Abstract: A method for guiding a user operating a requesting device includes identifying requesting parameters of the requesting device, where the requesting parameters include a location of a requesting device, a trajectory of a requesting device, or a combination thereof. The method includes generating one or more safety scores associated with one or more roadways based on vehicle behavior information associated with one or more vehicles, pedestrian behavior information associated with one or more roadside unit devices, or a combination thereof. The method includes determining a route of the requesting device based on the one or more safety scores and the requesting parameters and broadcasting the route to the requesting device.

Abstract: 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.

Abstract: A fluid mixing device that includes a housing having a fuel inlet and at least one primary orifice positioned at the inlet, wherein the at least one orifice configured to disperse a stream of fuel into a plurality of fuel droplets. The plurality of fuel droplets contact a fuel impingement surface to break up the plurality of fuel droplets into a plurality of smaller secondary droplets and create a thin film of secondary droplets on the impingement surface. At least one pressurized air channel delivers an airflow into contact with the secondary droplets. The secondary droplets pass through a plurality of secondary outlet orifices to exit the housing. A size of the plurality of secondary droplets is reduced when passing out of the plurality of secondary orifices.

Abstract: A metering system for a fuel atomizer includes a housing having a fuel inlet and an oxidizer inlet arranged coaxially, and an oxidizer metering device having a plurality of oxidizer channels, an oxidizer flow controller, and a fuel metering device. The oxidizer channels are spaced apart circumferentially in the housing and are arranged angled in at least one of a radially inward direction and a tangential direction to create a swirl of oxidizer flow in a mixing chamber of the fuel atomizer. The oxidizer flow controller is configured to control flow of oxidizer from the oxidizer inlet to the plurality of oxidizer channels. The fuel metering device is configured to control fuel flow from the fuel inlet to the mixing chamber.

Abstract: A pedestrian tracking system includes: a buffer or a memory configured to store a trajectory sequence of a pedestrian; a step attention module and a control module. The step attention module iteratively performs a step attention process to predict states of the pedestrian. Each iteration of the step attention process includes the step attention module: learning the stored trajectory sequence to provide time-dependent hidden states, reshaping each of the time-dependent hidden states to provide two-dimensional tensors; condensing the two-dimensional tensors via convolutional networks to provide convolutional sequences; capturing global information of the convolutional sequences to output a set of trajectory patterns represented by a new sequence of tensors; learning time-related patterns in the new sequence and decoding the new sequence to provide one or more of the states of the pedestrian; and modifying the stored trajectory sequence to include the predicted one or more of the states of the pedestrian.

Abstract: 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.

Abstract: A method of controlling fuel delivery to an engine includes providing a fluid atomizer, a mechanically driven air compressor, a start up air source, and an air valve coupled between the mechanically driven air compressor and the start up air source, charging the start up air source, delivering compressed air from the start up air source to the fluid atomizer, providing an initial air/fluid mixture with the fluid atomizer, and operating the air valve to direct compressed air from the mechanically driven air compressor to the fluid atomizer.

Abstract: 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.

Abstract: 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.

Abstract: A method for guiding a user operating a requesting device includes identifying requesting parameters of the requesting device, where the requesting parameters include a location of a requesting device, a trajectory of a requesting device, or a combination thereof. The method includes generating one or more safety scores associated with one or more roadways based on vehicle behavior information associated with one or more vehicles, pedestrian behavior information associated with one or more roadside unit devices, or a combination thereof. The method includes determining a route of the requesting device based on the one or more safety scores and the requesting parameters and broadcasting the route to the requesting device.

Abstract: 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.

Abstract: 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.

Abstract: A metering system for a fluid atomizer includes a housing, first and second metering members, and at least one solenoid. The housing includes a mixing chamber. The first metering member is operable to control flow of a first fluid to the mixing chamber. The second metering member is arranged coaxial with the first metering member and operable to control flow of a second fluid to the mixing chamber. The at least one solenoid is configured to operate at least one of the first and second metering members.

Abstract: A fluid mixing device that includes a housing having a fuel inlet and at least one primary orifice positioned at the inlet, wherein the at least one orifice configured to disperse a stream of fuel into a plurality of fuel droplets. The plurality of fuel droplets contact a fuel impingement surface to break up the plurality of fuel droplets into a plurality of smaller secondary droplets and create a thin film of secondary droplets on the impingement surface. At least one pressurized air channel delivers an airflow into contact with the secondary droplets. The secondary droplets pass through a plurality of secondary outlet orifices to exit the housing. A size of the plurality of secondary droplets is reduced when passing out of the plurality of secondary orifices.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: A fluid mixing device that includes a housing having a fuel inlet and at least one primary orifice positioned at the inlet, wherein the at least one orifice configured to disperse a stream of fuel into a plurality of fuel droplets. The plurality of fuel droplets contact a fuel impingement surface to break up the plurality of fuel droplets into a plurality of smaller secondary droplets and create a thin film of secondary droplets on the impingement surface. At least one pressurized air channel delivers an airflow into contact with the secondary droplets. The secondary droplets pass through a plurality of secondary outlet orifices to exit the housing. A size of the plurality of secondary droplets is reduced when passing out of the plurality of secondary orifices.

Abstract: 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.

Abstract: 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.