113 results about "Advance driver assistance system" patented technology

A system and method are provided for driving assistance. The system includes an image capture device configured to capture an actual image relative to an outward view from a motor vehicle and depicting an object. The system further includes a processor configured to render, based on a set of 3D CAD models, synthetic images with corresponding intermediate shape concept labels. The processor is further configured to form a multi-layer CNN which jointly models multiple intermediate shape concepts, based on the rendered synthetic images. The processor is also configured to perform an intra-class appearance variation-aware and occlusion-aware 3D object parsing on the actual image by applying the CNN to the actual image to output an image pair including a 2D and 3D geometric structure of the object. The processor is additionally configured to perform an action to mitigate a likelihood of harm involving the motor vehicle, based on the image pair.

The invention discloses a vehicle lane-changing path tracking control method based on model prediction, and belongs to the technical field of intelligent vehicle control. The vehicle lane-changing path tracking control method is applied to an advanced driver-assistance system of a vehicle and comprises the steps of establishing an expected lane-changing path model based on obverse and reverse trapezoid yaw angle acceleration, performing force analysis on a lane-changing vehicle, establishing a 3-DoF vehicle dynamic model, converting the nonlinear 3-DoF vehicle dynamic model into a discrete linear prediction model, designing an objective function and constraint conditions of a model prediction controller, and calculating and outputting a physical quantity for controlling the motion of the vehicle according to an expected path. The expected lane-changing path planned according to the vehicle lane-changing path tracking control method improves the comfort of a driver. Control quantities comprise a driving force and a front wheel steering angle of vehicle driving so as to ensure high-precision vehicle speed control while satisfying the lateral lane-changing requirements. The robustnessof control tracking is high, and the control precision is high, so that lateral tracking errors can be effectively reduced.

The invention provides an automatic driving expected function safety hazard assessment method based on zero-day loopholes, which comprises the following four steps of: 1, determining a zero-day vulnerability hazard map model of an expected function safety system; 2, simplifying a zero-day vulnerability model of the expected function security system, and constructing a hazard path threatening the expected function security; 3, respectively calculating hazard values SK and SUK of a known trigger event and an unknown trigger event through a calculation program based on the hazard path; and 4, calculating an expected function safety system safety value svs based on the dynamic weight scheme. Hazard assessment of expected function safety and zero-day vulnerability safety assessment are combined, a solution for improving the expected function safety is invented based on an information safety solution, and the expected function safety hazard detection rate of an advanced driving assistance system and an automatic driving system is improved.

The invention discloses a target object detection method and a corresponding detection device, relates to the field of wireless communication, and can solve problems of low target object detection result accuracy and the like caused by mutual interference between radar detection devices in the prior art. The method is characterized in that each detection device transmits a radio signal in the determined frequency band capable of avoiding mutual interference so that interference of the transmitted signal or a related signal of any detection device on the target object determined by other detection devices is avoided. Furthermore, the frequency band is divided according to the determined threshold value, the frequency bands are allowed to be partially overlapped, frequency resources can be effectively utilized, frequency domain resource waste caused by complete separation of the sweep frequency bands of the multiple detection devices in the frequency domain is avoided, high anti-interference performance is achieved with low frequency resource cost, and in addition, radar communication of more purposes can be supported. The method is advantaged in that the ADAS capability of an automatic driving or advanced driving assistance system of the automobile is improved, and the method can be applied to the Internet of Vehicles, such as vehicle external V2X, inter-vehicle communication long-term evolution technology LTE-V, vehicle-vehicle V2V and the like.

The invention provides an automatic driving data collecting and forwarding device and method. The device comprises a logic circuit module and also comprises a video deserializer, a video serializer, avideo compression processor and an Ethernet transceiver, wherein the video deserializer, the video serializer, the video compression processor and the Ethernet transceiver are connected to the logiccircuit module. The method comprises the following steps: receiving first video data sent by a vehicle-mounted camera and carrying out format conversion on the first video data; synchronously copyingthe first video data into at least two pieces of second video data, performing format conversion on one piece of second video data, and sending the second video data to an advanced driving assistancesystem; encoding and compressing the other part of the second video data, and sending the encoded and compressed second video data to a computer; receiving first Ethernet data of an Ethernet sensor; and synchronously copying the first Ethernet data into at least two parts of second Ethernet data, and respectively sending the at least two parts of second Ethernet data to the advanced driving assistance system and the computer.

The embodiment of the invention provides a vehicle upgrading method and device, and the method comprises the steps that a server determines at least two part groups in a vehicle, and each part group comprises an upgrading control part which is used for controlling a part in the part group to carry out OTA upgrading; the server generates a first upgrade package for a first component group in the at least two component groups, and an upgrade control component of the first component group is a first upgrade control component; and the server sends the first upgrade package to the first upgrade control component, wherein the first upgrade package is used for upgrading components in the first component group. By adopting the embodiment of the invention, the vehicle upgrading efficiency can be improved, and the vehicle stability is improved. The scheme can be further used for improving the ADAS capability of an automatic driving or advanced driving assistance system, and can be applied to the Internet of Vehicles, such as vehicle external V2X, inter-vehicle communication long-term evolution technology LTE-V, vehicle-vehicle V2V and the like.

In some examples, one or more characteristics of one or more driving scenes may be obtained. Based at least on the one or more characteristics, one or more behaviors of a simulated driver may be simulated via a machine learning model. An operation associated with one or more advanced driving assistance system (ADAS) functions may be performed based at least on the simulated one or more behaviors.

The invention relates to a virtual lane line construction method and system depending on a following target, and the method comprises the following steps: judging whether a current lane line cannot beobtained by a camera or not, extracting all target detection information from a sensing result if the current lane line cannot be obtained by the camera, or else, carrying out the continuous judgment; calculating an initial target deviation of each target according to a pre-established sensing coordinate system; calculating the deviation compensation amount of each target; according to the initial target deviation and the deviation compensation amount of each target, calculating the target deviation of each target after deviation compensation; determining a drivable area between the vehicle and the following target according to the distance of the target center point relative to the origin of the sensing coordinate system and the target deviation of each target, and selecting the following target in the drivable area; and constructing a virtual lane line based on the following target center point and the vehicle center point. The method can be widely applied to the technical field ofadvanced driving assistance systems.

The invention discloses a vehicle safety control method, device and system. The method, the device and the system are used for solving the problem that a vehicle is out of control due to backbone network communication faults. The method comprises the steps that the communication state of a CAN-FD backbone network of a vehicle is monitored, wherein the backbone network is used for transmitting a driving control instruction, and the driving control instruction is used for controlling the motion state of the vehicle; when the communication state of the backbone network is abnormal, motion state information of the vehicle and information of a lane where the vehicle is located is acquired; a target driving control instruction is generated according to the motion state information of the vehicleand the information of the lane where the vehicle is located, wherein the target driving control instruction is used for controlling the vehicle to decelerate to a preset safe vehicle speed in the driving lane; and a target driving control instruction is transmitted through a chassis controller area network (CAN) which is in direct communication connection with the advanced driving assistance system. According to the scheme, after abnormal communication of the backbone network is monitored, vehicle safety control is directly achieved through the CAN, the probability of traffic accidents caused by out-of-control of the vehicle is reduced, and the vehicle control safety is improved.

A method is provided in an Advanced Driver-Assistance System (ADAS). The method extracts, from an input video stream including a plurality of images using a multi-task Convolutional Neural Network (CNN), shared features across different perception tasks. The perception tasks include object detection and other perception tasks. The method concurrently solves, using the multi-task CNN, the different perception tasks in a single pass by concurrently processing corresponding ones of the shared features by respective different branches of the multi-task CNN to provide a plurality of different perception task outputs. Each respective different branch corresponds to a respective one of the different perception tasks. The method forms a parametric representation of a driving scene as at least one top-view map responsive to the plurality of different perception task outputs. The method controls an operation of the vehicle for collision avoidance responsive to the at least one top-view map indicating an impending collision.

The invention relates to the technical field of vehicle infrastructure cooperation, and discloses a vehicle early warning method, a vehicle infrastructure cooperative system and a storage medium. Thevehicle early warning method comprises the following steps that the early warning information of a local vehicle is acquired, and the early warning type of each early warning information is identified; according to the early warning type and a presupposed mapping relation, the early warning type scoring of the early warning information is obtained; according to the early warning type, a relative motion parameter between the local vehicle and a hazard source in the early warning information is acquired, and the early warning risk scoring of the early warning information is calculated accordingto the relative motion parameter; the number of vehicles in the surrounding area of the local vehicle is detected, and the vehicle density is calculated according to the number of vehicles; the earlywarning weight value of the early warning information is calculated according to the early warning type scoring, the early warning risk scoring and the vehicle density; and the early warning information, conforming to the early warning condition, of the early warning weight value is selected and output. According to the vehicle early warning method, the effective early warning can be accurately selected for alarming, the early warning accuracy is improved, and the interference of an early warning system to a driver or an advanced driving auxiliary system is reduced when multiple early warningsoccur simultaneously.

The invention belongs to the field of vehicle electronics and provides an HUD data display method and device for intelligent navigation. The method comprises the following steps: acquiring forward senior driving assistance system information and front collision prevention alarm information; acquiring road early-warning information and 360-degree look-around provided blind region early-warning information; acquiring vehicle early-warning information and navigation information; displaying the forward senior driving assistance system information, front collision prevention alarm information, road early-warning information, 360-degree look-around provided blind region early-warning information, vehicle early-warning information and navigation information through HUD. The technical scheme provided by the invention has the advantage of high safety.

The embodiment of the invention provides a secure access method and device, applied to the fields of communication technology and network connection vehicles, and the method comprises the steps: receiving a first message from a second node, the first message comprising a first cipher text, and the first cipher text being obtained according to a security parameter and a first secret key negotiation parameter; decrypting the first cipher text according to the security parameter to obtain a first key negotiation parameter; determining a first shared key according to the first key negotiation parameter and a key negotiation algorithm; and obtaining first identity authentication information according to the first shared key and the PSK between the first node and the second node, wherein the first identity authentication information is used for authenticating the identity of the first node. Through the embodiment of the invention, the node can be prevented from being successfully associated with an attacker with an incredible identity. The scheme can be further used for improving the ADAS capability of an automatic driving or advanced driving assistance system, and can be applied to the fields of Internet of Vehicles V2X, inter-vehicle communication long-term evolution technology LTE-V, vehicle-to-vehicle V2V and the like.

A system and method are provided for driving assistance. The system includes an image capture device configured to capture an actual image relative to an outward view from a motor vehicle and depicting an object. The system further includes a processor configured to render, based on a set of 3D CAD models, synthetic images with corresponding intermediate shape concept labels. The processor is further configured to form a multi-layer CNN which jointly models multiple intermediate shape concepts, based on the rendered synthetic images. The processor is also configured to perform an intra-class appearance variation-aware and occlusion-aware 3D object parsing on the actual image by applying the CNN to the actual image to output an image pair including a 2D and 3D geometric structure of the object. The processor is additionally configured to perform an action to mitigate a likelihood of harm involving the motor vehicle, based on the image pair.

An apparatus (1) for calibrating an ADAS sensor of a vehicle (9) comprises: a base unit (2) including a plurality of wheels (20); a support structure (3) integral with the base unit (2); a vehicle calibration assistance structure (4), mounted on the support structure (3) and including a calibration device (41, 42) configured to facilitate aligning or calibrating the ADAS sensor; a position detector, configured to capture values of a position parameter representing a position of the support structure (3) relative to the vehicle (9); a processing unit, configured to process the values of the position parameter in real time to derive information regarding an actual position of the support structure (3) relative to the vehicle (9).

The invention provides a pixel type headlamp control system and method and a vehicle. The pixel type headlamp control system comprises a vehicle body controller, an advanced driving assistance systemand a headlamp control module, wherein the vehicle body controller is used for collecting state information of the vehicle; the advanced driving assistance system is used for collecting traffic information of the road surface in front of the vehicle; and the headlamp control module is connected with the vehicle body controller, the advanced driving assistance system and the pixel type headlamp, and the headlamp control module is used for controlling the pixel type headlamp according to the vehicle state information and the traffic information of the road surface in front of the vehicle. According to the invention, the pixel type headlamp can be automatically controlled with extremely fine resolution according to different traffic conditions and scenes, and corresponding reminding marks canbe projected for specific scenes, so that the night driving safety is improved. In addition, natural switching between high beams and low beams can be ensured, and the visual fatigue of a driver is reduced.

The invention provides a brake lamp recognition method and device and electronic equipment, and the method comprises the steps of inputting a target image into a trained target detection network, andobtaining a plurality of feature maps with specified sizes, wherein the feature map of the specified size corresponds to a region of interest in the target image; inputting the feature maps of the specified sizes into a trained full convolutional neural network for taillight segmentation to obtain masks of the feature maps of the specified sizes, the masks indicating positions of taillights turnedon in the target image; and inputting the mask into a trained stop lamp identification network to obtain a classification result corresponding to the mask, the classification result representing whether a taillight turned on in the mask is a stop lamp. According to the application, the accuracy of identifying the area where the turned-on taillight is located is improved, so that the identification accuracy of the brake light can be improved, and the advanced driving assistance system is more helpful for improving the driving safety.

The invention discloses a parking space identification method using an all-around image. The method comprises the following steps of: firstly, preprocessing an all-around image, secondly, determining the position of a parking space corner point by adopting a double constraint condition of combining straight line detection with corner point detection, and finally, identifying the type and the position of a parking space by using a template matching method. According to the method, the error recognition rate of parking space recognition is reduced by means of double constraint conditions, and the method can be applied to advanced driving assistance systems such as automatic parking.

An embodiment of the invention discloses a test system and method for a vehicle advanced driving assistance system. The method comprises the steps that: collection equipment collects driving data generated when a target vehicle and a test vehicle run, wherein the driving data have a collection time point; display equipment collects an ADAS signal generated by an ADAS of the test vehicle when the test vehicle runs, and correspondingly displays the ADAS signal and a time point at which the ADAS signal is generated; shooting equipment shoots the correspondingly displayed ADAS signal and the time point when the ADAS signal is generated, and sends a shot image to processing equipment; the processing equipment recognizes the image to obtain the ADAS signal and the time point at which the ADAS signal is generated; according to the ADAS signal generation time point and the driving data acquisition time point, time synchronization processing is performed on the driving data of the target vehicle and the test vehicle and the ADAS signal; and the ADAS is tested based on the driving data of the target vehicle after time synchronization processing, the driving data of the test vehicle and the ADAS signal.

An advanced driving assistance system (ADAS)-linked active hood apparatus for always-on operation is provided. The apparatus includes a rotary arm that is fixed to a hood of a vehicle, a rotary bracket configured to be rotated in conjunction with the rotary arm when rotation force is applied to the rotary bracket and a first link configured to interconnect the rotary bracket and the rotary arm. A motor unit is fixed to a vehicle body and applies rotation force to the rotary bracket. A controller is configured to receive driving information of the vehicle via an advanced driving assistance system (ADAS) and to set a pop-up height of the hood. The controller operates the motor unit to perform pop-up and restoration of the hood to an original position when a collision is expected based on the received driving information.

The present invention relates to a method for creating a traffic scene in a virtual driving environment. A method for executing a traffic scene-generating device comprises the steps of (a), in a statein which the driving data generated by using the preceding traffic data and detailed traffic data is acquired, extracting the driving environment information by inputting the driving data into a situation analyzer; extracting the vehicle state information for the autonomous vehicle by inputting the driving data to a vehicle information extractor to thereby generate the sequential traffic log based on the driving sequence, wherein the previous traffic data corresponds to the discrete traffic data extracted from an existing driving image through an image-based advanced driving assistance system, and the detailed traffic data corresponds to the sequential traffic data collected from the sensors of a data collection vehicle driven in an actual driving environment; and (b) inputting the sequential traffic log into a scene enhancement network.

The embodiment of the invention discloses pattern display equipment. The pattern display equipment is used for calibrating an advanced driving assistance system of an automobile, the pattern display equipment comprises a base, a plate-shaped display screen and a controller, the base is used for being connected with a calibration bracket, the calibration bracket is arranged at a preset position relative to the automobile when calibrating the advanced driving assistance system; the plate-shaped display screen is installed on the base and used for displaying a calibration pattern, the calibrationpattern is used for calibrating a driving assistance system of the automobile; and the controller is electrically connected with the plate-shaped display screen and is used for controlling the plate-shaped display screen to display the calibration pattern. In this way, the controller controls the plate-shaped display screen to display the calibration pattern, so that the quality of the calibration pattern is improved.

According to the antenna and the preparation method thereof, the millimeter wave sensor and the terminal provided by the embodiment of the invention, the gaps exist between the plurality of coupling branches and the microstrip feed line, so that a resonant structure (namely LC) is formed between the plurality of coupling branches and the microstrip feed line, and the antenna generates another resonance, so that the antenna can generate two resonance points; a larger bandwidth is realized, the range resolution of the millimeter-wave radar is improved, and the problem that the bandwidth of the existing antenna cannot meet the use of the millimeter-wave radar in long-distance and medium-distance scenes is solved. Furthermore, according to the method, the capability of an advanced driving assistance system (ADAS) of the terminal in automatic driving or auxiliary driving is improved, and the method can be applied to the Internet of Vehicles, such as vehicle external connection (V2X), inter-vehicle communication long term evolution (LTE-V), vehicle-vehicle (V2V) and the like.

The invention relates to the field of automobiles, and discloses a 360-degree panoramic advanced driving auxiliary system and an automobile. The system is characterized in that: two sensor integratedbodies are arranged outside a vehicle roof, wherein one integrated body is arranged at the front part of the vehicle roof, the other integrated body is arranged at the rear part of the vehicle roof, and the positions of a skylight and a luggage rack are reserved in the middle part. Through the sensor information processing calculation, a driving display screen picture is divided into three main pictures to be simultaneously displayed, and comprises a 360-degree panoramic high-altitude visual field picture, a first visual angle picture at the right front side, the left side and the right side,and a first visual angle picture at the right rear side, the left side and the right side; each picture is marked in red with the speed of the vehicle at a high speed that is closer to the vehicle andmay intersect with the vehicle; red indicates the object that is closer to the vehicle or that may collide the vehicle according to the driving trajectory, so that the driver pays attention and receives timely voice reminder; according to the 360-degree panoramic advanced driving auxiliary system, the driver obtains a large-range 360-degree panoramic high-altitude visual field picture, more comprehensive surrounding environment information is obtained, and the driving safety level is improved.

The invention discloses a voice reminding method, an advanced driving assistance system and a computer storage medium. The method comprises the steps of obtaining road condition information in real time, and determining a dangerous source in a preset range of a vehicle according to the road condition information, grading the dangerous source, and determining the grade of the dangerous source, and carrying out graded reminding on the dangerous sources according to the grades of the dangerous sources so as to carry out different-grade reminding on different grades of dangerous sources in real time. By means of the mode, corresponding reminding can be conducted on different kinds of dangerous sources in real time, and the driving safety is improved.

The invention provides a clutch control method and device, and a computer readable storage medium, and belongs to the field of vehicles. The control method comprises the steps of after a function of an advanced driving assistance system of the vehicle is activated, acquiring a four-wheel braking force provided by an electronic stabilization program system; determining brake master cylinder pressure equivalent to the four-wheel brake force; and controlling the state of a clutch based on the brake master cylinder pressure equivalent to the four-wheel brake force.

The invention relates to a brake control method and system, electronic equipment and a storage medium. The method comprises the steps that a vehicle control unit receives a first brake signal sent byan advanced driving assistance system, wherein the first brake signal includes a first brake force degree value, and the first brake force degree value is determined by the advanced driving assistancesystem based on first collected data; the vehicle control unit also receives a second brake signal sent by an electronic control brake system, wherein the second brake signal includes a second brakeforce degree value, and the second brake force degree value is determined by the electronic control brake system based on second collected data; and the vehicle control unit determines a target brakeforce degree value according to the first brake force degree value and the second brake force degree value, and sends an execution command to a motor controller according to the target brake force degree value. A braking signal source of the advanced driving assistance system is increased, and double-source control is adopted for the vehicle control unit so that running safety of the vehicle can be improved.

The invention discloses a pure electric vehicle emergency brake control method, a vehicle control unit and a control device, and relates to the field of vehicle emergency brake safety. The method comprises the steps that when handshaking with an advanced driving assistance system succeeds, sending a negative torque parameter to the advanced driving assistance system; receiving an effective negative torque request initiated by the advanced driving assistance system, responding and braking; after the preset time, sending the new negative torque capacity again, and receiving a new effective negative torque request and responding to for braking until a braking switching request is received; and when switching to request braking of the vehicle body electronic stability control system, controlling the advanced driving assistance system to set the braking energy recovery torque capacity of the vehicle body electronic stability control system to be zero, controlling the vehicle body electronicstability control system to perform mechanical braking, and stopping the crawling function. Mechanical braking is directly carried out during ESC braking, braking energy recovery is not carried out,and the potential safety hazard that emergency braking cannot be carried out due to the fact that the charging and discharging capacity of a battery is low is avoided.

An apparatus (1) for calibrating an ADAS sensor of an advanced driver assistance system of a vehicle (9), comprises a base unit (2); a support structure (3) connected to the base unit (2); a vehicle calibration assistance structure (4) including a first surface, wherein the first surface has a first combination of predetermined graphical features and can be associated with the support structure, so that the first surface, at an operating position, faces towards the service area (8); and a flexible panel roller assembly connected to the support structure and including a roller and a flexible target panel (40).

The invention discloses a method and device for testing the function of an advanced driving assistance system; the method comprises the steps: obtaining the road test data of a road test vehicle, andenabling the road test data to comprise CAN bus data and ADAS sensor data; and calculating the road test data according to a problem model, screening out problem data in the road test data, and generating a test result of the advanced driving assistance system function of the road test vehicle according to the problem data. When the functions of the advanced driving assistance system are tested, CAN bus data and ADAS sensor data are utilized, so that the utilization rate of the ADAS sensor data is increased, and the test result is more accurate.