The method for establishing a smart vehicle control model employs a machine learning way, prevents manual parameter regulation, and reduces labor cost due to parameter regulation.

The invention provides a multi-intelligent-vehicle intersection traffic coordination control method in a vehicle-road coordination environment. The method comprises the following steps: 1, establishing a traffic right division model; 2, establishing a vehicle trajectory and signal timing overall optimization model; 3, establishing an overall control model according to the passage right division model and the vehicle track and signal timing overall optimization model. According to the multi-intelligent-vehicle intersection traffic coordination control method in a vehicle-road coordination environment, through establishing traffic right distribution model, a signal timing model and a vehicle track optimization model, a set of theoretical algorithm used for intersection overall control in thevehicle-road cooperation environment is established, quantitative analysis is further carried out on the control effects of different control algorithms under different conditions by setting four sets of simulation experiments, and the significant effect of the algorithm provided by the invention on intersection overall control in the vehicle-road cooperation environment is verified.