147 results about "Advanced driver assistance systems" patented technology

A method is provided for optimizing the use of autonomous features of advanced driver assistance systems and the tracking thereof. For example, a vehicle may be equipped with several driver assistance systems in which a driver of the vehicle may be assisted. The vehicle may automatically change the number of active assistance systems or suggest to the driver one or more assistance systems to activate based on several factors, including poor driving on behalf of the driver or poor driving conditions due to weather or road quality. Statistics regarding the use of such advanced driver assistance systems may be monitored and tracked and stored on an onboard database or transmitted continuously or periodically to various entities. For example, the system may operate to allow an insurance company to track the driving performance and the use of the advanced driver assistance systems to update actuarial models to more accurately adjust rates.

A method and arrangement are described for manoeuvre generation for automated driving on a one-way road of a vehicle (e) hosting the arrangement, the host vehicle (e) further including one or more advanced driver assistance systems. A collision free reference trajectory for longitudinal and lateral movement of the host vehicle (e) is determined repeatedly, with a fix time interval, for allowing the host vehicle (e) to retain a desired velocity and maintain the host vehicle (e) in a preferred lane utilizing model predictive control and quadratic program formulation. A control scheme where the structured environment of the one-way road is exploited in order to linearly formulate collision avoidance constraints is utilized. Manoeuvre generation is performed through solving the quadratic program. The one or more advanced driver assistance systems are controlled to perform the generated manoeuvre.

The invention discloses an advanced driver assistance system. The advanced driver assistance system comprises a data collection module, a driver behavior analysis module, an early warning level adjustment module and an early warning module. The data collection module comprises a road information collection module and a driver information collection module, the driver behavior analysis module performs comprehensive assessment on data collected by the data collection module, and the early warning level adjustment module adjusts the early warning level of the early warning module. According to the advanced driver assistance system, the state of a driver is obtained by collecting and analyzing the behaviors and physical signs of the driver, the early warning level of the ADAS is dynamically adjusted in combination with real-time road conditions and weather conditions, and therefore the early warning timeliness of the ADAS can be effectively improved.

Embodiments described herein may provide a method for generating a three-dimensional vector model of the interior of a structure. Methods may include: receiving sensor data indicative of a trajectory; receiving sensor data defining structural surfaces within a structure; generating a three-dimensional point cloud from the sensor data defining structural surfaces within the structure; segmenting the three-dimensional point cloud into two or more segments based, at least in part, on the sensor data indicative of trajectory; generating a three-dimensional surface model of an interior of the structure based on the segmented three-dimensional point cloud with semantic recognition and labelling; and providing the three-dimensional surface model of an interior of the structure to an advanced driver assistance system to facilitate autonomous vehicle parking.

A computer-implemented method and system are provided for driving assistance. The system includes an image capture device configured to capture image data relative to an outward view from a motor vehicle. The system further includes a processor configured to detect and localize objects, in a real-world map space, from the image data using a trainable object localization Convolutional Neural Network (CNN). The CNN is trained to detect and localize the objects from image and radar pairs that include the image data and radar data for different driving scenes of a natural driving environment. The processor is further configured to provide a user-perceptible object detection result to a user of the motor vehicle.

A method for improving prediction results of advanced driver assistance systems of a vehicle includes obtaining map data including information about a road geometry in a proximity of the vehicle. A sensor means is assigned, sensing a surrounding of the vehicle. A virtual sensing means output is generated, corresponding to an output of the sensing means if the sensing means. The generation is based on a mathematical model of the sensing means. The surrounding of the vehicle is sensed, and a sensing means output is generated. The sensing means output is compared to the virtual sensing means output. Parameters of the mathematical model are modified, and the virtual sensing means output are generated and compared to the sensing means output. Map data is combined with information derived from the sensing means output to generate combined information, which is output for further processing.

A computer-implemented depth estimation method based on non-parametric Census transform with adaptive window patterns and semi-global optimization. A modified cross-based cost aggregation technique adaptively creates the shape of the cross for each pixel distinctly. In addition, a depth refinement algorithm fills holes within the estimated depth map using the surrounding background depth pixels and sharpens the object boundaries by exerting a trilateral filter to the generated depth map. The trilateral filter uses the curvature of pixels as well as texture and depth information to sharpen the edges.

Advanced driver assistance systems (ADAS) and methods for object detection such as traffic lights, speed signs, in an automotive environment, are disclosed. In an embodiment, ADAS includes camera system for capturing image frames of at least a part of surroundings of vehicle, memory comprising image processing instructions and processing system for detecting one or more objects in a coarse detection followed by a fine detection. Coarse detection includes detecting presence of the one or more objects in non-consecutive image frames of the image frames, where non-consecutive image frames are determined by skipping one or more frames of the image frames. Upon detection of presence of the one or more objects in coarse detection, fine detection of the one or more objects is performed in a predetermined number of neighboring image frames of a frame in which the presence of the objects is detected in coarse detection.

The invention claims a DSRC-based (dedicated short-range communications based) intelligent vehicle map fusion system and method; the system comprises a vehicle positioning module, a local map generating module, a DSRC module, an ADAS (advanced driver assistance systems) map interface, a target vehicle screening module and a map fusion module; the vehicle positioning module is used for acquiring position and attitude of a main vehicle, the local map generating module is used for generating a local map corresponding to the current position of the main vehicle according to data of a vehicular sensor, the DSRC module is used for receiving position, attitude and local map information issued by a target vehicle within a communication range, and transmitting the position, attitude and local mpa of the main vehicle itself, the ADAS map interface module is used for providing protocols and interfaces to access an ADAS map, the target vehicle screening module is used for screening a target vehicle on the same lane as the main vehicle, and the map fusion module is used for fusing the local map of the main vehicle and that of the screened target vehicle to generate an extended local map of the main vehicle. The DSRC-based intelligent vehicle map fusion system and method can provide multi-vehicle sensing capacity sharing to extend the ambient sensing range, helping improve intelligent vehicle assisted driving/automatic driving performance.

A heater system for resisting fog and ice buildup on advanced driver assistance cameras provides a chamber covering the camera lens and providing a transparent window through which the camera lens may be directed. A heating element communicates with an air gap between the lens and the transparent window and the periphery of the transparent window to provide heating of the transparent window without blocking an image received by the camera lens.

The invention relates to an apparatus and method for failure diagnosis and calibration of sensors for advanced driver assistance systems. The apparatus includes a measuring unit including two or more sensors mounted in a vehicle a storage for storing characteristic data of each of the two or more sensors, and a processor for selecting one of the two or more sensors as a reference sensor and for determining whether or not a failure of the other sensor to be diagnosed is detected and whether calibration thereof is required, on the basis of error covariance information of the reference sensor.

The disclosure provides systems and processes for applying neural networks to detect intrusions and other anomalies in communications exchanged over a data bus between two or more devices in a network. The intrusions may be detected in data being communicated to an embedded system deployed in vehicular or robotic platforms. The disclosed system and process are well suited for incorporation into autonomous control or advanced driver assistance system (ADAS) vehicles including, without limitation, automobiles, motorcycles, boats, planes, and manned and un-manned robotic devices. Data communicated to an embedded system can be detected over any of a variety of data buses. In particular, embodiments disclosed herein are well suited for use in any data communication interface exhibiting the characteristics of a lack of authentication or following a broadcast routing scheme—including, without limitation, a control area network (CAN) bus.

That present invention relates to an advanced driver assistance system, in particular to a lane shift early warning control method based on a 360-DEG circumferential image system; according to the self-crossing time TTLC and the distance DLC between self and lane, whether the vehicle deviates from the lane or not is judged, and combined with the lane width, whether the vehicle crosses the lane ordeviates from the lane is judged comprehensively, and a lane deviation warning is issued after the vehicle crosses the lane or deviates from the lane to remind the driver to control the vehicle to runnormally. The self-crossing time refers to the time required for the wheel center of the front wheel to travel to the lane on the same side; overrun time TTLC=distance D between wheel center of frontwheel and lane boundary/lateral deviation velocity VD. The distance between the vehicle and lane refers to the physical distance between the wheel center of the front wheel and the lane on the same side, which is calculated by the lane information collected by the front camera. As that LDW function is developed based on the 360-DEG circumferential view image system, the hardware cost brought by the LDW function can be directly saved and the cost is low.

The invention provides an ADASIS (advanced driver assistance systems interface specifications) extended information output device based on a safe driving map. The ADASIS extended information output device comprises a touch screen, a high-accuracy positioning sensor, a route planning module, a positioning matching module, a safe driving map information supply module and the safe driving map, wherein the touch screen is used for acquiring information of passing points on a route input by a driver; the route planning module is used for planning a driving route; the high-accuracy positioning sensor is used for sending the current positioning information of an automobile to the positioning matching module; the positioning matching module is used for reading lane-level road information from the safe driving map, acquiring position information of the automobile in the safe driving map in combination with received current positioning information of the automobile and sending the position information to the safe driving map information supply module; the a safe driving map information supply module is used for storing the lane-level road information; the safe driving map information supply module is used for sending the lane-level road information, the position information and the driving route to third-party applications through extended ADASIS based protocols.

The invention relates to a super-pixel based road image segmentation method, which belongs to the field of image processing and is mainly applied to automobile road driving. The road image segmentation method comprises the steps of performing over-segmentation on a road image by using SLIC super-pixels, proposing a method for detecting an under segmentation region based on the regional color maximum difference in allusion to a circumstance that the SLIC super-pixels are easy to have an under segmentation phenomenon in a thin strip region, and adding a new clustering center to correct the undersegmentation; then performing regional feature extraction based on Gabor filtering and an LAB color space; and performing re-fusion on the over-segmentation region through calculating the similaritybetween the regions on the basis of considering the spatial position adjacency of the regions, and achieving accurate segmentation for a road region under a complex environment. The super-pixel basedroad image segmentation method serves as an important basic link of a vehicle-mounted advanced driver assistance system, and has a good segmentation effect and real-time processing ability for complexurban environment road images.

A vehicle that provides an advanced driver assistance system (ADAS) recommendation function and a method of controlling the vehicle are provided. The vehicle includes a collection unit that is configured to collect behavior information of a driver and a controller that is configured to determine an advanced driver assistance system (ADAS) mode recommendable to the driver based on the collected behavior information and to output the determined ADAS mode.

The invention discloses a control system of an electric vehicle and the electric vehicle. The control system comprises a gateway, chassis CAN buses connected with the gateway, a battery management system (BMS) module used for managing power-on-off, charging-discharging and energy of batteries, a power electronic unit (PEU) module, a gear control module connected with the PEU module by the chassis CAN buses, a vacuum-pump control module connected with the PEU module by the chassis CAN buses and an advanced driver assistance system (ADAS) module connected with the PEU module by the chassis CAN buses, wherein the PEU module comprises a driving control unit connected to one of the chassis CAN buses and used for controlling a driving motor based on accelerator pedal signals and brake pedal signals, an on board charge (OBC) and a direct current to direct current unit (DC/DC); and the driving control unit, the OBC and the DC/DC are independent nodes of buses and share a hardwire wakeup signal line of the BMS module. The control system of the electric vehicle is capable of improving the safety and real-time performance of a network and decreasing the error rate of analysis on gear positions and the error rate of analysis on the boosting of the electric vehicle, thereby ensuring the running safety of the electric vehicle.

A system and method for setting a warning reference of an advanced driver assistance system are provided. The method includes receiving, by a controller, vehicle information based on a driving condition from a telematics terminal and calculating statistical data for each item of the vehicle information based on the collected vehicle information. In addition, the controller is configured to store the statistical data in a database and calculate at least one time series risk index based on statistical data and a computation weight table stored in the database. The time series risk index is then transmitted to the telematics terminal.

A system and computer-implemented method detect and act upon operator reliance to vehicle alerts. The system and method include receiving user profile data of an operator that includes a baseline of at least one driving activity aided by activation of an alert from a feature of an Advanced Driver Assistance System (ADAS). The system and method may include receiving historical ADAS alert frequency data including a history of at least one driving activity aided by activation of the alert from the ADAS feature. The system and method may compare the user profile data with the historical ADAS alert frequency data, determine a reliance level based upon the comparing, and set at least a portion of an operator profile associated with the operator with the reliance level. As a result, a risk averse driver, and/or proper responsiveness to vehicle alerts may be rewarded with insurance-cost savings, such as increased discounts.

The invention discloses a vehicle door control method and device and a vehicle. The method applies an advanced driver assistance system ADAS, and comprises the steps of receiving a vehicle door unlocking request transmitted by a body control module BCM; obtaining a moving track of a moving object in a preset first warning area of the vehicle according to the vehicle door unlocking request; judgingwhether the moving object has a risk of colliding with the vehicle door or not according to the intersection condition of the moving track and a preset second warning area of the vehicle door; and when it is judged that the moving object and the vehicle door have the collision risk, sending a door opening forbidding instruction to the BCM. According to the invention, the moving object which may cause risks when the vehicle door is opened is obtained, the moving track of the moving object is obtained, the risk of collision with the vehicle door is judged by analyzing the moving track, the vehicle door is reasonably controlled, and safety is improved.

Provided is a vehicle capable of: acquiring an image of a road in front of a vehicle in an autonomous driving mode; recognizing a lane line, a subject lane, and an obstacle on the acquired image of the road; determining whether the recognized obstacle is in a stationary state based on obstacle information detected by an obstacle detector; acquiring, if the obstacle in the stationary state exists on at least one of two subject lane lines constituting the subject lane, a width of the obstacle overlapping the subject lane; determining whether keeping of travelling on the subject lane is to be performed based on the acquired width of the obstacle overlapping the subject lane; performing a deflection control within the subject lane to avoid the obstacle in the stationary state if it is determined that the keeping of travelling on the subject lane is to be performed; and performing control of departure from the subject lane or deceleration control if it is determined that the keeping of travelling on the subject lane is not to be performed.

The invention relates to a platform-based advanced driver assistance system based on software definition. The system comprises a hardware infrastructure layer, a control layer, a data and algorithm layer, a platform-based complete vehicle signal interface layer and an application layer, wherein the control layer, the data and algorithm layer, the platform-based complete vehicle signal interface layer and the application layer are located above the hardware infrastructure layer. According to the system, in combination with a platform-based design idea, a software definition concept and a layering idea, all resources in the ADAS can be defined through software and managed in a platform-based computing environment of the ADAS, the flexible adjustment of hardware, the dynamic allocation of theresources and the programmable configuration of ADAS functions are achieved, an ADAS solution can be quickly made, and therefore the complete vehicle suitability and function scalability of the ADASare effectively improved.

Various implementations include an automotive imaging system that includes at least three cameras disposed on a vehicle and an electronic control unit (ECU) in electronic communication with the cameras. The three cameras have overlapping fields of view, and a processor of the ECU may be configured for generating at least three stereoscopic images from images captured by each pair of cameras and blending these stereoscopic images into one high quality panoramic image. These images provide a wider field of coverage and improved images, which improves the ability of the safety and advanced driver assistance systems of the vehicle to detect and identify potential collision hazards and conduct situational analyses of the vehicle according to certain implementations.