Denso Corporation

Denso International America, Inc.

University of Cambridge

Hitachi, Ltd.

The University of Sheffield

Other

The University of Tokyo

The University of Newcastle Upon Tyne

Rajesh Kumar Malhan

Joseph Lull

Naohiro Sugiyama

Yuuichi Takeuchi

Tsuyoshi Yamamoto

Atsuo Watanabe

Takasumi Ohyanagi

Jeremy Rashid

C Mark Johnson

Florin Udrea

Toshiyuki Morishita

Wei Zhang

Cyril Buttay

Yuichi Takeuchi

Tsunenobu Kimoto

Hiroki Nakamura

Toshio Sakakibara

Hiroyuki Matsunami

Sebastian Fischmeister

Trong Duy Nguyen

Zaydoun Rawashdeh

Yuji Noguchi

Masaru Miyayama

Jeremy Suhail Rashid

Irina Nikitina

Konstantin Vassilevski

Alton Horsfall

Mark Crowley

Tishya Bhatia

Zhiyuan Du

Donghyun Shin

Jaspreet Sambee

Nicholas Wright

Anoop Pottammal

William Melek

Sriram Subramanian

Baris Fidan

Ami Woo

Sushrut Bhalla

Bismaya Sahoo

A warning system for warning vulnerable road users (VRUs) includes an edge computing device having a graphics processing unit (GPU), one or more sensors that acquire spatial-temporal data of road users, and one or more warning devices that output a warning to warn targeted VRUs of danger. The GPU uses one or more artificial intelligence (AI) algorithms to process the spatial-temporal data of the road users to predict a path, trajectory, behavior, and intent for the road users. The GPU then analyzes the predictions of the road users to determine convergences between the predictions to determine threat interactions and identify targeted VRUs. In response to determining threat interactions and identifying the targeted VRUs, the edge computing device outputs targeting instructions and warning response instructions to the one or more warning devices to deploy the one or more warning devices to warn the targeted VRUs.

Intersection infrastructure warning system

A system for predicting and interpreting bad driving behavior of a vehicle includes a first edge computing device that can acquire spatial-temporal data for the vehicle from one or more sensors that are part of traffic infrastructure. The first edge computing device includes a processor and instructions executable by the processor that execute unsupervised deep learning methods on the data from the sensors to cluster the data into segments and integrate a language model with the deep learning method to output the bad driving behavior in a natural language. The instructions further include normalizing the data, processing the data with a first artificial neural network (ANN) to output a first vector, processing the clustered data segments with a second ANN to output a second vector, concatenating the vectors into a single vector, and processing the single vector with a third ANN to output a predicted bad driving behavior of the vehicle.

System and method for predicting and interpreting driving behavior

The present disclosure is directed toward a method that includes acquiring current dynamic characteristics of a moving object about an un-signalized intersection, determining a dynamic traffic flow of the un-signalized intersection based on the current dynamic characteristics to determine a position of the moving object about the un-signalized intersection, and predicting future dynamic characteristics of the moving object based on the dynamic traffic flow and a predictive control. The future dynamic characteristics includes a predicted position of the moving object at a predefined time in the future. The method further calculates an entry parameter for a vehicle about an entrance of the un-signalized intersection based on the dynamic traffic flow and the predicted future dynamic characteristics and notifies the vehicle of the entry parameter.

Method for un-signalized intersection traffic flow management

A system for predicting and interpreting driving behavior of a vehicle includes a first edge computing device that can acquire spatial-temporal data for the vehicle from one or more sensors that are part of traffic infrastructure. The first edge computing device includes a processor and instructions executable by the processor that execute unsupervised deep learning methods on the data from the sensors to cluster the data into segments and integrate a language model with the deep learning method to output driving behavior in a natural language. The instructions further include normalizing the data, processing the data with a first artificial neural network (ANN) to output a first vector, processing the clustered data segments with a second ANN to output a second vector, concatenating the vectors into a single vector, and processing the single vector with a third ANN to output a predicted driving behavior of the vehicle.

A RLP system for a host vehicle includes a memory and levels. The memory stores a RLP algorithm, which is a multi-agent collaborative DQN with PER algorithm. A first level includes a data processing module that provides sensor data, object location data, and state information of the host vehicle and other vehicles. A second level includes a coordinate location module that, based on the sensor data, the object location data, the state information, and a refined policy provided by the third level, generates an updated policy and a set of future coordinate locations implemented via the first level. A third level includes evaluation and target neural networks and a processor that executes instructions of the RLP algorithm for collaborative action planning between the host and other vehicles based on outputs of the evaluation and target networks and to generate the refined policy based on reward values associated with events.

Multi-level collaborative control system with dual neural network planning for autonomous vehicle control in a noisy environment

An infrastructure edge device is configured to generate and broadcast a proxy safety message regarding a moving object. A method for a subject vehicle to process the proxy safety message includes determining whether data provided in the proxy safety message is valid based on sensor data from one or more sensors disposed about the subject vehicle, content of the proxy safety message, or a combination thereof. The method further discards the proxy safety message in response to the proxy safety message including invalid data.

Method and system for generating and processing safety messages for vehicle-to-everything communication

The present disclosure provides an auto-braking system which includes a braking device, a receiver, and a controller. The controller includes a determining portion, a verifying portion and an executing portion. The determining portion determines whether a vehicle will violate a red signal of the traffic light based on the traffic light state information. The verifying portion verifies the traffic light state information is valid by comparing the traffic light state information with the image of the traffic light captured by the sensor. The executing portion executes a first braking control to slow the vehicle at a first deceleration rate when the determining portion determines that the vehicle will violate a red signal. The executing portion executes a second braking control to slow the vehicle at a second deceleration rate to stop at a specified position when the verifying portion verifies that the traffic light state information is valid.

Auto-braking system for vehicle and method for auto-braking vehicle

A SiC semiconductor device includes: a SiC substrate made of intrinsic SiC having semi-insulating property; first and second conductive type SiC layers disposed in the substrate; an insulation separation layer made of intrinsic SiC for isolating the first conductive type SiC layer from the second conductive type SiC layer; first and second conductive type channel JFETs disposed in the first and second conductive type SiC layers, respectively. The first and second conductive type channel JFETs provide a complementary junction field effect transistor. Since an electric element is formed on a flat surface, a manufacturing method is simplified. Further, noise propagation at high frequency and current leakage at high temperature are restricted.

SiC semiconductor device having CJFET and method for manufacturing the same

A wide band gap semiconductor device having a JFET, a MESFET, or a MOSFET mainly includes a semiconductor substrate, a first conductivity type semiconductor layer, and a first conductivity type channel layer. The semiconductor layer is formed on a main surface of the substrate. A recess is formed in the semiconductor layer in such a manner that the semiconductor layer is divided into a source region and a drain region. The recess has a bottom defined by the main surface of the substrate and a side wall defined by the semiconductor layer. The channel layer has an impurity concentration lower than an impurity concentration of the semiconductor layer. The channel layer is formed on the bottom and the side wall of the recess by epitaxial growth.

Semiconductor device and method of manufacturing the same

A silicon carbide semiconductor device having a JFET or a MOSFET includes a semiconductor substrate and a trench. The semiconductor substrate has a silicon carbide substrate, a drift layer on the silicon carbide substrate, a first gate region on the drift layer, and a source region on the first gate region. The trench has a strip shape with a longitudinal direction and reaches the drift layer by penetrating the source region and the first gate region. The trench is filled with a channel layer and a second gate region on the channel layer. The source region is not located at an end portion of the trench in the longitudinal direction.

Silicon carbide semiconductor device and method of manufacturing the same

A semiconductor device with a JFET is disclosed. The semiconductor device includes a trench and a contact embedded layer formed in the trench. A gate wire is connected to the contact embedded layer, so that the gate wire is connected to an embedded gate layer via the contact embedded layer. In this configuration, it is possible to downsize a contact structure between the embedded gate layer and the gate wire.

Semiconductor device with junction field-effect transistor and manufacturing method of the same

A power electronic package includes: first and second high thermal conductivity insulating non-planar substrates; and multiple semiconductor chips and electronic components between the substrates. Each substrate includes multiple electrical insulator layers and patterned electrical conductor layers connecting to the electronic components, and further includes multiple raised regions or posts, which are bonded together so that the substrates are mechanically and electrically connected. The number, arrangement, and shape of the raised regions or posts are adjusted to have mechanical separation between the substrates. The electrical conductor layers are separated and isolated one another so that multiple electric circuits are provided on at least one of the substrates.

Power electronic package having two substrates with multiple semiconductor chips and electronic components

A semiconductor device includes: a substrate; and depletion and enhancement mode JFETs. The depletion mode JFET includes: a concavity on the substrate; a channel layer in the concavity; a first gate region on the channel layer; first source and drain regions on respective sides of the first gate region in the channel layer; first gate, source and drain electrodes. The enhancement mode JFET includes: a convexity on the substrate; the channel layer on the convexity; a second gate region on the channel layer; second source and drain regions on respective sides of the second gate region in the channel layer; second gate, source and drain electrodes. A thickness of the channel layer in the concavity is larger than a thickness of the channel layer on the convexity.

Semiconductor device having D mode JFET and E mode JFET and method for manufacturing the same

A wide band gap semiconductor device has a transistor cell region, a diode forming region, an electric field relaxation region located between the transistor cell region and the diode forming region, and an outer peripheral region surrounding the transistor cell region and the diode forming region. In the transistor cell region, a junction field effect transistor is disposed. In the diode forming region, a diode is disposed. In the electric field relaxation region, an isolating part is provided. The isolating part includes a trench dividing the transistor cell region and the diode forming region, a first conductivity-type layer disposed on an inner wall of the trench, and a second conductivity-type layer disposed on a surface of the first conductivity-type layer so as to fill the trench. The first conductivity-type layer and the second conductivity-type layer provide a PN junction.

Wide band gap semiconductor device including junction field effect transistor

A ceramic material has a perovskite structure and is represented by formula of (1&#x2212;x)ABO-xYZO. In the formula, 'x' is a real number that is greater than 0 and is less than 1 each of 'A,' &#x201c;B,&#x201d; &#x201c;Y,&#x201d; and &#x201c;Z&#x201d; is one or more kinds selected from a plurality of metal ions M other than a Pb ion and alkali metal ions, &#x201c;A&#x201d; is bivalent, &#x201c;B&#x201d; is tetravalent, &#x201c;Y&#x201d; is trivalent or combination of trivalent metal ions, and &#x201c;Z&#x201d; is bivalent and/or trivalent metal ions, or a bivalent and/or pentavalent metal ions.

Ceramic material and electronic device

Growing community of inventors

Nagoya, Japan

Rajesh Kumar Malhan