Abstract: Methods and systems for training a trajectory prediction model and performing a vehicle maneuver include encoding a set of training data to generate encoded training vectors, where the training data includes trajectory information for agents over time. Trajectory scenarios are simulated based on the encoded training vectors, with each simulated trajectory scenario representing one or more agents with respective agent trajectories, to generate simulated training data. A predictive neural network model is trained using the simulated training data to generate predicted trajectory scenarios based on a detected scene.

Abstract: Navigational systems and methods include building a topological graph of an environment using nodes that represent locations in the space and associated directions, with frontiers associated with particular nodes and directions within the topological graph. An action is determined using a policy trained with an action reward function that weighs exploration to find new objects and moving objects to a goal. An agent navigates within the environment in accordance with the determined action.

Abstract: Systems and methods are provided for multi-modal test-time adaptation. The method includes inputting a digital image into a pre-trained Camera Intra-modal Pseudo-label Generator, and inputting a point cloud set into a pre-trained Lidar Intra-modal Pseudo-label Generator. The method further includes applying a fast 2-dimension (2D) model, and a slow 2D model, to the inputted digital image to apply pseudo-labels, and applying a fast 3-dimension (3D) model, and a slow 3D model, to the inputted point cloud set to apply pseudo-labels. The method further includes fusing pseudo-label predictions from the fast models and the slow models through an Inter-modal Pseudo-label Refinement module to obtain robust pseudo labels, and measuring a prediction consistency for the pseudo-labels.

Abstract: A method for training a model for face recognition is provided. The method forward trains a training batch of samples to form a face recognition model w(t), and calculates sample weights for the batch. The method obtains a training batch gradient with respect to model weights thereof and updates, using the gradient, the model w(t) to a face recognition model what(t). The method forwards a validation batch of samples to the face recognition model what(t). The method obtains a validation batch gradient, and updates, using the validation batch gradient and what(t), a sample-level importance weight of samples in the training batch to obtain an updated sample-level importance weight. The method obtains a training batch upgraded gradient based on the updated sample-level importance weight of the training batch samples, and updates, using the upgraded gradient, the model w(t) to a trained model w(t+1) corresponding to a next iteration.

Abstract: A method for driving path prediction is provided. The method concatenates past trajectory features and lane centerline features in a channel dimension at an agent's respective location in a top view map to obtain concatenated features thereat. The method obtains convolutional features derived from the top view map, the concatenated features, and a single representation of the training scene the vehicle and agent interactions. The method extracts hypercolumn descriptor vectors which include the convolutional features from the agent's respective location in the top view map. The method obtains primary and auxiliary trajectory predictions from the hypercolumn descriptor vectors. The method generates a respective score for each of the primary and auxiliary trajectory predictions.

Abstract: Methods and systems for training a trajectory prediction model and performing a vehicle maneuver include encoding a set of training data to generate encoded training vectors, where the training data includes trajectory information for agents over time. Trajectory scenarios are simulated based on the encoded training vectors, with each simulated trajectory scenario representing one or more agents with respective agent trajectories, to generate simulated training data. A predictive neural network model is trained using the simulated training data to generate predicted trajectory scenarios based on a detected scene.

Abstract: Systems and methods for demand charge minimized operations while extending battery life, including determining a demand charge threshold based on received historical data. The systems and methods further including generating a charging pattern for a battery array from the historical. The systems and methods further including calculating a charging schedule for the battery array based on the demand charge threshold, a short term load profile, and the charging pattern. The charging schedule being calculated to follow the charging pattern without exceeding the demand charge threshold and transmitting commands to a battery controller in accordance with to the charging schedule.

Abstract: A computer-implemented method, system, and computer program product are provided for demand charge management. The method includes receiving an active power demand for a facility, a current load demand charge threshold (DCT) profile for the facility, and a plurality of previously observed load DCT profiles. The method also includes generating a forecast model from a data set of DCT values based on the current load DCT profile for the facility and the plurality of previously observed load DCT profiles. The method additionally includes forecasting a monthly DCT value for the facility using the forecast model. The method further includes preventing actual power used from a utility from exceeding the next month DCT value by discharging a battery storage system into a behind the meter power infrastructure for the facility.

Abstract: A computer-implemented method, system, and computer program product are provided for demand charge management. The method includes receiving an active power demand for a facility, a current load demand charge threshold (DCT) profile for the facility, and a plurality of previously observed load DCT profiles. The method also includes generating a data set of DCT values based on the current load DCT profile for the facility and the plurality of previously observed load DCT profiles. The method additionally includes forecasting a next month DCT value for the facility using the data set of DCT values. The method further includes preventing actual power used from a utility from exceeding the next month DCT value by discharging a battery storage system into a behind the meter power infrastructure for the facility.

Abstract: A computer-implemented method is provided for controlling a Battery Energy Storage System (BESS) having a battery set and connected to a Photovoltaic (PV) panel set. The method includes enforcing, by a processor device, a multi-objective Model Predictive Control (MPC) optimization on the BESS. The multi-objective MPC optimization includes a first objective of reducing a possibility of Demand Charge Threshold violations by minimal DCT increments which provide a higher demand charge savings, a second objective of improving a robustness of the BESS against energy forecast errors by increasing a State Of Charge (SOC) of the battery set, and a third objective of maximizing PV-utilization. The method further includes controlling, by the processor device, charging and discharging of the BESS in accordance with the multi-objective MPC optimization to meet the first, second, and third objectives.

Abstract: Systems and methods for adaptive demand charge management in a behind the meter energy management system. The system and method includes determining, in a first layer, an initial demand charge threshold (DCT), for a first period, based on historical DCT profiles, and generating recursively, in a second layer, a forecast of a power demand for a second period, wherein the second period is a subset of the first period. Further included is combining the first layer and the second layer to recursively modify the initial DCT with a DCT adjustment value to generate a modified DCT, wherein the DCT adjustment value is optimized according to the forecast of power demand for the second period, and controlling batteries according to the modified DCT, wherein the batteries are discharged if power demand is above the modified DCT, and the batteries are charged if the power demand is below the modified DCT.

Abstract: A computer-implemented method, system, and computer program product are provided for demand charge management. The method includes receiving an active power demand for a facility, a current load demand charge threshold (DCT) profile for the facility, and a plurality of previously observed load DCT profiles. The method also includes generating a data set of DCT values based on the current load DCT profile for the facility and the plurality of previously observed load DCT profiles. The method additionally includes forecasting a next month DCT value for the facility using the data set of DCT values. The method further includes preventing actual power used from a utility from exceeding the next month DCT value by discharging a battery storage system into a behind the meter power infrastructure for the facility.

Abstract: A computer-implemented method, system, and computer program product are provided for demand charge management. The method includes receiving an active power demand for a facility, a current load demand charge threshold (DCT) profile for the facility, and a plurality of previously observed load DCT profiles. The method also includes generating a forecast model from a data set of DCT values based on the current load DCT profile for the facility and the plurality of previously observed load DCT profiles. The method additionally includes forecasting a monthly DCT value for the facility using the forecast model. The method further includes preventing actual power used from a utility from exceeding the next month DCT value by discharging a battery storage system into a behind the meter power infrastructure for the facility.