Abstract: A method includes receiving a request to create a map of a geographical area, obtaining geographical-area parameters representing characteristics of the area, subdividing, based on the geographical-area parameters, the area into a plurality of sub-regions, and obtaining, for each of a plurality of robots, corresponding robot parameters representing characteristics of the robot. For each particular sub-region, the method also includes determining, based on the geographical-area parameters, corresponding sub-region parameters representing characteristics of the particular sub-region, assigning, based on the sub-region parameters and the robot parameters, a particular robot to survey the particular sub-region, and obtaining corresponding survey data captured by the particular robot, the survey data representing a survey of the particular sub-region by the particular robot.

Abstract: A method for mitigating the risk of operating a vehicle using a contextualized risk factor includes receiving a first input from a plurality of first sensors within the vehicle and a second input from a plurality of second sensors outside the vehicle, determining a set of internal vehicle condition factors based on the first input, and weighing the internal vehicle condition factors, the second input, and the identity of a user within the vehicle to generate the contextualized risk factor. The identity and behavior of the user is recorded in a user profile which is added to a user profile database. When the contextualized risk factor is greater than a calibrated safety threshold, the vehicle may take at least one of an indirect measure or a direct measure. The vehicle may also send an alert to a third-party as to the presence of an unsafe driving environment.

Abstract: A system for CI/CD of AI/ML based components includes a cloud infrastructure which receives multiple new requirements from a vehicle designer or a developer, with the new requirements adapted for artificial intelligence/machine learning (AI/ML) based components of a vehicle. A dataset is provided. A metamorphic relations (MR) module receives input information from the dataset and sends MR information to the dataset. A components requirements database includes the new requirements in addition to existing requirements for the AI/ML based components. The MR module also receives components requirements data from the components requirements database and sends the MR information to the components requirements database. An AI/ML algorithm analyzes the input information from the dataset and prepares an updated component dataset.

Abstract: A control signal is issued to a turbo shaft actuator to rotate a turbine at a first turbine speed in response to an ignition turn on signal. The first turbine speed is different from a default turbine speed. The rotation of the turbine at the default turbine speed results in exhaust gas having a first exhaust gas temperature after the exhaust gas passes through the turbine to a catalyst brick of the vehicle. The rotation of the turbine at the first turbine speed results in the exhaust gas having a second exhaust gas temperature after the exhaust gas passes through the turbine to the catalyst brick. The second exhaust gas temperature is higher than the first exhaust gas temperature. When the catalyst temperature is greater than a catalyst light-off temperature a control signal is issued to the turbo shaft actuator to rotate the turbine at the default speed.

Abstract: Examples described herein provide a method for capturing and representing implicit knowledge to enhance artificial intelligence (AI)-assisted decision-making. The method includes capturing raw data from user interactions and extracting, from the raw data, implicit knowledge representations. The method further includes generating documented implicit knowledge by systematically documenting the implicit knowledge representations, including individual actions and decisions taken during specific tasks, in a knowledge management system. The method further includes categorizing the documented implicit knowledge to create structured knowledge representations. The method further includes integrating the structured knowledge representations into an AI system, wherein the AI system utilizes the implicit knowledge to improve quality of data inputs and enhance decision-making capabilities.

Abstract: A vehicle system includes a conversion module, a control module in communication with the conversion module, and an alert module in communication with the control module. The conversion module is configured to receive vehicle specific information and user manuals and generate a plurality of embeddings for the vehicle specific information and user manuals. The control module is configured to receive the plurality of embeddings and an input query from a user specific to a vehicle, identify vehicle information for the vehicle based on the input query, and generate a response specific to the vehicle based on the vehicle information and the plurality of embeddings in response to the input query. The alert module is configured to generate and transmit a notification including the response for the user. Other example vehicle systems and control methods are also disclosed.

Abstract: An ICE emission mitigation signal is received prior to normal operation of an ICE of a hybrid vehicle. A command is issued to at least partially open a throttle to enable air flow into an intake manifold. A command is issued to an electric motor system to rotate a crankshaft coupled to each of the cylinders. The reciprocating motion of a piston in each cylinder compresses air in a combustion chamber of the cylinder causing compressed air to flow out of the combustion chamber. The air flowing into the combustion chamber has a first temperature and the compressed air flowing out of the combustion chamber has a second temperature. The second temperature is higher than the first temperature. The compressed air flows from the combustion chamber of the cylinder to an exhaust manifold via an exhaust valve of the cylinder and from the exhaust manifold through a catalyst brick.

Abstract: Control signals are issued to open a wastegate, rotate a turbine, and turn on a catalyst heater disposed between the turbine and a catalyst in response to a trigger signal. The rotation of the turbine causes recirculated air flow in a recirculation flow path including an exhaust manifold, exhaust walls between the exhaust manifold and the turbine, a turbine housing, exhaust walls between the turbine and the wastegate, exhaust walls between the wastegate and the exhaust manifold, and exhaust walls between the turbine and the catalyst heater. Heat is transferred from the recirculated air heated by the catalyst heater to the exhaust manifold, the exhaust walls between the exhaust manifold and the turbine, the turbine housing, the exhaust walls between the turbine and the wastegate, the exhaust walls between the wastegate and the exhaust manifold, and the exhaust walls between the turbine and the catalyst heater.

Abstract: A system for incorporating user feedback in a large language model (LLM) based retrieval augmentation (RAG) tools includes an application for incorporating user feedback (UFA). The UFA receives an input to the LLM from a host device user, generates an LLM output as a response to the input, causes a system user to verify the LLM output and provide user feedback via a human-machine interface (HMI) of the host device, and in response to the user feedback, engages a performance tuning optimizer that modifies the LLM output by: revising domain knowledge, revising system prompts, and performing constrained regeneration of the LLM output. The performance tuning optimizer progressively reduces computational resource utilization, progressively increases computational efficiency, and progressively reduces reliance on human validators and user feedback over time, and wherein the LLM output is a command to one or more systems of the host device.

Abstract: A system for computing confidence scores for large language model (LLM) based retrieval augmentation (RAG) tools includes a host device having a controller. The controller executing programmatic control logic including an algorithm for computing confidence scores for LLM based RAG tools (CLR application). The CLR application receives an input to the LLM from a user and engages an ensemble retriever. The ensemble retriever determines a similarity between the input and predetermined data in the one or more databases. The ensemble retriever generates an output and an output confidence score. The CLR application then causes a human validator to prioritize and review the output in accordance with the output confidence score, where the output is a command to one or more systems of the host device. The system progressively reduces computational resource utilization, progressively increases computational efficiency, and progressively reduces reliance on the human validator over time.

Abstract: A computer-implemented method when executed by data processing hardware causes the data processing hardware to perform operations. The operations include collecting, via a health monitoring application, lubrication data at a crank phase of an engine of a vehicle, determining, at the crank phase, a pressure rise difference in oil pressure between a measured pressure and an estimated pressure, determining, via the health monitoring application, whether the measured pressure deviates from the estimated pressure at the crank phase, and generating, based on the measured pressure deviating from the estimated pressure at the crank phase, an alert.

Abstract: A method of fuel injector management based on cylinder knock detection includes: receiving an individual cylinder knock count from a first cylinder; determining whether a knock metric is initialized for the first cylinder, whether the knock metric deviates from an established baseline knock metric after multiple cycles when the knock metric is initialized for the first cylinder, whether the knock metric is decreasing with respect to the established baseline knock metric when the knock metric deviates from the established baseline knock metric, whether a fuel system memory indicates rich, lean or healthy when that the knock metric is decreasing with respect to the established baseline knock metric, whether a knock adaptation control indicates a reduction of knock for the first cylinder, and updating a health status of a fuel injector based on the indication of rich, lean, or healthy.

Abstract: A method of fuel injector management based on cylinder knock detection includes: receiving an individual cylinder knock count from a first cylinder; determining whether a knock metric is initialized for the first cylinder, whether the knock metric deviates from an established baseline knock metric after multiple cycles when the knock metric is initialized for the first cylinder, whether the knock metric is decreasing with respect to the established baseline knock metric when the knock metric deviates from the established baseline knock metric, whether a fuel system memory indicates rich, lean or healthy when that the knock metric is decreasing with respect to the established baseline knock metric, whether a knock adaptation control indicates a reduction of knock for the first cylinder, and updating a health status of a fuel injector based on the indication of rich, lean, or healthy.

Abstract: A system and method for locating a trailer coupler on a trailer to assist with the coupling of the trailer coupler to a vehicle hitch on a vehicle. The system includes a human-machine interface, a vehicle camera and a trailer camera, a mobile device application (App) with access to camera and mobile network a vehicle-to-infrastructure communication network, controllers, a memory, sensors, and a trailer detection and trajectory planning application. The application includes: initializing a data stream from the vehicle and trailer camera, capturing the data stream from the vehicle camera and from the trailer camera, determining key landmarks in the data stream, combining the key landmarks, determining a coupler location, computing a joint reference trajectory using the coupler location, and providing navigation assistance in real time based on the joint reference trajectory.

Abstract: A method and system of promoting operator focus through systematic positive reinforcement. The method includes receiving sensor data containing operator features; analyzing the operator features to determine the operator is in an alert state; determining a duration of alert time the operator remains in the alert state; and issuing a first level positive reinforcement feedback (1L PRF) in response to the operator remaining in the alert state equal to a sustained attention threshold (AThreshold). The method further includes issuing a second level positive reinforcement feedback (2L PRF) when the number of 1L PFR issued is equal to a first predetermined first value (K1). The method further includes issuing a third level positive reinforcement feedback (3L PRF) when the number of 2L PFR issued is equal to a second predetermined calibration value (K2).

Abstract: A trigger signal is received from a trigger signal source. A first control signal is issued to a wastegate actuator to open a wastegate in response to the trigger signal. A second control signal is issued to a turbo shaft actuator to rotate a turbine of a turbocharger. The rotation of the turbine causes recirculated air to flow in a recirculation flow path including an exhaust manifold, the turbine, an exhaust wall system, and the wastegate. The exhaust wall system includes a turbine housing of the turbine, exhaust walls disposed between the turbine and the wastegate, and exhaust walls disposed between the turbine and a catalyst brick. At least a portion of the recirculation flow path is adjacent to a side of the catalyst brick. Heat transfer occurs from the recirculated air to the exhaust wall system and to the catalyst brick via the side of the catalyst.

Abstract: A resource sharing marketplace platform for vehicle parking spots includes a back-office server including a controller adapted to run a plurality of integrated systems and a wireless communication module in communication with the controller, wherein, the resource sharing marketplace platform is adapted to receive, via the wireless communication module, a request from a user, collect, via the wireless communication module, data related to available registered parking spots from a network database of registered parking spots, and provide a response to the user including a sub-group of registered parking spots.

Abstract: A resource sharing marketplace platform for vehicle parking spots includes a back-office server including a controller adapted to run a plurality of integrated systems and a wireless communication module in communication with the controller, wherein, the resource sharing marketplace platform is adapted to receive, via the wireless communication module, a request from a user, collect, via the wireless communication module, data related to available registered parking spots from a network database of registered parking spots, and provide a response to the user including a sub-group of registered parking spots.

Abstract: An evaluation system that determines a network connectivity performance road map includes one or more back-end servers in wireless communication with a plurality of vehicles located in a geographic region by a wireless communication network and one or more road map databases in electronic communication with the one or more back-end servers. The one or more road map databases store a map data road graph of the geographic region including a plurality of nodes connected by a plurality of edges and one or more statistical measures corresponding to the plurality of overall performance metrics of the wireless communication network for each of the plurality of nodes. The one or more back-end servers determine the network connectivity performance road map of the geographical region based on the statistics corresponding to the plurality of overall performance metrics for each of the plurality of nodes and each of the plurality of edges.

Abstract: A system and method for locating a trailer coupler on a trailer to assist with the coupling of the trailer coupler to a vehicle hitch on a vehicle. The system includes a human-machine interface, a vehicle camera and a trailer camera, a mobile device application (App) with access to camera and mobile network a vehicle-to-infrastructure communication network, controllers, a memory, sensors, and a trailer detection and trajectory planning application. The application includes: initializing a data stream from the vehicle and trailer camera, capturing the data stream from the vehicle camera and from the trailer camera, determining key landmarks in the data stream, combining the key landmarks, determining a coupler location, computing a joint reference trajectory using the coupler location, and providing navigation assistance in real time based on the joint reference trajectory.