Abstract: Systems and methods for generating instructions for a vehicle to navigate an unsignaled intersection are provided. The method may include: generating an expected return over a sequence of actions of the vehicle; determining an optimal policy by selecting an action with a maximum value for the vehicle; executing dynamic frame skipping to expedite learning a repeated action of the vehicle; prioritize an experience replay by utilizing an experience replay buffer to break correlations between sequential steps of the vehicle; generate a plurality of state-action representations based on at least one of the expected return, the optimal policy, the dynamic frame skipping, or the prioritized experience replay; generate the instructions for navigating the unsignaled intersection based on the plurality of state-action representations; and transmit the instructions for navigating the unsignaled intersection to the vehicle such that the vehicle executes the instructions to navigate the unsignaled intersection.

Abstract: According to one aspect, keyframe based autonomous vehicle operation may include collecting vehicle state information and collecting environment state information. A size of an object within the environment, a distance between the object and the autonomous vehicle, and a lane structure of the environment through which the autonomous vehicle is travelling may be determined. A matching keyframe model may be selected based on the size of the object, the distance from the object to the autonomous vehicle, the lane structure of the environment, and the vehicle state information. Suggested limits for a driving parameter associated with autonomous vehicle operation may be generated based on the selected keyframe model. The autonomous vehicle may be commanded to operate autonomously according to the suggested limits for the driving parameter.

Abstract: According to one aspect, an autonomous vehicle policy generation system may include a state input generator generating a set of attributes associated with an autonomous vehicle undergoing training, a traffic simulator simulating a simulation environment including the autonomous vehicle, a roadway associated with a number of lanes, and another vehicle within the simulation environment, a Q-masker determining a mask to be applied to a subset of a set of possible actions for the autonomous vehicle for a time interval, and an action generator exploring a remaining set of actions from the set of possible actions and determining an autonomous vehicle policy for the time interval based on the remaining set of actions and the set of attributes associated with the autonomous vehicle.

Abstract: One robotic destination dispatch system for elevators comprises a destination dispatch module configured to determine an optimal elevator for a passenger. The robotic destination dispatch system includes a guide robot in wireless data communication with the destination dispatch module. The guide robot has a processor in communication with a propelling device, a sensory device, and a memory comprising software. The software includes computer-readable instructions executable by the processor to: (a) implement an auction-based scheduling algorithm; (b) determine an identity of the passenger; (c) receive from the destination dispatch module the optimal elevator for the passenger; and (d) activate the propelling device to cause the guide robot to move and physically guide the passenger to the optimal elevator.

Abstract: Systems and methods for generating instructions for a vehicle to navigate an unsignaled intersection are provided. The method may include: generating an expected return over a sequence of actions of the vehicle; determining an optimal policy by selecting an action with a maximum value for the vehicle; executing dynamic frame skipping to expedite learning a repeated action of the vehicle; prioritize an experience replay by utilizing an experience replay buffer to break correlations between sequential steps of the vehicle; generate a plurality of state-action representations based on at least one of the expected return, the optimal policy, the dynamic frame skipping, or the prioritized experience replay; generate the instructions for navigating the unsignaled intersection based on the plurality of state-action representations; and transmit the instructions for navigating the unsignaled intersection to the vehicle such that the vehicle executes the instructions to navigate the unsignaled intersection.

Abstract: According to one aspect, an autonomous vehicle policy generation system may include a state input generator generating a set of attributes associated with an autonomous vehicle undergoing training, a traffic simulator simulating a simulation environment including the autonomous vehicle, a roadway associated with a number of lanes, and another vehicle within the simulation environment, a Q-masker determining a mask to be applied to a subset of a set of possible actions for the autonomous vehicle for a time interval, and an action generator exploring a remaining set of actions from the set of possible actions and determining an autonomous vehicle policy for the time interval based on the remaining set of actions and the set of attributes associated with the autonomous vehicle.

Abstract: According to one aspect, keyframe based autonomous vehicle operation may include collecting vehicle state information and collecting environment state information. A size of an object within the environment, a distance between the object and the autonomous vehicle, and a lane structure of the environment through which the autonomous vehicle is travelling may be determined. A matching keyframe model may be selected based on the size of the object, the distance from the object to the autonomous vehicle, the lane structure of the environment, and the vehicle state information. Suggested limits for a driving parameter associated with autonomous vehicle operation may be generated based on the selected keyframe model. The autonomous vehicle may be commanded to operate autonomously according to the suggested limits for the driving parameter.

Abstract: The disclosure includes a system and method for providing navigation guidance. The system includes a tracking application and a user. The tracking application determines a location of a user, determines a position of at least one object in proximity to the user, determines a path for the user to avoid the at least one object, generates linear and angular velocities that correspond to the path and generates directions that correspond to the linear and angular velocities. The user can receive the directions as audio instructions or via a tactile belt with motors that vibrate to convey the directions.

Abstract: The disclosure includes a system and method for using a robot to simulate user motions by detecting a user, estimating a first position and orientation of the user, determining a current position of the robot, generating an initial path from the current position of the robot to a goal position based on whether the robot affects the user while travelling on the initial path, determining whether the user will traverse in response to the robot when the robot travels on the initial path, responsive to the user traversing in response to the robot, estimating a second position where the user will move when the robot is near, and generating a new path from the current position of the robot to the goal position.

Abstract: The disclosure includes a system and method for using a robot to simulate user motions by detecting a user, estimating a first position and orientation of the user, determining a current position of the robot, generating an initial path from the current position of the robot to a goal position based on whether the robot affects the user while travelling on the initial path, determining whether the user will traverse in response to the robot when the robot travels on the initial path, responsive to the user traversing in response to the robot, estimating a second position where the user will move when the robot is near, and generating a new path from the current position of the robot to the goal position.

Abstract: The disclosure includes a system and method for switching vibration modalities based on conditions to provide navigation guidance. The system includes a tactile belt and a computing device. The computing device includes a modality module for receiving path data describing a path planned for a user associated with a tactile belt and location data describing a location of the user associated with the tactile belt, determining condition data based on the path data and the location data and determining a vibration modality based on the condition data. The condition data describes a direction change. The vibration modality describes a pattern for vibration and indicates a vibration signal. The system applies the vibration signal indicated by the vibration modality to the tactile belt to instruct the user associated with the tactile belt to follow the path.

Abstract: A system for detecting a person and estimating pose information comprises a processor and a memory storing instructions causing the system to: retrieve depth data from a sensor, the depth data describing distance information associated with one or more objects detected by the sensor; cluster the depth data to determine two or more candidate leg clusters, each candidate leg cluster including a portion of the depth data that may represent a human leg detected by the sensor; identify a candidate leg cluster pair including two candidate leg clusters within a certain distance between each other; determine whether there is a connectivity between the two candidate leg clusters included in the candidate leg cluster pair; and responsive to determining that there is a connectivity between the two candidate leg clusters, determine that the candidate leg cluster pair is qualified to be a leg cluster pair representing a person.