Abstract: The performance of a neural network (NN) and/or deep neural network (DNN) can limited by the number of operations being performed as well as management of data among the various memory components of the NN/DNN. A sparsity-inducing regularization optimization process is performed on a machine learning model to generate a compressed machine learning model. A machine learning model is trained using a first set of training data. A sparsity-inducing regularization optimization process is executed on the machine learning model. Based on the sparsity-inducing regularization optimization process, a compressed machine learning model is received. The compressed machine learning model is executed to generate one or more outputs.

Abstract: Techniques for creating, sharing, and using bundles (also referred to as packages) in a multi-tenant database are described herein. The bundle includes an interface directly accessible to the consumer account and a hidden bundle schema not directly accessible by the consumer account. A consumer account can upgrade from a first version to a second version by way of an intermediate version.

Abstract: A method performed by a processor of a computing system is described herein, where the method includes obtaining an image that includes an object having a shape, where a boundary of the shape of the object in the digital image is labeled in the digital image. The method also includes computing an encoding for the shape, where computing the encoding for the shape includes partitioning the shape into multiple partitions. Computing the encoding for the shape further includes, for the multiple partitions, computing angle-based contour descriptors that represent boundaries of the partitions, where the encoding for the shape of the object is based upon the angle-based contour descriptors.

Abstract: Provided herein is technology relating to a function allocation system (FAS) that deploys artificial intelligence models for a connected automated highway (CAH) system and a connected automated vehicle (CAV) system to distribute driving intelligence between the CAV system and the CAH system. The FAS comprises a communication module, a data module, and a computing module. The computing module is configured to analyse scenes using sensing data, determine automated driving function requirements, deploy function allocation methods, and analyse CAH system and CAV system functions. The function allocation methods provide analysis, guidance, and optimization capabilities for sensing, decision-making, and control functions. The FAS allocates automated driving functions to the CAV system and the CAH system based on their respective intelligence levels.

Abstract: Technologies described herein relate to training and compressing a computer-implemented model. To that end, an untrained computer-implemented model is obtained, where the untrained computer-implemented model is to be trained and compressed. The untrained computer-implemented model includes an operator that comprises a structure. Further, training data is obtained, where the training data is to be employed to train the computer-implemented model. Upon receipt of a request from a user, the untrained computer-implemented model is trained and compressed based upon the training data. The untrained computer-implemented model is trained and compressed without further input from the user, such that a trained and compressed computer-implemented model is generated. The trained and compressed model does not include the structure.

Abstract: The invention provides a roadside computing system (RCS), or an edge computing system, for an autonomous vehicle. The RCS comprises a hierarchy of roadside unit (RSU) and an onboard unit (OBU) in an individual vehicle. The RSU comprises a data processing module and a communication module, and is capable of generating guidance information and targeted instructions for individual vehicle. The data processing module of the RSU comprises two processors: an External Object Calculating Module (EOCM) and an AI processing unit. Thus, the RCS utilizes roadside edge computing power and AI models to support autonomous driving for the vehicle. The OBU comprises a data processing module, a communication module, and a vehicle control module, and is capable of generating vehicle-specific targeted instruction for the vehicle based on guidance information and targeted instructions received from RSUs, and controlling the vehicle based on vehicle-specific targeted instruction.

Abstract: The invention presents a cloud-based model deployment and control system (CMDCS) for providing automated driving services. The CMDCS comprises a cloud-based platform, an onboard unit (OBU), and a Vehicle-to-System component. The cloud-based platform comprises a localization-enhancement subsystem and a cloud computing module. The CMDCS is configured to collect detectable data and undetectable data from vehicles, road, and cloud. Then, the CMDCS deploys a set of end-to-end AI models and methods for automated driving services, comprising sensing, prediction, planning, and control services. The AI models and methods are trained and optimized to process collected data for providing operating parameters for vehicles. Then, the vehicles can be effectively and efficiently controlled and operated by the CMDCS. In addition, the CMDCS is configured to generate and provide detailed time-sensitive vehicle specific control instructions.

Abstract: Systems and methods for generating object references with selectable scopes are provided. The systems and methods perform operations including calling, by a first entity, a reference generator function using one or more arguments associated with a database object that the first entity is authorized to access according to a first set of access privileges, the one or more arguments comprising a scope definition that defines persistence of a reference. The operations include obtaining, from the reference generator function, a reference to the database object, the reference persisting according to the scope definition. The operations include passing the reference to a second entity to enable the second entity to perform one or more database operations on the database object according to a second set of access privileges derived from the first set of access privileges.

Abstract: Techniques for executing show commands are described herein. A plurality of navigation steps is utilized, each navigation step corresponding to a different layer in a database structure and each navigation step including an operator to fetch items from a metadata database up to respective bounded limits. Dependency information is also fetched for objects of the specified object type in the show command. After a set of objects from the last layer are processed, memory for the navigation steps is flushed and the next set of objects are processed.

Abstract: Provided herein is an artificial intelligence-based mobile roadside intelligent unit (MRIU) for providing, supplementing, and/or enhancing the control and operation of autonomous vehicles in normal and long-tail scenarios. The MRIU comprises a computing module configured to provide supplemental computation capability for autonomous driving. The MRIU comprises a communication module to communicate and exchange data with a vehicle or a cloud. The MRIU provides prediction, decision-making, and/or control functions for autonomous driving. The MRIU provides edge computing capability for autonomous vehicles to train and operate artificial intelligence-based intelligent driving models in a distributed fashion. Specifically, an edge computing unit conducts data fusion and data feature extraction, provides prediction, formulates control strategies, generates vehicle control instructions, and/or distributes vehicle control information and/or instructions for an autonomous vehicle.

Abstract: The invention provides an autonomous vehicle and intelligent control (AVIC) system with distributed AI computing, which is a component of a Connected Automated Vehicle Highway (CAVH) system. This AVIC system is configured to realize training and application for distributed AI computing by providing automated vehicles (AVs) and/or connected automated vehicles (CAVs) with vehicle-specific control instructions comprising instructions for vehicle longitudinal and lateral position, speed, and steering and control. Detailed and time-sensitive vehicle-specific control instructions comprise control instructions for speed, spacing, lane designation, vehicle following, lane changing, and/or route guidance. Specifically, through the system, CAVs can be effectively and efficiently controlled by the AVIC system.

Abstract: The invention provides an autonomous vehicle and center guidance system (AVCGS) for drone/tele driving or digital twins by sending guidance instructions to an autonomous vehicle (AV) or a connected automated vehicle (CAV). The AVCGS is a component of a Connected Automated Vehicle Highway (CAVH) system. This AVCGS is configured to operate AVs or CAVs using a hierarchy of traffic control centers/units (TCCs/TCUs). The AVCGS comprises automatic or semi-automated computational modules, a TCC/TCU communication module, and/or an onboard unit (OBU) communication module and a vehicle control module. The AVCGS communicates with one or more entities. The vehicle-specific guidance instructions and information comprise vehicle maneuver, safety maintenance, traffic control/road condition, and special information. The AVCGS provides backup in case of any errors or failures. Specifically, through the AVCGS, AVs or CAVs can be effectively and efficiently operated.

Abstract: The invention provides systems and methods for an autonomous vehicle and center control system (AVCCS), which is a component of a Connected Automated Vehicle Highway (CAVH) system. The AVCCS is configured to realize drone/tele driving or digital twins by providing automated vehicles (AVs) or connected automated vehicles (CAVs) with vehicle-specific control instructions comprising instructions for vehicle longitudinal and lateral position, speed, and steering and control. Specifically, through the system, AVs or CAVs can be effectively and efficiently controlled by the AVCCS. In addition, the AVCCS is configured to provide vehicle-specific control instructions to AVs or CAVs and control them through a hierarchy of traffic control centers/units (TCCs/TCUs) or the combination of TCCs/TCUs and the onboard units (OBUs) with a vehicle control module, wherein said TCCs/TCUs are configured to fulfill vehicle maneuver tasks, monitor safety maintenance tasks, and take over if the system fails.

Abstract: This invention presents an automated driving system with distributed computing (ADS-DC). During the operation of a connected automated vehicle (CAV), some or all of its automated driving capabilities for sensing, prediction, planning, decision-making, or control may be downgraded due to long-tail events or malfunctions. The intelligent roadside toolbox (IRT) functions as an edge server or a cloud, and can supplement CAV's sensing functions, prediction and management functions, planning and decision-making functions, and vehicle control functions by providing customized, on-demand, and dynamic computing resources and functions to the CAV. In addition, the IRT computing functions provide the computation support for sensing, prediction, planning, decision-making, and/or control functions of said CAV. Namely, the IRT functions as an edge server or a cloud to provide processing, training or optimization of CAV driving models as well as facilitate the implementation of the driving models in the CAV.

Abstract: This invention presents a function allocation system for an autonomous vehicle (AV). During the operations of the AV, some or all of its automated driving capabilities or functions could be downgraded due to long-tail events or malfunctioning. The roadside intelligent infrastructure, or the cloud platform, could supplement some or all of AV's automated driving functions, including sensing, prediction and decision-making, and/or control functions. The function allocation system dynamically allocates these functions between AV and intelligent infrastructure, achieving a higher system intelligence level S than the downgraded vehicle intelligence level V. In addition, a function allocation system could dynamically allocate sensing, prediction and decision-making, and/or control functions between AV and a cloud platform. This invention also presents a function integration system or a fusion system for an AV.

Abstract: This technology relates to autonomous vehicle (AV) control systems tailored for critical points of a partially instrumented infrastructure. The first system integrates an onboard unit (OBU) and communication modules to interact with roadside units (RSUs) or a cloud platform, delivering time-sensitive control instructions to vehicles at critical points. The OBUs execute these instructions for driving tasks. The second system combines an OBU with a cloud platform, leveraging cloud services for enhanced functionality like storage and computing. It adapts to diverse critical point scenarios, employing proactive incident prediction and rapid detection methods for optimized performance.

Abstract: A first indication that a first product was delivered via a first delivery service to a first location corresponding to a first user associated with a first user account of a service platform is received by a processing device. A second indication that a second product was delivered via a second delivery service to a second location corresponding to a second user associated with a second user account is received by the processing device. The processing device determines that first product and the second product were delivered within a first time period associated with the event based on the first indication and the second indication. Responsive to determining that the first product and the second product were delivered within the first time period, a video conference for the event is initiated between a plurality of participants comprising the first user and the second user.

Abstract: The invention provides a vehicle AI computing system (VACS) that supports autonomous driving through an Onboard Unit (OBU) for vehicle-based computing and distributed computing based on vehicle road-cloud. The vehicle-based computing can effectively complete various computational tasks by using onboard computing resources. The distributed computing allows the vehicle to work in collaboration with roadside units (RSUs) and/or the cloud to effectively complete various computational tasks. The VACS features an OBU with a sensing module, a communication module, and a data processing module that integrates data from vehicle sensors, RSUs, and the cloud. The OBU also includes a vehicle control module that helps control the vehicle based on the data of RSU and cloud. The VACS leverages high performance computation resources to implement end to end driving tasks including sensing, prediction, planning and decision making, and control.

Abstract: The invention provides an autonomous vehicle (AV) system with an artificial intelligence (AI) system for automated vehicle control and traffic operations. This AI system comprises a computation component configured to provide sensing, behavior prediction and management, decision making, and vehicle control for the vehicle. This AI system is configured to receive local knowledge, information, data, and models from a roadside unit (RSU) or a cloud to improve performance and efficiency of the vehicle. The AI system is configured to train models with heuristic parameters obtained from a local traffic control center/traffic control unit (TCC/TCU) or the cloud to provide an improved model. The AI system is configured to provide intelligence coordination to distribute intelligence among vehicles, RSUs and cloud. The system also provides localized self-evolving artificial intelligence.

Abstract: Provided herein is technology relating to intelligent transportation systems and automated vehicles and particularly, but not exclusively, to function allocation systems and methods for a connected automated vehicle highway system that provides transportation management and operations and vehicle control for connected and automated vehicles.