Member Info for johnchucka

Terry,
Patent IP wise Hyundai and Kai look to be linked.

[0041] According to one exemplary embodiment, after a takeover prompt, driver-observation device 106, always active in the case of high automation, analyzes the viewing behavior of driver 104 in order to draw conclusions from it about his/her situational awareness for the instantaneous driving situation. The requirements for the viewing behavior are deduced, for example, from the type of takeover situation. Thus, for example, in the case of a takeover in non-critical driving situations, it is sufficient if only a front roadway area of vehicle 100 is covered visually by the driver, while in the case of a necessary braking or lane-change maneuver, a side and rear area should also be secured. Next, the instantaneous viewing behavior is evaluated relative to the demands of the driving situation. FIG. 3 shows, by way of example, an underlying functional sequence of a control takeover in the sense of the approach presented here.

[0042] As soon as the driver deactivates the high automation using one of the available mechanisms, and therefore assumes control of the vehicle, the system state changes to a transition mode in which on one hand, it is possible to control the vehicle completely manually, and on the other hand, available assistance and safety systems of vehicle 100 are switched in according to the requirement. The type and intensity of the systems now activated depend on the estimated situational awareness, that is, the degree of attentiveness of driver 104 determined based on the viewing direction, as well as on the evaluation of the manual driver performance.

[0043] For example, if control of the vehicle is taken over without driver 104 having sufficiently secured the forward area, also known as front area, then according to one exemplary embodiment, systems for maintaining a safe distance, for instance, collision-warning systems or automatic braking systems, are activated in an especially sensitive parameterization.

[0044] If, in the case of a possibly necessary lane change, perhaps because of an obstacle on the roadway, it is determined that the driver is not adequately securing the area to the side or to the rear, then according to a further exemplary embodiment, lane-change warning systems and/or lane-keeping assistance systems are activated in an especially sensitive parameterization.

[0045] If, after control has been taken over without the requirement for critical maneuvering, an overly sharp variation of a lane position is determined, for instance moving to and fro within a traffic lane or, e.g., slow drifting out of the lane or a departure from the lane, then according to a further exemplary embodiment, systems for improving a lane-keeping quality, perhaps in the form of a lane-center guidance assistance or a lane-departure warning, are activated in an especially sensitive parameterization.

METHOD AND DEVICE FOR ASSISTING A DRIVER DURING THE DEACTIVATION OF A HIGHLY AUTOMATED DRIVING MODE OF A VEHICLE
A method for assisting a driver during the deactivation of a highly automated driving mode of a vehicle. In this context, a takeover signal, which represents a takeover of control of the vehicle by the driver, and auxiliary information are read in. The auxiliary information includes image information representing the driver and/or vehicle-control information representing a control of the vehicle by the driver. In a further step, a degree of attentiveness of the driver is determined, using the takeover signal and the auxiliary information. Finally, using the degree of attentiveness, an assistance signal is output to assist the driver during the takeover of control, by activating at least one driver-assistance function of the vehicle.

0002] In the case of highly automated driving, at system limits, the control of the vehicle should be taken over again by the driver with a sufficient time reserve. For example, time periods between 4 and 10 seconds are regarded as sufficient. The degree of automation is thereby able to change from highly automated to manual. Likewise, the driver is also able to deactivate the automation without prompting, e.g., by switch, and thus change to the manual driving mode.

[0003] Driver-monitoring cameras detect a viewing direction of the driver, for instance, and are able to detect a state of drowsiness of the driver based on various eye parameters such as blinking of the eyelid or eye movements. In the event driver drowsiness is detected, a suitable system may indicate, for example, that the driver should take a break. The analysis of the viewing direction may be used for assessing the visual attentiveness, and therefore, for the output of warnings to the distracted driver.
https://worldwide.espacenet.com/publicationDetails/biblio?CC=US&NR=2020039535A1&KC=A1&FT=D&ND=3&date=20200206&DB=&locale=en_EP#

VEHICULAR DRIVER MONITORING SYSTEM
A vehicular driver monitoring system includes an illumination source that emits non-visible light that illuminates at least a portion of a driver of the vehicle, a reflector disposed at the vehicle and within a line of sight of the illuminated portion of the driver, a camera disposed in the vehicle and having a field of view that encompasses the reflector, and a control having an image processor that processes image data captured by the camera. The reflector reflects at least some non-visible light and allows visible light to pass through. The camera captures image data representative of the non-visible light emitted by the illumination source that reflects off the illuminated portion of the driver of the vehicle and reflects off the reflector so as to be directed toward the camera. The control, responsive to processing of image data captured by the camera, monitors the illuminated portion of the driver.
https://worldwide.espacenet.com/publicationDetails/biblio?II=0&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200507&CC=US&NR=2020143560A1&KC=A1#
https://patents.justia.com/patent/20200143560
Drawings
http://www.freepatentsonline.com/20200143560.pdf

METHOD AND DEVICE FOR ADAPTING A POSITION OF A SEAT DEVICE OF A VEHICLE DURING AND/OR PRIOR TO A SWITCHOVER OF THE VEHICLE FROM AN AUTOMATED DRIVING MODE TO A MANUAL DRIVING MODE

[0011] A vehicle could be a vehicle for transporting passengers such as a vehicle that drives in a highly automated manner. A passenger may be a vehicle driver or a front-seat passenger or some other passenger (i.e. a vehicle occupant) of a vehicle. A seat device, for example, may involve an adjustable seat and/or a seat bench in a vehicle. An automated driving mode may be understood as a driving mode of a vehicle in which a driver assistance system, for example, executes certain driving maneuvers nearly completely or completely on its own. For instance, when driving on an expressway, a vehicle may assume the complete control, including passing and evasive maneuvers. Toward this end, the vehicle is capable of communicating with its environment and of interacting with other vehicles, for example. In an assisted driving mode, a driver should not take his eyes off the situation on the road at any time so that he can intervene in an emergency situation, if necessary. In an automated driving mode, the driver may intermittently tend to other things and has to be able to intervene only when prompted, for instance within 10 seconds, in order to resume the vehicle control. During the period in which the driver leaves the driving task to the vehicle, he may occupy himself with other things or assume a more comfortable seated position or position of a seat device such as a comfort position. A manual driving mode may be understood as a manual control, e.g., a linear and transverse control, of a vehicle by a vehicle driver. The adjustment signal may include an item of information pertaining to a preferred change in the position of a seat device of a vehicle. Using the adjustment signal, for example, an electrically controlled seat adjustment is able to be actuated. In an upright position, for example, the passenger may sit upright in the seat device, and in the comfort position, the passenger may recline in the seat device, for instance. The position signal may indicate an angular position of a backrest of a seat device, for example.
https://worldwide.espacenet.com/publicationDetails/description?CC=US&NR=2020130546A1&KC=A1&FT=D&ND=3&date=20200430&DB=&locale=en_EP#

SPATIAL AND TEMPORAL ATTENTION-BASED DEEP REINFORCEMENT LEARNING OF HIERARCHICAL LANE-CHANGE POLICIES FOR CONTROLLING AN AUTONOMOUS VEHICLE
Systems and methods are provided that employ spatial and temporal attention-based deep reinforcement learning of hierarchical lane-change policies for controlling an autonomous vehicle. An actor-critic network architecture includes an actor network that process image data received from an environment to learn the lane-change policies as a set of hierarchical actions, and a critic network that evaluates the lane-change policies to calculate loss and gradients to predict an action-value function (Q) that is used to drive learning and update parameters of the lane-change policies. The actor-critic network architecture implements a spatial attention module to select relevant regions in the image data that are of importance, and a temporal attention module to learn temporal attention weights to be applied to past frames of image data to indicate relative importance in deciding which lane-change policy to select.

Deep reinforcement learning (DRL) has recently emerged as a new way to learn driving policies. DRL refers to any number of a machine learning technique that extend a reinforcement learning approach to learning of the entire process using deep learning techniques. DRL can be used to actively target problems that interact with the environment and learn by maximizing a scalar reward signal. An agent of a DRL algorithm uses a neural network (e.g., a convolutional neutral network that is used to recognize an agent's state) to select the action to be performed in response to receiving any given observation. Neural networks are machine learning models that employ one or more layers of nonlinear units to predict an output for a received input. A “deep neural network” is used to refer to a neural network with one or more hidden layers in addition to an output layer. The output of each hidden layer is used as input to the next layer in the network, i.e., the next hidden layer or the output layer. Each layer of the network generates an output from a received input in accordance with current values of a respective set of parameters.
https://worldwide.espacenet.com/publicationDetails/biblio?II=40&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200507&CC=US&NR=2020139973A1&KC=A1#
https://patents.justia.com/patent/20200139973
Drawings
http://www.freepatentsonline.com/20200139973.pdf

METHOD FOR DISAMBIGUATING AMBIGUOUS DETECTIONS IN SENSOR FUSION SYSTEMS
A disambiguating system for disambiguating between ambiguous detections is provided. The system includes a plurality of modules, wherein each module is configured to disambiguate between ambiguous detections by selecting, as a true detection, one candidate detection in a set of ambiguous detections and wherein each module is configured to apply a different selection technique. The system includes: one or more modules configured to select as the true detection, the candidate detection whose associated position is closer to a position indicated by other data and one or more modules configured to select as the true detection, the candidate detection with the highest probability of being true based on other sensor data.
https://worldwide.espacenet.com/publicationDetails/biblio?II=10&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200507&CC=US&NR=2020142026A1&KC=A1#
https://patents.justia.com/patent/20200142026
Drawings
http://www.freepatentsonline.com/20200142026.pdf

COMBINING DRIVER ALERTNESS WITH ADVANCED DRIVER ASSISTANCE SYSTEMS (ADAS)
The disclosure is directed to systems and methods for operating or controlling an ADAS mechanism. A first sensor of an ADAS mechanism can determine a potential obstacle to a vehicle, and a position of the potential obstacle relative to the first sensor. A second sensor can determine a gaze angle of a user of the vehicle. An activation engine in communication with the first sensor and the second sensor can determine a proximity of the gaze angle of the user to the determined position of the potential obstacle. The activation engine can control, in response to the determined proximity, an operation of the ADAS mechanism for responding to the potential obstacle.
https://worldwide.espacenet.com/publicationDetails/biblio?II=8&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200507&CC=US&NR=2020139965A1&KC=A1#
https://patents.justia.com/patent/20200139965
Drawings
http://www.freepatentsonline.com/20200139965.pdf

https://www.eyelock.com/

CONTROL APPARATUS, CONTROL METHOD, AGENT APPARATUS, AND COMPUTER READABLE STORAGE MEDIUM
A control apparatus controls an agent apparatus functioning as a user interface of a request processing apparatus that acquires a request indicated by at least one of a voice and a gesture of a user and performs a process corresponding to the request. The control apparatus includes a gaze point specifying section specifying a gaze point of the user, and a face control section controlling an orientation of a face or line of sight of an agent used to transmit information to the user. The face control section controls the orientation of the face or line of sight of the agent such that the face or line of sight of the agent becomes oriented toward the user, if the gaze point is positioned at (i) a portion of the agent or (ii) a portion of an image output section that displays or projects an image of the agent.
https://worldwide.espacenet.com/publicationDetails/biblio?CC=US&NR=2020143185A1&KC=A1&FT=D&ND=3&date=20200507&DB=&locale=en_EP#
https://patents.justia.com/patent/20200143185
Drawings
http://www.freepatentsonline.com/20200143185.pdf

https://worldwide.espacenet.com/publicationDetails/biblio?CC=WO&NR=2020091156A1&KC=A1&FT=D&ND=3&date=20200507&DB=&locale=en_EP#

TERMINAL
The present invention relates to a terminal. A terminal according to an embodiment of the present invention can comprise: a front camera; a rear camera; and a processor which receives a first image from the rear camera, receives a second image from the front camera, detects a gaze area in the first image on the basis of the second image, and controls such that the focus can be set to the detected area. Therefore, focusing can be performed conveniently in accordance with the gaze.
Drawings
P17
http://www.freepatentsonline.com/WO2020091156A1.pdf

EYEBALL INFORMATION ESTIMATION DEVICE, EYEBALL INFORMATION ESTIMATION METHOD, AND EYEBALL INFORMATION ESTIMATION PROGRAM
An eyeball information estimation device includes: an acquisition unit acquiring an image including a pupil of a subject and a Purkinje image of the subject; a detection unit detecting a center position of the pupil and a position of the Purkinje image; a selection unit selecting which of first and second sight line angle calculation processings of calculating a sight line angle of the eye of the subject is to be executed; and a processing unit estimating an eyeball center position of the subject based on a three-dimensional face model and updating an eyeball center position of a storage unit, at least on a condition that a pupil reliability is higher than a first pupil threshold value, and a Purkinje reliability is higher than a first Purkinje threshold value, when the first sight line angle calculation processing is selected.
https://worldwide.espacenet.com/publicationDetails/biblio?CC=US&NR=2020105016A1&KC=A1&FT=D&ND=3&date=20200402&DB=&locale=en_EP#

APPARATUS AND METHOD FOR CALIBRATING DRIVER MONITORING CAMERA
An apparatus for calibrating a driver monitoring camera may include: a camera configured to capture an image of a driver's face; a control unit configured to receive the captured image from the camera, and detect the face to determine a face position; and a display unit configured to display the determination result of the face position by the control unit.
https://worldwide.espacenet.com/publicationDetails/biblio?II=5&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200430&CC=US&NR=2020134870A1&KC=A1#
https://patents.justia.com/patent/20200134870
Drawings
http://www.freepatentsonline.com/20200134870.pdf

APPARATUS FOR DETERMINING VISUAL CONFIRMATION TARGET
An apparatus for determining a visual confirmation target, the apparatus includes a gaze detection portion detecting a gaze direction of a driver for a vehicle, a vehicle information acquisition portion, an image acquisition portion acquiring a captured image, a gaze region extraction portion extracting a gaze region of the driver within the captured image based on a detection result of the gaze direction, a candidate detection portion recognizing objects included in the captured image, generating a top-down saliency map based on the captured image and the vehicle information, and detecting an object having saliency in the top-down saliency map among the recognized objects as a candidate for a visual confirmation target, and a visual confirmation target determination portion determining a visual confirmation target on a basis of an extraction result of the gaze region and a detection result of the candidate for the visual confirmation target.
….
Next, a functional configuration of the ECU 14 provided at the vehicle 1 according to the present embodiment is explained with reference to FIG. 4. As illustrated in FIG. 4, the ECU 14 mainly includes a gaze detection portion 400, an image acquisition portion 401, a vehicle information acquisition portion 402, a gaze region extraction portion 403, a candidate detection portion 404, and a visual confirmation target determination portion 405. The gaze detection portion 400, the image acquisition portion 401, the vehicle information acquisition portion 402, the gaze region extraction portion 403, the candidate detection portion 404, and the visual confirmation target determination portion 405 are achieved by the CPU 14a of the ECU 14 executing the program stored at the ROM 14b. Alternatively, the aforementioned configurations may be achieved by hardware. In the present embodiment, the ECU 14 functions as an apparatus for determining a visual confirmation target.
https://worldwide.espacenet.com/publicationDetails/biblio?II=7&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200430&CC=US&NR=2020134336A1&KC=A1#
https://patents.justia.com/patent/20200134336
Drawings
http://www.freepatentsonline.com/20200134336.pdf

ACTIVATION ZERO-BYPASS AND WEIGHT PRUNING IN NEURAL NETWORKS FOR VEHICLE PERCEPTION SYSTEMS
In one example implementation according to aspects of the present disclosure, a computer-implemented method includes capturing a plurality of images at a camera associated with a vehicle and storing image data associated with the plurality of images to a memory. The method further includes dispatching vehicle perception tasks to a plurality of processing elements of an accelerator in communication with the memory. The method further includes performing, by at least one of the plurality of processing elements, the vehicle perception tasks for the vehicle perception using a neural network, wherein performing the vehicle perception tasks comprises performing an activation bypass for values below a first threshold, and performing weight pruning of synapses and neurons of the neural network based at least in part on a second threshold. The method further includes controlling the vehicle based at least in part on a result of performing the vehicle perception tasks.
https://worldwide.espacenet.com/publicationDetails/biblio?II=1&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200430&CC=US&NR=2020134459A1&KC=A1#
https://patents.justia.com/patent/20200134459

FIXED-POINT QUANTIZATION IN NEURAL NETWORKS FOR VEHICLE PERCEPTION SYSTEMS
Examples of techniques for using fixed-point quantization in deep neural networks are disclosed. In one example implementation according to aspects of the present disclosure, a computer-implemented method includes capturing a plurality of images at a camera associated with a vehicle and storing image data associated with the plurality of images to a memory. The method further includes dispatching vehicle perception tasks to a plurality of processing elements of an accelerator in communication with the memory. The method further includes performing, by at least one of the plurality of processing elements, the vehicle perception tasks for the vehicle perception using a neural network, wherein performing the vehicle perception tasks comprises quantizing a fixed-point value based on an activation input and a synapse weight. The method further includes controlling the vehicle based at least in part on a result of performing the vehicle perception tasks.
https://worldwide.espacenet.com/publicationDetails/biblio?II=0&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200430&CC=US&NR=2020134324A1&KC=A1#
https://patents.justia.com/patent/20200134324
Drawings
http://www.freepatentsonline.com/20200134324.pdf

Empathy-Based Speed Alert
A vehicle includes a controller, programmed to responsive to detecting a speeding event, generate an alert factor and send an alert to at least one of an in-vehicle output device or an outside-vehicle output device based on the alert factor; and responsive to detecting a user failing to respond, increase the alert factor and send the alert for output based on the increased alert factor.

The user history data 204 may include any data related to the behavior history of the current vehicle user/driver. For instance, the user history data 206 may include vehicle usage patterns, number of alert elevations, response to past alerts, driving record, points, age, financial situation, and/or family relationship of the current vehicle user. The identity of the current vehicle user may be determined using the interior camera 140 with facial recognition technologies or the microphone 142 with voice recognition technologies. Additionally or alternatively, the identity may be manually input via the HMI controls 118 or via remotely input via the server 186. An interested party may remotely input the identity of the vehicle user for a specific period of time via the server 186. As some non-limiting examples, the interested party may be a parent of the vehicle user, an insurance company, a car rental company or the like.

The area history data 208 may include any information of the area in which the vehicle 102 is currently traveling or anticipated to travel determined via the GNSS controller 124 and/or the navigation controller 126. For instance, the area history data 208 may include the number of accidents, aggregated driving pattern, likelihood of police presence, numbers of traffic stops, accident rate, and/or average price of ticket cost in the area.

The computing platform 104 may further collect the real-time data 210 from the server 186 via the communication network 188 in a real-time manner. The real-time data 210 may be further collected from various components of the vehicle 102. The exterior camera may be configured to capture images outside the vehicle to collect information such as road hazards, accidents, police presences or the like. The seat sensor 180 and/or the interior camera 140 may be configured to collected information about the occupancy of the vehicle 102, such as the number and type of passengers. In addition, the real-time data 210 may include information about approaching school zones, construction zones, traffic signals and stops, reported police locations, current speed, and/or duration of speeding events.
https://worldwide.espacenet.com/publicationDetails/biblio?II=38&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200430&CC=US&NR=2020130577A1&KC=A1#
https://patents.justia.com/patent/20200130577
Drawings
http://www.freepatentsonline.com/20200130577.pdf

VEHICLE OBSTACLE INFORMING DEVICE
A vehicle obstacle informing device includes: an obstacle detection section configured to detect an obstacle in surroundings of a vehicle; a gaze detection section configured to detect a gaze direction of an occupant seated in a driving seat; and an informing section configured to make the occupant aware of the obstacle using at least one of display or audio in cases in which the gaze of the occupant as detected by the gaze detection section is directed toward the obstacle during self-driving of the vehicle.
https://worldwide.espacenet.com/publicationDetails/biblio?CC=US&NR=2020130580A1&KC=A1&FT=D&ND=3&date=20200430&DB=&locale=en_EP#
https://patents.justia.com/patent/20200130580
Drawings
http://www.freepatentsonline.com/20200130580.pdf

ANALYZING EFFECT OF A SECONDARY COGNITIVE LOAD TASK ON A PRIMARY EXECUTIVE TASK
This disclosure relates to analyzing effect of a secondary cognitive load task on a primary executive task. Human random sequence generation is a marker to study cognitive functions and inability to generate random sequences (RS) can reveal underlying impairments. Traditionally, ‘call out’ or ‘write down’ procedures are used to obtain human generated numbers, wherein short term memory and number of previously generated entities visible to a subject plays a major role. Also precise trial-wise or response-wise analysis may not be possible. In the present disclosure, the human generated random numbers are digitized into RS and a cognitive load (CL) inducing task is imposed on the executive task. The CL demanding task disrupts randomization performance. Deviation from randomness, load index based on gaze data and deviation from pupillometry data of healthy subjects are provided as indicators of an interference effect imposed by the CL and thereby indicative of underlying impairments.
https://worldwide.espacenet.com/publicationDetails/biblio?CC=US&NR=2020135325A1&KC=A1&FT=D&ND=3&date=20200430&DB=&locale=en_EP#
https://patents.justia.com/patent/20200135325

A DROWSINESS DETECTION SYSTEM
A machine-implemented method for automated detection of drowsiness, which includes receiving from an imaging device directed at the face of an operator a series of images of the face of the operator onto processing hardware, on the processor detecting facial landmarks of the operator from the series of images to determine the level of talking by the operator, the level of yawning of the operator, the PERCLOS of the operator, on the processor detecting the facial pose of the operator from the series of images to determine the level of gaze fixation by the operator, on the processor calculating the level of drowsiness of the operator by ensembling the level of talking by the operator, the level of yawning of the operator, the PERCLOS of the operator and the level of gaze fixation by the operator, and generating an alarm when the calculated level of drowsiness of the operator exceeds a predefined value.
https://worldwide.espacenet.com/publicationDetails/biblio?II=0&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200430&CC=WO&NR=2020084469A1&KC=A1#

5DT INC
More than 25 years in business
Over 200 simulators deployed worldwide
Simulators for vehicles and machines from more than 35 manufacturers
More than 125 different vehicles and machines simulated
Regional offices in 4 countries
https://5dt.com/about/