Member Info for johnchucka

EVALUATION OF A SIMULATED VEHICLE-RELATED FEATURE
A method performed by a vehicle feature evaluation system (1) for enabling evaluation of a simulated vehicle-related feature. The vehicle feature evaluation system determines (1001) in relation to a road-driven vehicle (2), with support from a tracking system (5), an orientation of a head-mounted display (4), HMD, adapted to be worn by an occupant (3) on-board the road-driven vehicle. The vehicle feature evaluation system further determines (1002) a simulated vehicle design feature to be evaluated in the road-driven vehicle. Moreover, the vehicle feature evaluation system provides (1006) in real-time to a HMD display (41) of the HMD, taking into consideration the HMD orientation, a virtual representation (7) of the simulated vehicle design feature superimposed on a real-time surrounding-showing video stream (6) derived from real-world image data (211) captured with support from one or more vehicle-attached cameras (21) adapted to capture surroundings external of the road-driven vehicle.

[0004] According to a first aspect of embodiments herein, the object is achieved by a method performed by a vehicle feature evaluation system for enabling evaluation of a simulated vehicle-related feature. The vehicle feature evaluation system determines in relation to a road-driven vehicle, with support from a tracking system, an orientation of a head-mounted display, HMD, adapted to be worn by an occupant on-board the road-driven vehicle. The vehicle feature evaluation system further determines a simulated vehicle design feature to be evaluated in the road-driven vehicle. Moreover, the vehicle feature evaluation system provides in real-time to a HMD display of the HMD, taking into consideration the HMD orientation, a virtual representation of the simulated vehicle design feature superimposed on a real-time surrounding-showing video stream derived from real-world image data captured with support from one or more vehicle-attached cameras adapted to capture surroundings external to the road-driven vehicle.
https://worldwide.espacenet.com/publicationDetails/description?CC=US&NR=2020184841A1&KC=A1&FT=D&ND=3&date=20200611&DB=&locale=en_EP#
Drawings
http://www.freepatentsonline.com/20200184841.pdf

Since the vehicle feature evaluation system provides in real-time to a HMD display of the HMD, taking into consideration the HMD orientation, a virtual representation of the simulated vehicle functionality feature superimposed on a real-time real-world video stream derived from real-world image data captured with support from one or more forward-facing cameras provided on the HMD in eye-position of the occupant, there is provided to the HMD display a real-time physical world view—essentially as seen by the occupant with support from the eye-level forward facing camera(s)—electronically mixed with the computer-generated virtual representation temporally and spatially commensurate with said physical world view such that the real-world video stream appears as a background overlaid with said virtual representation. Thus, live imagery from the physical world is electronically merged with computer-generated imagery, a concept commonly referred to as mixed reality and/or augmented reality. More specifically, the virtual representation of the simulated vehicle functionality feature is overlaid the real-world video stream, a concept commonly referred to as video see-through. The camera(s) and/or HMD may for instance be adapted to support arranging and/or re-arranging said camera(s) such that the camera(s) are positioned to correspond to respective points of right and left eye views of the occupant. Thus, with the forward-facing camera(s) provided in eye-position of the HMD-wearing occupant, the real-time real-world video stream may represent what the occupant would see even if not wearing the HMD, such as temporally and spatially commensurate with what said occupant would see even if not wearing the HMD. Subsequently, with the HMD-wearing occupant being on-board the road-driven vehicle, e.g. seated in a driver's seat or passenger's seat thereof, the real-time real-world video stream may then represent what a driver or passenger of said road-driven vehicle would see even if not wearing the HMD, such as for instance a portion of an interior of the vehicle and/or a view exterior of the vehicle through the windscreen or other window(s) thereof. Accordingly, upon in real-time superimposing a virtual representation of a simulated vehicle functionality feature—such as for instance a virtual display with e.g. new and/or updated design and/or functionality—on the real-world video stream, said simulated vehicle functionality feature may be evaluated in a road-driven vehicle, e.g. while said road-driven vehicle is driven in real traffic and/or along actual roads. Thereby, with the exception of the virtual representation of the simulated vehicle functionality feature, the entire test environment is authentic and/or real. Consequently, the simulated vehicle functionality feature may be evaluated in real traffic and/or in real road-driving scenarios, which thus enables said simulated vehicle functionality feature to be evaluated under more reality-resembling conditions

EVALUATION OF A SIMULATED VEHICLE FUNCTIONALITY FEATURE
A method performed by a vehicle feature evaluation system (1) for enabling evaluation of a simulated vehicle functionality feature. The vehicle feature evaluation system determines (1001) in relation to a road-driven vehicle (2), with support from a tracking system (5), an orientation of a head-mounted display (4), HMD, adapted to be worn by an occupant (3) on-board the road-driven vehicle. The vehicle feature evaluation system further determines (1002) a simulated vehicle functionality feature to be evaluated in the road-driven vehicle. Moreover, the vehicle feature evaluation system provides (1004) in real-time to a HMD display (42) of the HMD, taking into consideration the HMD orientation, a virtual representation (7) of the simulated vehicle functionality feature superimposed on a real-time real-world video stream (6) derived from real-world image data captured with support from one or more forward-facing cameras (41) provided on the HMD in eye-position of the occupant.

It is therefore an object of embodiments herein to provide an improved and/or alternative approach supporting evaluation of virtual vehicle functions and/or concepts.
According to a first aspect of embodiments herein, the object is achieved by a method performed by a vehicle feature evaluation system for enabling evaluation of a simulated vehicle functionality feature. The vehicle feature evaluation system determines in relation to a road-driven vehicle, with support from a tracking system, an orientation of a head-mounted display, HMD, adapted to be worn by an occupant on-board the road-driven vehicle. The vehicle feature evaluation system further determines a simulated vehicle functionality feature to be evaluated in the road-driven vehicle. Moreover, the vehicle feature evaluation system provides in real-time to a HMD display of the HMD, taking into consideration the HMD orientation, a virtual representation of the simulated vehicle functionality feature superimposed on a real-time real-world video stream derived from real-world image data captured with support from one or more forward-facing cameras provided on the HMD in eye-position of the occupant.
https://worldwide.espacenet.com/publicationDetails/biblio?II=2&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200611&CC=US&NR=2020184030A1&KC=A1#
https://patents.justia.com/patent/20200184030
Drawings
http://www.freepatentsonline.com/20200184030.pdf

Lewbo ,
GE have published a few patents dated 2020-06-11 describing spockpit design including the one below focusing on fatigue.

AIRCRAFT AND METHOD OF CONTROLLING 2020-06-11
A method of controlling an aircraft includes tracking, using at least one sensor, one of an input by a pilot or a biometric parameter of a first pilot during flight of the aircraft. The method also includes determining a lack of attention by the pilot or a depth of sleep of the pilot based on the biometric parameter.

In one aspect, the disclosure relates to a method of controlling an aircraft. The method includes tracking, using at least one sensor, one of an input by a first pilot or a biometric parameter of a first pilot during flight of the aircraft, determining, using a controller that is operatively connected to the at least one sensor, a lack of attention by the first pilot or a depth of sleep of the first pilot based on the biometric parameter, allowing a predetermined amount of lack of attention by the first pilot or controlled rest, and controlling at least one system of the aircraft when the determined lack of attention or determined depth of sleep satisfies a predetermined threshold.
In another aspect, the disclosure relates to a method of controlling an aircraft. The method includes tracking, using at least one sensor, a biometric parameter of a first pilot during flight of the aircraft, determining, using a controller that is operatively connected to the at least one sensor, a lack of attention or depth of sleep of the pilot based on the biometric parameter, allowing a predetermined amount of lack of attention or depth of sleep, and modifying access to a system of the aircraft when the amount of lack of attention or depth of sleep satisfy a predetermined threshold.

The processor 122 of the controller 120 can send a signal or control command to any or all of the imaging module 102, audio module 104, seat tracking module 108, haptic feedback generator 114, or door lock module 116. In one non-limiting example, upon receipt of combined input from the biometric sensor 106 and timer 115 that a pilot's eyes have been closed for a predetermined time duration, the processor 122 can issue a command to the haptic feedback generator 114 to vibrate one or both seats 54, 55 (FIG. 2) to increase an alertness level of the pilot or co-pilot. In another non-limiting example, the processor 122 can send a signal to the imaging module 102, such as a visual message to be read by the pilot or co-pilot on the flight display 52, or a command to enable or disable the image sensor 103.
https://worldwide.espacenet.com/publicationDetails/biblio?II=6&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200611&CC=US&NR=2020183382A1&KC=A1#
https://patents.justia.com/patent/20200183382
Drawings
http://www.freepatentsonline.com/20200183382.pdf

AIRCRAFT AND METHOD OF ADJUSTING A PILOT WORKLOAD
A method of adjusting an operator workload during a travel segment including tracking over a time period, using at least one sensor, one of inputs by an operator indicative of an operator workload or image sensor data or a biometric parameter indicative of an operator stress level during the travel segment. Determining, using a controller that is operatively connected to the at least one sensor, a level of one of the operator workload or operator stress level. The method also includes adjusting, using a controller that is operatively connected to the control computer, the operator workload when the level of one of the operator workload or operator stress level exceeds a predetermined threshold.

The tracking system 100 can include at least one imaging module 102 and at least one audio module 104. The imaging module 102 can include an image sensor 103 configured to sense visual information about a pilot or co-pilot, such as rapid eye movement, eyes moving one direction or another, being open or closed, a direction of gaze, or a facial state such as eyebrows raised or lowered, by way of non-limiting examples and provide an output signal based thereon. An eye movement or body movement parameter can be stored by the tracking system 100 The imaging module 102 or the flight control computer 22 can also be in signal communication with any of the flight displays 52, such as to display a visual indication based on the sensed visual information from the imaging module 102.
https://worldwide.espacenet.com/publicationDetails/biblio?II=10&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200611&CC=US&NR=2020184833A1&KC=A1#
https://patents.justia.com/patent/20200184833
Drawings
http://www.freepatentsonline.com/20200184833.pdf

METHOD AND SYSTEM FOR DISPLAY AND INTERACTION EMBEDDED IN A ****PIT
The invention relates to a method and system for display and interaction with an aircraft control system, intended for an aircraft pilot, embedded in a ****pit of the aircraft. The method is implemented by a system for display and interaction including a first so-called head-down man-machine interface and a second so-called head-up man-machine interface. The method includes determining a line of sight of the pilot, receiving a command to enter the frozen display mode and keeping at least part of the display on the second man-machine interface in a frozen position, independently of the pilot's line of sight, then displaying at least one complementary man-machine interface element, as a function of the pilot's line of sight, in at least one free area of the ****pit, and displaying a cursor representative of the pilot's line of sight.

SUMMARY OF THE INVENTION
To that end, according to one aspect, the invention relates to a method for display and interaction with an aircraft control system suitable for an aircraft pilot, implemented by a display and interaction system embedded in a ****pit of the aircraft and including a first man-machine interface called head-down and a first controller suitable for controlling the display of said first man-machine interface, and a second man-machine interface called head-up, and a second controller suitable for controlling the display on said second man-machine interface, the display and interaction system further including a device configured to determine the line of sight of the pilot as a function of a position of the head and/or eyes of the pilot, the second controller being configured in order, in a first standard display mode, to adapt at least one display on the second man-machine interface as a function of the pilot's line of sight. The method includes the following steps:
determining a line of sight of the pilot,
receiving a command to enter the frozen display mode and to keep at least part of the display on the second man-machine interface in a frozen position, independently of the pilot's line of sight,
displaying at least one complementary man-machine interface element, as a function of the pilot's line of sight, in at least one free area of the ****pit, and displaying a cursor representative of the pilot's line of sight.

Advantageously, the proposed display and interaction method makes it possible to obtain a display continuity, and therefore to obtain a unified display having improved usage ergonomics for the interaction.
https://worldwide.espacenet.com/publicationDetails/biblio?CC=US&NR=2020183154A1&KC=A1&FT=D&ND=3&date=20200611&DB=&locale=en_EP#
https://patents.justia.com/patent/20200183154
Drawings
http://www.freepatentsonline.com/20200183154.pdf

https://cmmbvision.com/business-areas

Satellite Mobile Multimedia
Through its strategic ownership in Silkwave Holdings, the Company provides multimedia services to connected-cars and mobile devices. Silkwave is world’s first connected-car multimedia operator. It uses groundbreaking satellite-LTE Converged™ technology to deliver mobile audio-video digital entertainment, telematics data, and Internet services. Its services can target vehicles, boats, trains, mobile devices with unprecedented economies of scale and ubiquity. Its infrastructure includes world’s only L-band mobile broadcast satellite that covers China, Southeast Asia, and India and can simultaneously service billions of users in the region.
Silkwave’s primary business and market is providing mobile multimedia to connected smart cars in China, world’s largest vehicle market with 295 million growing to 400 million by 2025. In China, Silkwave has developed full-fledged local partnership, operating platform, and ecosystem support. Its XingYun multimedia solution App is in the process of being adopted as the industry standard for future Chinese cars and is ready for commercial deployment by 2018. Business and revenue models will include service activation fee, subscription, advertising, and value-added services.
Silkwave is also developing markets in India and Indonesia with local partners, where it will leverage the technology ecosystem in China to quickly expand business to the region with speed and scalability.

https://silkwaves.com/ecosystem

METHOD AND APPARATUS FOR ENHANCED CAMERA AND RADAR SENSOR FUSION
A sensor fusion system (120) for an autonomous vehicle and/or advanced driver assistance systems (ADAS) that combines measurements from multiple independent sensors (102/104) to generate a better output. The multiple sensors (102/104) can interact and perform "cross-training" for enhanced sensor performance. The sensor fusion system (120) utilizes data exchange and cross-training between sensors (102/104) for enhanced sensor performance while constantly improving sensor fusion results. Some exemplary embodiments of the present disclosure provide a system for an autonomous vehicle and/or a vehicle ADAS that combines information from independent sensors in order to accurately distinguish environmental objects and movements. This allows the vehicle to accurately make informed navigation decisions based on the environmental surroundings. The sensor fusion system (120) can exchange ground truth information between the sensors (102/104) related to a same object, which allows for constant machine learning object classification and constant speed/distance estimation calibration.

[0004] Autonomous driving and ADAS demand reliable environmental sensing, and each of the many different sensors has its own merits and shortcomings. For example, cameras capture high quality images and are good at scenario interpretation (object detection and classification), but they do not perform as well for measuring distance and speed. Cameras can also be sensitive to lighting and weather conditions. On the other hand, radars are robust to all weather conditions and provide accurate distance and speed measurements, but they are usually limited in imaging resolution and lack classification capabilities (i.e., radars can detect objects but are unable to tell what the objects are). Thus, the strengths and weaknesses of cameras and radars are very complementary.
https://worldwide.espacenet.com/publicationDetails/description?CC=WO&NR=2020115544A1&KC=A1&FT=D&ND=3&date=20200611&DB=&locale=en_EP#
Drawings
http://www.freepatentsonline.com/WO2020115544A1.pdf

https://cmmbvision.com/business-areas

GENTEX CORP 2020-06-11
IMAGING SYSTEM FOR IRIS AUTHENTICATION AND DRIVER MONITORING
An imaging apparatus comprises a first light source configured to project a first illumination onto a vehicle occupant and a second light source configured to project a second illumination onto the vehicle occupant. The system further comprises an imager comprising a pixel array. A lens apparatus comprises a first lens comprising a first field of view and a second lens comprising a second field of view. At least one shutter is selectively controlled to transmit the first illumination from the first lens to the pixel array. The at least one shutter is further controlled to selectively transmit the second illumination from the second lens to the pixel array. The imager is configured to process the first illumination in the first field of view and the second illumination in the second field of view.
https://worldwide.espacenet.com/publicationDetails/biblio?II=12&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200611&CC=WO&NR=2020115682A1&KC=A1#
https://patents.justia.com/patent/20200186701
Drawings
http://www.freepatentsonline.com/WO2020115682A1.pdf

SELF-DRIVING INFRASTRUCTURE
The present disclosure relates to providing vehicles in the real world with instructions while operating on a roadway portion. The roadway portion may be one or more lanes in a segment of a roadway. A first set of vehicles may be equipped with a communication device for communication with one or more servers configured to provide instructions and/or other information. One or more objects at or near the roadway portion may be identified. A presence of first object not in the first set of vehicles may be detected. The first object may not include a communication device. A warning notification may be provided to vehicles at or near the roadway portion when the first object is detected. Instructions to perform one or more driving maneuvers may be provided to vehicles at or near the roadway portion when the first object is detected.
https://worldwide.espacenet.com/publicationDetails/biblio?II=1&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200611&CC=US&NR=2020184814A1&KC=A1#
https://patents.justia.com/patent/20200082717
Drawings
http://www.freepatentsonline.com/20200184814.pdf

ADAPTIVE INFRARED LIGHTING FOR FULL VEHICLE CABIN BASED ON OCCUPANCY
A system for selectively activating infrared lights in a vehicle cabin includes a controller comprising a processor and a non-transitory computer readable memory, two or more infrared illumination sources positioned within the vehicle cabin, the two or more infrared illumination sources communicatively coupled to the controller, an imaging device communicatively coupled to the controller and a machine-readable instruction set stored in the non-transitory computer readable memory of the controller. The machine-readable instruction set causes the system to perform at least the following when executed by the processor: receive image data from the imaging device, determine a location of an occupant in the vehicle cabin based on the image data, and activate a first infrared illumination source of the two or more infrared illumination sources that corresponds to the location of the occupant in the vehicle cabin.
https://worldwide.espacenet.com/publicationDetails/biblio?II=0&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200611&CC=US&NR=2020184669A1&KC=A1#
https://patents.justia.com/patent/20200184669
Drawings
http://www.freepatentsonline.com/20200184669.pdf

Seeing common themes week after week during patent digging reinforces to me this statement by Dipti Vachani

“The future of mobility and the safe, scalable deployment of advanced driver assistance systems to fully autonomous vehicles for mass production requires unprecedented industry collaboration,” said Dipti Vachani, senior VP at Arm’s automotive department.
https://eandt.theiet.org/content/articles/2019/10/arm-toyota-and-gm-join-forces-to-make-driverless-car-chips/

OMNIDIRECTIONAL SENSOR FUSION SYSTEM AND METHOD AND VEHICLE INCLUDING THE SAME
The present disclosure relates to an omnidirectional sensor fusion system and method and a vehicle including the same. The omnidirectional sensor fusion system includes a sensor track processing unit configured to receive recognition information from one or more sensors to generate a sensor track, a sensor track association determination unit configured to determine, based on the generated sensor track being located at an overlapping point of sensing regions of the one or more sensors, an association between a previous sensor fusion track and the sensor track, the sensor track association determination unit further configured to change sensor track information in response to the determined association and output a sensor fusion track, a sensor fusion track tracing unit configured to trace the output sensor fusion track, and a sensor fusion track maintenance unit configured to maintain the traced sensor fusion track.
https://worldwide.espacenet.com/publicationDetails/biblio?CC=US&NR=2020174113A1&KC=A1&FT=D&ND=3&date=20200604&DB=&locale=en_EP#

SENSOR FUSION TARGET PREDICTION DEVICE AND METHOD FOR VEHICLES AND VEHICLE INCLUDING THE DEVICE
A sensor fusion target prediction device and method for vehicles that can estimate a prediction value in the state in which no current measurement value is present, and a vehicle including the device are disclosed. The sensor fusion target prediction device may include a learning unit for receiving sensor fusion target information and learning one or more parameters based on the received sensor fusion target information, a prediction unit for, upon receiving current sensor fusion target information, calculating a prediction value of the current sensor fusion target information based on the one or more parameters learned by the learning unit, and a target tracking unit for determining whether the sensor fusion target information is received and tracking a target using the prediction value calculated by the prediction unit based on not receiving the sensor fusion target information.
https://worldwide.espacenet.com/publicationDetails/biblio?CC=US&NR=2020180646A1&KC=A1&FT=D&ND=3&date=20200611&DB=&locale=en_EP#
https://patents.justia.com/patent/20200180646
Drawings
http://www.freepatentsonline.com/20200180646.pdf

ENHANCED OBJECT DETECTION AND MOTION STATE ESTIMATION FOR A VEHICLE ENVIRONMENT DETECTION SYSTEM
The present disclosure relates to a vehicle environment detection system (2) arranged to detect at least one detection (6, 6'; 12, 13; 12', 13') and comprises at least one radar system (3), at least one camera device (4) and at least one processing unit (5). For each radar detection (6; 12, 13) at least one azimuth detection angle (Õ d , ¸ 1 , ¸ 2 ) with respect to an x-axis (7, 14) and a detected Doppler velocity component (v D ; v D1 , v D2 ) that is constituted by detected Doppler velocity with respect to the radar system (3) are obtained. For each detection, said processing unit (5) is arranged to: - Obtain corresponding camera detections (6'; 12', 13') for at least two image frames, constituting an optical flow. - Determine a velocity y-component (v y ; v y1 ', v y2 ') from said optical flow, where the velocity y-component (v y ; v y1 ', v y2 ') is constituted by a projection of a resulting velocity (v r ; v r1 , v r2 ; v r1 ', v r2 ) onto a y-axis (9, 15) that extends perpendicular to the x-axis (7, 14). - Determine the resulting velocity (v r ; v r1 , v r2 ; v r1 ', v r2 ') from the detected Doppler velocity component (v D ; v D1 , v D2 ) and the velocity y-component (v y ; v y1 , v y2 ; v r1 ', v r2 ').
https://worldwide.espacenet.com/publicationDetails/biblio?II=0&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200611&CC=US&NR=2020182992A1&KC=A1#
Drawings
http://www.freepatentsonline.com/20200182992.pdf

READINESS AND IDENTIFICATION BY GAZE AND/OR GESTURE PATTERN DETECTION
A vehicle control handoff system includes a controller comprising a processor and a non-transitory computer readable memory, one or more environment sensors and an imaging device communicatively coupled to the controller, and a machine-readable instruction set stored in the non-transitory computer readable memory of the controller. The machine-readable instruction set causes the system to: receive image data from at least one imaging device, receive one or more signals corresponding to an environment of a vehicle from the one or more environment sensors, define a gaze pattern comprising a first gaze direction corresponding to a first location within the environment of the vehicle, determine a first gaze based on the image data of the driver, determine whether the first gaze corresponds to at least one gaze direction of the gaze pattern, and transfer control of a vehicle operation from control by the controller to the driver in response to determining that the first gaze corresponds to the gaze pattern.
https://worldwide.espacenet.com/publicationDetails/biblio?II=3&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200611&CC=US&NR=2020183383A1&KC=A1#
https://patents.justia.com/patent/20200183383
Drawings
http://www.freepatentsonline.com/20200183383.pdf

INFRASTRUCTURE SENSOR DETECTION AND OPTIMIZATION METHOD
An infrastructure-based warning system, where the system is used as part of an intelligent intersection or intelligent road, and is used to detect various objects, such as vulnerable road users (VRUs) and vehicles. The system includes both cameras and radar, the operation of which is optimized based on which of the camera or radar is least affected by current conditions. This optimization includes the use of a marker, attached to infrastructure in the field of view of the detection device, such as a camera, to be optimized. If the camera accurately and consistently detects the marker, then camera detections of objects are weighted with more significance than the detection of objects using radar. If on the other hand, if the camera is unable to accurately detect the marker because of ambient conditions, then the greatest amount of confidence is placed on radar detection.
https://worldwide.espacenet.com/publicationDetails/biblio?CC=US&NR=2020175875A1&KC=A1&FT=D&ND=3&date=20200604&DB=&locale=en_EP#

Possible association with;
GM 2020-05-28
SYSTEMS AND METHODS FOR ENHANCED DISTANCE ESTIMATION BY A MONO-CAMERA USING RADAR AND MOTION DATA
Systems and methods for depth estimation of images from a mono-camera by use of radar data by: receiving, a plurality of input 2-D images from the mono-camera; generating, by the processing unit, an estimated depth image by supervised training of an image estimation model; generating, by the processing unit, a synthetic image from a first input image and a second input image from the mono-camera by applying an estimated transform pose; comparing, by the processing unit, an estimated three-dimensional (3-D) point cloud to radar data by applying another estimated transform pose to a 3-D point cloud wherein the 3-D point cloud is estimated from a depth image by supervised training of the image estimation model to radar distance and radar doppler measurement; correcting a depth estimation of the estimated depth image by losses derived from differences: of the synthetic image and original images; of an estimated depth image and a measured radar distance; and of an estimated doppler information and measured radar doppler information.
https://worldwide.espacenet.com/publicationDetails/biblio?CC=US&NR=2020167941A1&KC=A1&FT=D&ND=3&date=20200528&DB=&locale=en_EP#

Morning TLS,
Another example perhaps of how the inside/outside camera sensor fusion is becoming a safety platform architecture standard necessary to feed the ice, fog and cloud levels of 5G.

SYSTEMS, APPARATUS, AND METHODS FOR EMBEDDED ENCODINGS OF CONTEXTUAL INFORMATION USING A NEURAL NETWORK WITH VECTOR SPACE MODELING
Systems, Apparatuses and Methods for implementing a neural network system for controlling an autonomous vehicle (AV) are provided, which includes: a neural network having a plurality of nodes with context to vector (context2vec) contextual embeddings to enable operations of the of the AV; a plurality of encoded context2vec AV words in a sequence of timing to embed data of context and behavior; a set of inputs which comprise: at least one of a current, a prior, and a subsequent encoded context2vec AV word; a neural network solution applied by the at least one computer to determine a target context2vec AV word of each set of the inputs based on the current context2vec AV word; an output vector computed by the neural network that represents the embedded distributional one-hot scheme of the input encoded context2vec AV word; and a set of behavior control operations for controlling a behavior of the AV.

[0039] The sensor system 28 includes one or more sensing devices 40a-40n that sense observable conditions of the exterior environment and/or the interior environment of the vehicle 10 and generate sensor data relating thereto.
https://worldwide.espacenet.com/publicationDetails/biblio?CC=US&NR=2020050207A1&KC=A1&FT=D&ND=3&date=20200213&DB=&locale=en_EP#

TLS,
Noted, but relevant to me as this is part of a core team of authors who have been involved in 'gaze' related GM patents which is where I infer possible association.