173 results about "Advance driver assistance system" patented technology

An advanced driver assist system (ADAS) includes a processing circuit and a memory storing instructions executable by the processing circuit. The processing circuit executes the instructions to cause the ADAS to: obtain, from a vehicle, a video sequence including a plurality of frames captured while driving the vehicle, where each of the frames corresponds to a stereo image including a first viewpoint image and a second viewpoint image; determine depth information in the stereo image based on reflected signals received while driving the vehicle; fuse the stereo image and the depth information to generated fused information, and detect at least one object included in the stereo image based on the fused information.

Systems and methods described herein include implementation of road surface-based localization techniques for advanced vehicle features and control methods including advanced driver assistance systems (ADAS), lane drift detection, passing guidance, bandwidth conservation and caching based on road data, vehicle speed correction, suspension and vehicle system performance tracking and control, road estimation calibration, and others.

A method and system of diagnosing a vehicle with a vehicle diagnostic system to provide repair recommendations includes connecting a vehicle diagnostic computer tool to a diagnostic port of a vehicle to be in communication with an electronic system of the vehicle and reading vehicle data information of the vehicle with the vehicle diagnostic computer, such as diagnostic trouble codes (DTCs). A diagnostic evaluation program is operable to detect whether particular electrical vehicle systems are present on the vehicle, such as safety systems including Advanced Driver Assistance Systems. The system may additionally receive information regarding damage to the vehicle, such as from a collision. The system includes a repair information database and a report generator program that is operable to generate a repair recommendation report, including for example based on the vehicle data information, the particular electrical vehicle systems determined to be present, and the damage to the vehicle.

The invention provides an open environment automatic driving danger early warning method and system based on the Internet of Things, and the method comprises the steps: a first sensor group disposed on a vehicle continuously monitors the condition of a driving path, and transmits the monitored condition information of the driving path to an intelligent auxiliary driving center; a second sensor group deployed on the vehicle continuously monitors the state of the driver and sends the monitored state information of the driver to the intelligent auxiliary driving center; and the advanced driving assistance system fuses the road condition information and the driver state information to form a danger evaluation coefficient, and performs graded early warning according to the danger evaluation coefficient. By means of the method and the corresponding system, the attention index of the driver can be monitored in real time, the early warning threshold value and strategy are dynamically adjusted according to the fatigue degree and the concentration degree of the driver, and personalized risk prompts are provided; the risk level is subdivided, early warning measures are changed from light to heavy, safety is ensured, excessive interference is avoided, and the driving experience is improved.

The present application provides a method and device for window occlusion detection, which belongs to the field of sensor technology and can be used for assisted driving and autonomous driving. The method includes: obtaining a first window echo intensity and a second window echo intensity, the first window echo intensity represents the reference window echo intensity, and the second window echo intensity represents the window echo intensity at the current moment; obtaining the detection parameters of the target point at the first moment and the detection parameters at the second moment, the detection parameters including the reflectivity and / or position coordinates of the target point; according to the first window echo intensity, the second window echo intensity, the detection parameters at the first moment and the detection parameters at the second moment, obtaining a window occlusion parameter, the window occlusion parameter is used to indicate the window occlusion state. This method improves the accuracy of lidar window occlusion detection, so as to improve the terminal's advanced driving assistance system (ADAS) capabilities in autonomous driving or assisted driving.

A lane hazard mitigation algorithm includes a sensor for detecting a first hazard in a host road lane and a second hazard in an adjacent road lane, a processor for determining a host lane mitigation including a host lane speed reduction in response to the first hazard and an adjacent lane mitigation including an adjacent lane speed reduction in response to the second hazard, the processor being further configured to generate a lane change control signal in response to the adjacent lane speed reduction being less than the host lane speed reduction and to generate a vehicle speed reduction control signal in response to the host lane speed reduction being less than the adjacent lane speed reduction, and a vehicle controller for controlling a host vehicle in response to the lane change control signal and the vehicle speed reduction control signal.

Techniques are disclosed for the implementation of machine learning model training utilities to generate models for advanced driving assistance system (ADAS), driving assistance, and / or automated vehicle (AV) systems. The techniques described herein may be implemented in conjunction with the utilization of open source and cloud-based machine learning training utilities to generate machine learning trained models. One example of such an open source solution includes TensorFlow, which is a free and open-source software library for dataflow and differentiable programming across a range of tasks. TensorFlow may be used in conjunction with many different types of machine learning utilities, such as Amazon's cloud-based SageMaker utility for instance, which is a fully-managed service that enables developers and data scientists to quickly and easily build, train, and deploy machine learning models at any scale.

Systems and methods for providing a real-time, augmented reality (mixed reality) simulation of an experience operating a semi-autonomous (e.g., SAE levels 2 to 5) vehicle are disclosed. In an exemplary embodiment, a user is presented with a simulated environment that allows the user to blend the immediate surroundings with interactive visual data representing various automated features ranging from ADAS (Automated Braking, Lane Keeping . . . ) to operating a fully autonomous vehicle. The first person perspective allows the user to get familiar with these vehicles before operating them in the real world. Additionally the interactions of the user with the semi-automated vehicles and automated features are recorded so they can be analyzed for future improvements.

An Augmented Reality (AR) display device interoperating with a vehicle and a method for operating the same are disclosed. An AR display device according to the present disclosure can provide an intuitive AR route to a parking available area or charging available area in a parking lot or charging station based on Advanced Driver Assistance Systems (ADAS) sensing data of a vehicle and / or control data of a parking lot / charging station. It is recognized that the vehicle has arrived in from of a selected parking space or charger, and an AR graphic interface can be changed in real time to sequentially guide forward driving, a change point to reverse driving, and reverse driving to the vehicle in correspondence to a current driving state of the vehicle, such that the vehicle can be parked accurately in the parking space or in front of the charger.

Distance calculations for autonomous vehicle (AV) or advanced driver assistance system (ADAS) navigation may include calculating a distance between two points within an image captured by a vehicle camera. To calculate distance in ADAS and AV systems, the vectors and other values may be represented as floating-point (FP) values. The use of FP values may provide improved performance of these calculations in ADAS, AV systems, and other systems that seek to reduce or minimize computation speed. When the input values are represented as FP values, the distance may be calculated as a square root of a sum of squares of the two FP values. Improved systems and methods are provided for floating-point calculation related to a square root, such as for determining distance calculations.

Aspects of the disclosure relate to automotive grade MCM technology which may include advanced driver assistance system (ADAS) system-on-chip and multiple dynamic random access memories (DRAMs) in one package. In addition, a thermal-mechanical testing vehicle (TMTV) may be used to mimic ADAS chips on ADAS system from thermal, mechanical, or manufacturability perspective. There may be a system which includes multiple MCM components designed into a customized printed circuit board (PCB) with a liquid cooling system.

A smart driving method, device, storage medium, and computer program are disclosed, which can be used for advanced driver assistance systems (ADAS) and autonomous driving. The method includes: acquiring environmental information surrounding the vehicle and the vehicle's current state information; determining a control point based on the environmental and state information; and generating a control trajectory for the current moment based on the control point, historical control trajectories, and state information. This control trajectory represents the path used to guide the vehicle's movement. By concentrating the influence of environmental information on characteristics at the control point and generating the control trajectory at the current moment through the control point, the control requirements of different scenarios are met. Furthermore, it eliminates the need to pre-process environmental information to generate multiple trajectory lines, significantly reducing the computational requirements. By using the priority and corresponding weight information of multiple information sources, switching between different characteristics is achieved, ensuring a smooth transition between multiple characteristics or scenarios and improving the performance of the advanced driver assistance system.

1. The name of the design product: vehicle detector. 2. The use of the design product: used for diagnosing and calibrating the advanced driver assistance system of the vehicle, and four-wheel positioning of the vehicle, etc. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view 1.

A beam control method is provided in the invention. The beam control method may be applied to a beam control apparatus configured in a car. The beam control method may include the following steps. The beam control apparatus obtains an image. An advanced driver assistance system (ADAS) of the beam control apparatus may determine whether at least one pedestrian is detected in front of the car according to the image. When the ADAS detects at least one pedestrian in front of the car, a beam control device may obtain pedestrian information of the at least one pedestrian and speed information of the car, and determine whether to enable a polite mode according to the pedestrian information and the speed information. When the beam control device enables the polite mode, the beam control device may control the display pattern of the beam device according to the pedestrian information.

A computer-implemented method for detecting objects within an advanced driver assistance system (ADAS) is provided. The method includes obtaining road scene datasets from a plurality of cameras, including at least road scene images and road scene data annotations, to be provided to an object detection neural network communicating with an open-vocabulary detector of a vehicle, converting, by a text prompter, the road scene data annotations into natural text inputs, converting, by a text embedder, the natural text inputs into embeddings, minimizing objective functions during training to adjust parameters of the object detection neural network, and detecting, by the object detection neural network, objects within the road scene datasets to provide alerts or notifications to a driver of the vehicle pertaining to the detected objects.

Radiofrequency systems for use in advanced driver assistance systems (ADAS) can include a mixture of high frequency (e.g., above 1 GHz) analog and components and lower-frequency digital devices mounted on one main circuit board. Cost savings can be achieved by providing high-frequency signal paths on an interposer circuit board that is mounted to the main circuit board and couples devices requiring high-frequency signalling (e.g., distributing a local oscillator signal to several devices forming part of a cascaded radar system). The interposer is fabricated from special purpose materials suitable for routing high frequency signals with low loss, while the main circuit board can be fabricated from commodity materials suitable for lower frequency applications.

A method includes receiving a desired state from a path planner, the desire state including at least a first desired yaw rate of the vehicle and a first desired lateral velocity of the vehicle. The method further includes determining, by a path tracking controller based at least in part on the first desired yaw rate and the first desired lateral velocity, a second desired yaw rate of the vehicle and a second desired lateral velocity of the vehicle. The method further includes determining, by a vehicle motion controller based at least in part on the second desired yaw rate and the second desired lateral velocity, an active rear steering command and a torque vectoring command. The method further includes controlling the vehicle using at least one of the active rear steering command and the torque vectoring command to cause the vehicle to follow a path generated by the path planner.

A smart ultrasonic integrated-circuit that allows at least one MEMS device to be combined with a piezoelectric transducer in a sensor array module. The sensor array module is capable of additional functionality for an advanced driver assistance system. For example, the MEMS device can add functionality because its wide bandwidth allows for simultaneous detection of audio signals and ultrasonic signals. Accordingly, the sensor array module may provide dual-mode (audio and ultrasonic) sensing in a single module. Additionally, the size / cost of a MEMS device allows for the use of a two-dimensional array for receiving ultrasonic echoes which can add a dimension to the ultrasonic range detection for a vehicle.

The embodiment of the invention provides an information transmission method and device, which are applied to the field of communication, in particular to the field of short-distance communication, such as a vehicle-mounted wireless communication system, and the method comprises the following steps: a first node receives a first MCS index value from a second node, and the first MCS index value corresponds to a first modulation mode; the first node receives data from the second node or sends the data to the second node according to the first MCS index value; wherein a first MCS information subset where the first MCS index value is located belongs to a predefined MCS information set containing 32 MCS information subsets. By adopting the embodiment of the invention, the selection flexibility of the modulation mode can be improved, and the efficiency and reliability of data transmission can be improved. The scheme can be further used for improving the ability of an automatic driving or advanced driving assistance system (ADAS), and can be applied to the Internet of Vehicles, such as vehicle external connection V2X, inter-vehicle communication long term evolution technology LTE-V, vehicle-vehicle V2V and the like.

A radar for an Advanced Driver Assistance System (ADAS) comprises at least one transmitting antenna coupled to a vehicle, wherein the at least one transmitting antenna is configured to send radar signals from the vehicle in the direction of a scenario of interest, at least one receiving antenna coupled to the vehicle, wherein the at least one receiving antenna is configured to receive reflected radar signals, and at least one processor.The processor is configured to execute computer-executable instructions to obtain multiple time samples of the reflected radar signals from the at least one receiving antenna at predetermined periodic intervals, to execute an autocorrelation algorithm on the obtained multiple time samples, to normalize a zero-delay-first delay ratio according to an output of the autocorrelation algorithm, and to compare the normalized zero-delay-first delay ratio with a specified threshold to determine whether the reflected radar signals contain an object identified as road clutter.

A system comprises: a sensor configured to detect a gesture relating to a vehicle; a network; an electronic control unit (ECU) coupled to the network, a display device, and the sensor, the ECU providing media functionality for the vehicle, the ECU configured to present a surround view video on the display device, determine a gesture state and screen coordinates for the gesture, and send the gesture state and the screen coordinates over the network; cameras providing feeds; and an ECU coupled to the network and to the cameras, the ECU providing an advanced driver assistance system (ADAS) for the vehicle, the ECU configured to receive the gesture state and the screen coordinates over the network, generate the surround view video based on the feeds of the cameras and the gesture state and the screen coordinates, and send the surround view video over the network.

A hardware-in-the-loop (HiL) test system is for testing sensor fusion of an advance driver assistance system (ADAS). The ADAS includes a plurality of sensors and an electronic control unit (ECU) processing outputs of the sensors. The HiL test system includes a three-dimensional (3D) scenario simulator for generating drive scenarios including objects in a surrounding environment of a simulated vehicle, and a sensor target emulator for generating emulated sensors inputs to the plurality of sensors corresponding to the drive scenarios generated by the 3D scenario simulator. The sensor target emulator is configured to synchronize the emulated sensor inputs by interpolating a current location of the objects from parameters extracted from the drive scenarios.

A chassis-integrated control device is provided. A receiver is configured to receive status information from each of the individual chassis control units present in a vehicle, as well as route information from an advanced driver assistance system. A control signal generator is configured to determine a target vehicle movement for the vehicle to be driven, based on the route information, and to generate control signals for the individual chassis control units to steer the vehicle so that it moves according to the target vehicle movement. A motion limiter is configured to generate information about the maximum curvature of a curve at which the vehicle is able to maneuver, based on status information and / or road surface information.A transmitter is set up to transmit information about the maximum curvature to the advanced driver assistance system and to forward the control signals to the individual chassis control units.

The system comprises: sensors configured to detect gestures relating to a vehicle; a network; an electronic control unit (ECU) connected to the network, a display device, and the sensors, the ECU providing media functions to the vehicle, the ECU being configured to perform the steps of presenting surround view video on the display device, determining gesture states and screen coordinates for the gestures, and transmitting the gesture states and screen coordinates over the network; a camera providing a feed; and an ECU connected to the network and the camera, the ECU providing an advanced driver assistance system (ADAS), the ECU being configured to perform the steps of receiving the gesture states and screen coordinates over the network, generating the surround view video based on the feed from the camera and the gesture states and screen coordinates, and transmitting the surround view video over the network.

The present disclosure relates to a method and a device for controlling an advanced driver-assistance system (ADAS) based on the load and the slope of a driving vehicle. The method may include calculating information on the load of the driving vehicle; transmitting a required acceleration while controlling an adaptive cruise control of the driving vehicle; comparing the time required to reach the required acceleration with the time required to reach an actual acceleration of the driving vehicle; transmitting a warning signal about overload to a driver based on the reaching time; calculating information on the slope on which the driving vehicle is traveling; and controlling the adaptive cruise control based on the information on the slope of the driving vehicle.

To provide a gripping detection system in which a driver is requested to grip a handle without disturbing the driver based on environment information of a vehicle during activation of a high-level operation support system.SOLUTION: A gripping detection system comprises: a steering part which includes a gripping part that a driver of the movable body grips; a first acquisition part which acquires environmental information related to environment where the movable body is used; an output part; and a control part. The steering part includes a second acquisition part which acquires measurement value varied according to behavior of hands of the driver. The control part executes, when the measurement value is not in a determination range defined in advance within a determination time defined in advance, at least one of: a range setting control which causes the output part output to indicate that the steering part is not gripped, and sets the determination range to be a first range or to be a second range where determination of gripping is alleviated relative to the first range according to environmental information; and a time setting control which sets the determination time to be a first time or a second time that is longer than the first time.SELECTED DRAWING: Figure 6

The application discloses an advanced driving assistance system and an intelligent driving automobile, and relates to the technical field of intelligent driving automobiles.The advanced driving assistance system comprises an information assistance module, a central decision unit and an electronic controller.The electronic controller is connected with the central decision unit and the information assistance module respectively.The information assistance module is used for sensing real-time information of a vehicle.The electronic controller is used for receiving the real-time information and determining a coefficient matrix which needs to be adjusted according to the real-time information.The central decision unit is used for adjusting a standard coefficient matrix according to the coefficient matrix and controlling vehicle driving by using the adjusted standard coefficient matrix.The electronic controller (unit) shares the computing power burden of the central decision unit, and the central decision unit realizes the anti-skid speed limiting function by adjusting the coefficient matrix, so as to guarantee the driving safety of the advanced driving assistance system of the intelligent driving automobile.

Some embodiments relate to environmental text perception using vision language models (VLMs). For example, an Advanced Driver Assistance System (ADAS) may identify candidate parking spaces, and a VLM may be used to evaluate parking signs and determine whether it is permissible and / or the cost to park in a candidate parking space. For example, frames from corresponding (e.g., front-facing, repeater, side pillar) camera(s) may be evaluated for corresponding parking signs (e.g., using a sign recognition DNN or a VLM). If a parking sign is detected, the image of the sign may be provided as input to a VLM with a textual prompt instructing the VLM to determine whether it is permissible to park at a corresponding location (and if so, the cost). The generated response may be provided to the ADAS to confirm or invalidate the candidate parking space, and a representation of the results may be provided to the driver.

An artificial intelligence framework is described that incorporates a number of neural networks and a number of transformers for converting a two-dimensional image into three-dimensional semantic information. Neural networks convert one or more images into a set of image feature maps, depth information associated with the one or more images, and query proposals based on the depth information. A first transformer implements a cross-attention mechanism to process the set of image feature maps in accordance with the query proposals. The output of the first transformer is combined with a mask token to generate initial voxel features of the scene. A second transformer implements a self-attention mechanism to convert the initial voxel features into refined voxel features, which are up-sampled and processed by a lightweight neural network to generate the three-dimensional semantic information, which may be used by, e.g., an autonomous vehicle for various advanced driver assistance system (ADAS) functions.