Hitachi Astemo Ltd.

Hitachi, Ltd.

Hitachi Automotive Systems, Ltd.

Hitachi Astemo Americas, Inc.

Subrata Kumar Kundu

Naveen Kumar Bangalore Ramaiah

Yashodeep Dilip Lonari

Xiaoliang Zhu

Akshay Gokhale

Yoichi Iihoshi

Takashi Okada

Yuuki Okuda

Yuto Imanishi

Zifu Wang

Hiroaki Itsuji

Xunfei Zhou

Lars Watts

Zhiyi Su

Paul Liu

In some examples, a vehicle is able to communicate with a computing device over a network. The vehicle includes a processor configured to determine a future driving condition for the vehicle, and further determine that the future driving condition corresponds to a past accident condition. The processor receives, from the computing device, verification data for at least one diagnostic pattern corresponding to the past accident condition. The processor executes an artificial intelligence (AI) algorithm using the verification data corresponding to the at least one diagnostic pattern. Based on determining that an output of the AI algorithm does not correspond to an expected output for the verification data, the processor performs at least one action.

Detecting anomalies in vehicle artificial intelligence systems

In some examples, a system receives sensor data from sensors on board a vehicle. Based at least on the sensor data indicating an anomaly has occurred and is affecting a travel path of the vehicle, an uncertainty threshold is compared with an uncertainty value associated with a prediction model. For instance, the uncertainty value may be indicative of a difference between a predicted value predicted by the prediction model and an actual measured value related to at least one operation parameter of the vehicle. Based at least on determining that the anomaly has occurred and that the uncertainty value is within the uncertainty threshold, sending, by the system, a communication for obtaining an updated prediction model.

Verification of vehicle prediction function

In some examples, a service computing device receives, from a vehicle computing device onboard a vehicle, a communication including sensor data obtained from at least one sensor onboard the vehicle. Based on the communication, the service computing device determines a transmission delay corresponding to a difference between a time when the vehicle sent the communication and a time when the communication was received. Based on the communication, the service computing device determines a trajectory of the vehicle on a travel route. Based on the sensor data, transmission delay, wind direction and magnitude, surrounding objects, and trajectory, the service computing device determines vehicle control information for the vehicle. The service computing device sends, to the vehicle, based at least on the vehicle control information, at least one instruction causing the vehicle to perform at least one control operation for traversing one or more locations associated with the trajectory of the vehicle.

Wind and transmission delay management for connected vehicles

A system comprising at least one hardware processor for updating a cloud-based road anomaly database is disclosed, wherein the system receives information from a vehicle regarding an object detected by one or more sensors of the vehicle, the information may include a location and/or a size of the detected object; compares the location and/or the size of the first detected object against data stored in a road feature database regarding the first detected object; determines, based on comparing the location and/or the size, an accuracy score associated with the first detected object and the second detected object; and updates the cloud-based road anomaly database with the received information for the second detected object based on the associated accuracy score being higher than at least one of a threshold accuracy score or an accuracy score associated with corresponding object information stored in the cloud-based road anomaly database.

Method and systems for detection accuracy ranking and vehicle instructions

In some examples, a system may determine a plurality of candidate routes between a source location and a destination location for a vehicle, and may segment each candidate route into multiple road segments. Further, the system may receive vehicle computing resource information and sensor configuration information for the vehicle. The system may determine that at least one of the sensor configuration or the computing resources on board the vehicle fails to satisfy a threshold associated with autonomous navigation of a road segment of a first candidate route of the plurality of candidate routes. The system may select, for the vehicle, the first candidate route based at least on determining that a computing device external to the vehicle is scheduled to perform at least one computational task for the vehicle to enable the vehicle to meet the threshold associated with autonomously navigating the road segment of the first candidate route.

Allocating resources for a vehicle

In some examples, a system may determine a plurality of candidate routes between a source location of a vehicle and a destination location for the vehicle. Further, the system may determine one or more respective observation zone volumes for each candidate route of the plurality of candidate routes. The system may determine a field of view (FOV) for one or more vehicle sensors onboard the vehicle. In addition, the system may select a route for the vehicle from the plurality of candidate routes based at least on comparing an overlap of the FOV with the respective observation zone volumes for the candidate routes.

Precautionary observation zone for vehicle routing

In some examples, a system may receive, from at least one camera of a vehicle, at least one image including a road. The system may further receive vehicle location information including an indication of a location of the vehicle. In addition, the system may receive at least one of historical information from a historical database, or road anomaly information, where the road anomaly information is determined from at least one of a road anomaly database or real-time road anomaly detection. Based on the at least one image, the indication of the location of the vehicle, and the at least one of the historical information or the road anomaly information, the system may generate at least one of a disparity map or a disparity image.

Data driven dynamically reconfigured disparity map

In some examples, a rotary electric machine includes a stator having a plurality of stator coils arranged in a circular pattern around a central opening configured for receiving a rotor. The rotary electric machine further includes a respective dedicated inverter circuit associated with each respective stator coil. For instance, each respective inverter circuit may be configured to convert direct current power to alternating current power to provide to the respective stator coil.

Rotary electric machine with selectable coil control

In some examples, one or more processors may receive at least one first visible light image and a first thermal image. Further, the processor(s) may generate, from the at least one first visible light image, an edge image that identifies edge regions in the at least one first visible light image. At least one of a lane marker or road edge region may be determined based at least in part on information from the edge image. In addition, one or more first regions of interest in the first thermal image may be determined based on at least one of the lane marker or the road edge region. Furthermore, a gain of a thermal sensor may be adjusted based on the one or more first regions of interest in the first thermal image.

Combining visible light camera and thermal camera information

In some examples, a system may determine a plurality of routes between a source location and a destination location. Further, the system may segment each route of the plurality of routes into multiple road segments. The system may determine a first field of view (FOV) for each road segment. In addition, the system may receive vehicle sensor configuration information for vehicle sensors on board a vehicle. The system may determine a second FOV for the vehicle sensors. Additionally, the system may select a route for the vehicle based at least on comparing the second FOV with the first FOV for a plurality of the road segments.

Vehicle routing using connected data analytics platform

In some examples, a system may receive location information. The system may determine at least one landmark based on the location information. In addition, the system may determine one or more current conditions for the at least one landmark. Further, the system may receive sensor configuration information. Based on the sensor configuration information and the one or more current conditions, the system may determine the detectability of the at least one landmark.

Determining landmark detectability

A system for dynamic image compression in autonomous vehicles with multiple cameras. The cameras of a vehicle may be prioritized based on various features, and different image compression techniques may be assigned to different cameras in the vehicle, based on the priorities of the cameras, to reduce overall processing load of the vehicle.

Dynamic image compression for multiple cameras of autonomous vehicles

In some examples, one or more processors of a vehicle may receive location field-of-view (FOV) data for an upcoming location on a route traversed by the vehicle. For instance, the one or more processors may select, based on the location FOV data, one or more sensors to activate on the vehicle for performing sensing in a direction of a field of view indicated by the location FOV data. In addition, the one or more processors may cause the vehicle to traverse the upcoming location with the one or more sensors activated on the vehicle for performing sensing in the direction of the FOV indicated by the location FOV data.

Reducing processing requirements for vehicle control

Example implementations described herein involve a system for predicting vehicle behavior with a higher efficiency which can reduce the number of sensors and the amount of data needed for vehicle control systems. Example implementations described herein can be used for any type of vehicle control system, such as a powertrain control system, an adaptive cruise control system, an autonomous driving system, because the target vehicle to be predicted can be replaced to a preceding vehicle, a surrounding vehicle, and an ego vehicle.

System for predicting vehicle behavior

Example implementations described herein are directed to depression detection on roadways (e.g., potholes, horizontal panel lines of a roadway, etc.) through using vision sensor to realize improved safety for advanced driver assistance systems (ADAS) and autonomous driving (AD). Example implementations described herein detect candidate depressions in the roadway in real time and adjust the control of the vehicle system according to the detected depressions.

Growing community of inventors

Canton, MI, United States of America

Subrata Kumar Kundu