Abstract: A system for controlling sensor fusion can include a processor and a memory. The memory can store a sensor data adjustment module, a sensor fusion module, and a communications module. The sensor data adjustment module can include instructions that, when executed by the processor, cause the processor to: (1) calculate reliability scores for sensors and (2) multiply values of data, produced by the sensors, by the reliability scores to produce a scored input value. The sensor fusion module can include instructions that, when executed by the processor, cause the processor to cause the scored input value to be processed by a reservoir computing network in a manner that realizes the sensor fusion. The communications module can include instructions that, when executed by the processor, cause one or more readout values, based on the sensor fusion, to be communicated to an automated vehicle technology system to control movement of a vehicle.

Abstract: An example operation includes one or more of capturing, by a vehicle, internal audible data from an interior of the vehicle and external sensor data from an exterior of the vehicle, identifying, by the vehicle, a type and a tone of the internal audible data, determining that a driver of the vehicle is distracted based on the type and the tone of the internal audible data, determining, by the vehicle, that a dangerous situation related to the vehicle exists based on the external sensor data, and generating an alert within the vehicle based on the driver being distracted and the dangerous situation related to the vehicle.

Abstract: An example operation includes one or more of receiving eye movement data of an occupant in a vehicle and visual data of an oncoming object on a path toward the vehicle, generating eye movement tokens from the eye movement data and visual tokens from the visual data, executing at least one artificial intelligence (AI) model on the eye movement tokens and the visual tokens to identify data of a dangerous situation related to the vehicle, generating a recommendation to avoid the dangerous situation based on the data of the dangerous situation output by the AI model, and generating an alert within the vehicle based on the recommendation.

Abstract: Systems, methods, and other embodiments described herein relate to real-time risk reasoning within a vehicle. In one embodiment, a method includes acquiring sensor data about a surrounding environment of a vehicle. The method includes, responsive to identifying a risk to the vehicle from the sensor data, merging tokens that are features extracted from the sensor data into a condensed representation of a context of the surrounding environment associated with the risk. The method includes providing a driving recommendation according to the risk.

Abstract: Systems and methods described herein relate to receiving intended position data and actual position data regarding a vehicle, generating sensed position data regarding the vehicle, determining a weighting function based on an intended position loss and a sensed position loss, and determining a weighted position of the vehicle by applying the weighting function to the intended position data and the sensed position data.

Abstract: A method for managing moving agents is provided. The method comprises identifying goods agents, moving agents, and a plurality of requests within a predetermined area, generating a nodal graph including the moving agents, requests, and goods as vertices and edges defining relations between two vertices, obtaining actions for the moving agents by inputting the nodal graph to a reinforcement-learning based graphical neural network model stored in the moving agents, the reinforcement-learning based graphical neural network outputs the action for the moving agent in response to receiving the nodal graph, and instructing the moving agents to operate based on the actions to satisfy at least one of the plurality of requests.

Abstract: Systems, methods, and other embodiments described herein relate to forming and managing a platoon or convoy of unmanned aerial vehicles (UAVs). In one embodiment, a method includes receiving, from a plurality of UAVs. The intent messages indicate an air corridor and planned path for a respective UAV. The method also includes grouping, based on the air corridor and planned path in multiple intent messages, a set of UAVs into a platoon and generating a coordinated flight path and coordinated flight parameters for the platoon. The method also includes flying the set of UAVs based on the coordinated flight path and the coordinated flight parameters.

Abstract: A system and method for online learning adaptive cruise control (ACC) for driving a vehicle includes one or more non-transitory memories storing an ACC model pool comprising one or more ACC models, and one or more processors. The one or more processors operably causes the system to generate, using a trained meta algorithm and based on historical user inputs and user preferences of a user, one or more personalized ACC models associated with the user, and include the one or more personalized ACC models in the ACC model pool, determine whether the user triggers a real-time ACC disengagement, in response to determining that the user triggers the real-time ACC disengagement, select, based on real-time user inputs, a predicted ACC model from the ACC model pool including the one or more personalized ACC models, and engage the vehicle with the predicted ACC model.

Abstract: Systems and methods are provided for authenticating vehicle communications. The system can identify, by a roadway device, a vehicle traveling on a roadway and authenticate a proxy device associated with the vehicle. Sensor data can be transmitted to the vehicle based on the authentication of the proxy device, wherein the vehicle is operated to navigate the roadway based on the sensor data.

Abstract: An approach is provided for spatial aggregation for location based services. The approach involves, for example, determining a plurality of partitions for a geographic area. The approach also involves determining a set of destinations that is common to a first partition and a second partition of the plurality of partitions. The set of destinations are associated with a plurality of trips originating from first partition, the second partition, or a combination thereof. The approach further involves determining a statistical property of the plurality of trips between any of the set of destinations and the first partition, the second partition, or a combination thereof. The approach further involves merging the first partition with the second partition into the traffic analysis zone based on the statistical property.

Abstract: Systems and methods are provided for managing batteries for electrical vehicles utilizing varying power amounts. For example, a presently disclosed electric vehicle may comprise: (1) a battery providing electrical power for operation of the electric vehicle, wherein the operation of the electric vehicle comprises multiple phases that require a different amount of electrical power; and (2) one or more processors configured to: (a) predict one or more parameters associated with performance of the battery during the multiple phases for current operation of the electric vehicle, wherein the prediction is based on a machine learning model trained on data associated with performance of the battery during the multiple phases for previous operation of the electric vehicle; and (b) based on the prediction, dynamically adjust electrical power provided by the battery during one of the multiple stages for the current operation of the electric vehicle to manage the one or more parameters.

Abstract: Systems, methods, and other embodiments described herein relate to monitoring the deviation of system properties for a PRC from environmental factors and mitigating the deviation. In one embodiment, a method includes monitoring system properties of a PRC that predicts a parameter for a vehicle environment during a task, and the PRC is associated with a machine learning (ML) model that outputs the parameter. The method also includes predicting a PRC state and a reservoir drift using the system properties. The method also includes mitigating PRC degradation associated with the reservoir drift by switching from the PRC to a computation framework, and the computation framework calculates the parameter using the ML model.

Abstract: Systems and methods for detecting one or more approaching vehicles include one or more processors and an infrastructure camera operable to capture one or more images of surroundings of an ego vehicle. The surroundings include a ramp, one or more lanes of a freeway, and the one or more approaching vehicles, and the ramp and the lanes share at least one merging point. The one or more processors operable to transform the one or more images of surroundings to a bird's eye view of the surroundings, generate a static segmentation map and one or more dynamic objects in the static segmentation map based on the bird's eye view, predict a lane occupancy of the ramp and the lanes based on range estimation of the ego vehicle and the one or more dynamic objects, and transmit information about the predicted lane occupancy to the ego vehicle.

Abstract: A learning-based lane change prediction algorithm, and systems and methods for implementing the algorithm, are disclosed. The prediction algorithm evaluates the driving behaviors of a target human driver and predicts lane change maneuvers based on those personalized driving behaviors. The algorithm may include an online lane change decision prediction phase and an offline prediction training and cost function recovery phase. During the offline training phase, a machine learning model may be trained based on historical vehicle states. During the online validation phase, driving data may be collected and fed to the trained model to predict a driver's lane change maneuver, identify potential vehicle trajectories, and determine a most probable vehicle trajectory based on a driver's cost function recovered during the offline phase.

Abstract: Systems, methods, and other embodiments described herein relate to guiding a user travelling along a path. In one embodiment, a method includes predicting, by a processor, a behavior of a user based on at least sensor data received by the processor. The user is travelling on a pedestrian path. The method further includes, in response to a predicted behavior, controlling a guide, by the processor, to output the guide along the pedestrian path to direct the user.

Abstract: Systems, methods, and other embodiments described herein relate to providing navigational guidance to a pedestrian on infrastructure elements or vehicles in the vicinity of the pedestrian based on the pedestrian being identified as unfamiliar with an environment. In one embodiment, a method includes determining that a pedestrian is in an unfamiliar area based on sensor data that characterizes the pedestrian. The method also includes acquiring a navigational instruction presented on a user device of the pedestrian. The method further includes presenting navigational assistance on an electronic display in a vicinity of the pedestrian responsive to an indication that the pedestrian is in the unfamiliar area. The navigational assistance is based on the navigational instruction.

Abstract: System, methods, and other embodiments described herein relate to improving the safety of pedestrians at a road crossing. In one embodiment, a method includes acquiring sensor data about a pedestrian and a vehicle in surroundings of a road crossing. The method further includes identifying an intention to cross the road crossing of the pedestrian and a driving behavior of the vehicle. The method additionally includes determining a safety condition for the pedestrian to cross the road crossing based, at least in part, on the driving behavior. Moreover, the method includes controlling at least one lighting mechanism of the road crossing according to the safety condition.

Abstract: Minimizing signaling traffic between a User Plane (UP) and a Control Plane (CP), where Policy and Charging Function/Policy and Charging Rule Function (PCF/PCRF) software transmits a first and a second Policy and Charging Control rule (PCCRule1 and PCCRule2) to CP equipment. The CP equipment installs both PCCRule1 and PCCRule2 on UP equipment as UPRule1 and UPRule2 respectively, where UPRule1 is set as active during a first time period and the UPRule2 set as active during a second time period. User Plane Function (UPF) software matching data traffic with a Packet Detection Rule (PDR) to generate identified traffic during the first and second time periods and automatically redirecting data traffic to a predetermined location at the expiration of the first and second time periods respectively. UPRule1 and UPRule2 are automatically enabled and disabled alternatively after expiration of their respective timers by the UPF software.

Abstract: Systems, methods, and other embodiments described herein relate to generating audiovisual and virtual content that are interesting to occupants about a geographic area during vehicle travel using adaptive timing. In one embodiment, a method includes detecting features about an area surrounding a vehicle during vehicle travel using sensor data. The method also includes transitioning a mode for the vehicle using the features and occupant parameters. The method also includes generating audiovisual content and virtual information of a view within the area for the mode using a time sequence. The method also includes adapting an environment of the vehicle using the audiovisual content, the virtual information, and the occupant parameters.

Abstract: Systems and methods are provided for platoon formation. The systems and methods may receive a platoon intent message from a first vehicle. A first location, first destination, and first high occupancy lane (HOL) price of the first vehicle may be determined from the platoon intent message. A second vehicle with a second platoon intent message comprising a second location and second destination that are within a location threshold and destination threshold of the first location and first destination of the first vehicle may be identified. A second HOL price of the second vehicle based on the second platoon intent message may be determined. It may be determined that the first HOL price of the first vehicle and the second HOL price of the second vehicle are above a price threshold. Upon such a determination, a platoon between the first and second vehicles may be established.