Abstract: Provided herein are systems and methods for vertical federated machine learning. Vertical federated machine learning can be performed by a central system communicatively coupled to a plurality of satellite systems. The central system can receive encrypted data from the satellite systems and apply a transformation that transforms the encrypted data into transformed data. The central system can identify matching values in the transformed data and generate a set of location indices that indicate one or more matching values in the transformed data. The central system can transmit instructions to the satellite systems to access data stored at locations indicated by the location indices and to train a machine learning model using data associated with said locations.

Abstract: Methods and systems are provided for controlling a robot to navigate a perceptually aliased environment, the robot being configured to infer a first Gaussian mixture model (GMM) of a first pose of the robot, and to plan an optimal control action by: determining a second GMM of a simulated pose of the robot by simulating applying the first control action to the first GMM; determining from the second GMM a range of possible observations; calculating scene probabilities for associating each possible observation with each aliased scene of a set of aliased scenes; calculating from the scene probabilities an objective function to determine an estimated cost of the first control action; and comparing the estimated cost of the first control action with estimated costs calculated for one or more additional control actions, to determine an optimal control action.

Abstract: A method for automatically initiating a change of lane in an automated automotive vehicle. Sensory data is combined in a sensory fusion processor to generate a stack of semantic images of a sensed vehicular driving environment. The stack is used in a reinforcement learning system using a Markov Decision Process in order to optimize a neural network of an automated lane change system.

Abstract: A system for controlling a vehicle includes a processor configured to execute instructions stored on a non-transitory computer readable medium. The system also includes a sensor coupled to the processor and configured to receive sensory input. The system also includes a controller coupled to the processor and configured to control the vehicle. The processor is further configured to: create a synthetic image based on the sensory input; derive a deep reinforcement learning (RL) policy using the synthetic image, wherein the deep RL policy determines a longitudinal control for the vehicle; and instruct the controller to control the vehicle based on the deep RL policy.

Abstract: A system for controlling a vehicle includes a first sensor for detecting at least one environment characteristic. The system also includes a driver characteristic input device configured to receive at least one driver characteristic corresponding to a driving style of a driver. The system also includes a controller that includes a reinforcement learning adaptive cruise control that is in communication with the first sensor and the driver characteristic input device, the reinforcement learning adaptive cruise control being configured to: determine a target behavior for the vehicle based on the at least one environment characteristic and the at least one driver characteristic; and selectively control the vehicle based on the target behavior.

Abstract: Methods and systems are provided for controlling a robot to navigate a perceptually aliased environment, the robot being configured to infer a first Gaussian mixture model (GMM) of a first pose of the robot, and to plan an optimal control action by: determining a second GMM of a simulated pose of the robot by simulating applying the first control action to the first GMM; determining from the second GMM a range of possible observations; calculating scene probabilities for associating each possible observation with each aliased scene of a set of aliased scenes; calculating from the scene probabilities an objective function to determine an estimated cost of the first control action; and comparing the estimated cost of the first control action with estimated costs calculated for one or more additional control actions, to determine an optimal control action.