Abstract: An autonomous vehicle operates in a Follow Mode, wherein an apparatus for controlling movement of a vehicle includes an exterior monitoring system comprising at least one sensor to monitor an exterior region and to detect a location of a target user. A controller is configured to A) interactively map an activity zone having a selected expanse in the exterior region relative to the vehicle, B) compare a monitored location of the target user to the activity zone, C) detect a relocation event when the comparison of the monitored location of the target user to the activity zone exceeds a predetermined deviation, and D) send a navigation command in response to detecting the relocation event in order to autonomously reposition the vehicle so that a relative location of the target user is restored to the activity zone.

Abstract: Providing explanations in route planning includes determining a route based on at least two objectives received from a user, where a second objective of the at least two objectives is constrained to within a slack value of a first objective of the at least two objectives; receiving, from the user, a request for an explanation as to an action along the route; and providing the explanation to the user. The explanation describes an extent of violating the slack value.

Abstract: A navigation and positioning system for an underwater glider includes a micro-electro-mechanical system inertial measurement unit, a global positioning system receiving module, a triaxial magnetometer, a Doppler velocimeter, and an integrated navigation hardware processing system. If a navigation and positioning error is too large, the underwater glider stops working in real time and switches from the underwater working state to the up floating error correction state; and when velocity and location errors of a GPS/INS integrated navigation system are smaller than specified thresholds, the underwater glider switches from the up floating error correction state to the underwater working state and continues to work. An H? Kalman filter algorithm based on an adaptive multiple fading factor is established to ensure robustness and adaptability of navigation and positioning of a glider.

Abstract: Techniques for analyzing driving scenarios are discussed herein. For example, techniques may include determining a level of exposure associated with scenarios, searching for similar scenarios, and generating new additional scenarios. A driving scenario may be represented as top-down multi-channel data. The top-down multi-channel data may be provided as input to a neural network trained to output a prediction of future events. A multi-dimensional vector representing the scenario can be received as an intermediate output from the neural network and may be stored to represent the scenario. Multi-dimensional vectors representing different scenarios may be stored in a multi-dimensional space, and similar scenarios may be identified by proximity searching of the multi-dimensional space.

Abstract: System for navigating to a trajectory starting point by autonomous robot includes a GNSS navigation receiver including antenna, analog front end, plurality of channels, and a processor, generating navigation and orientation data for the robot; based on the navigation and the orientation data, the system calculating a position and a direction of movement for the robot towards the starting point of the trajectory, given known physical constraints for movement of the robot; the system calculating spatial and orientation coordinates z1, z2 of the robot, which relate to the position and the direction of movement, where z1 represents lateral deviation, and z2 represents angular deviation; the system continuing with a programmed path for the robot for any spatial and orientation coordinates z1, z2 within an attraction domain; and for any spatial and orientation coordinates of the robot outside the attraction domain, the system continues maneuvering until the robot is inside the attraction domain.

Abstract: A vehicle computing system may implement techniques to determine an action for a vehicle to perform based on a cost associated therewith. The cost may be based on a detected object (e.g., another vehicle, bicyclist, pedestrian, etc.) operating in the environment and/or a possible object associated with an occluded region (e.g., a blocked area in which an object may be located). The vehicle computing system may determine two or more actions the vehicle could take with respect to the detected object and/or the occluded region and may generate a simulation associated with each action. The vehicle computing system may run the simulation associated with each action to determine a safety cost, a progress cost, a comfort cost, an operational rules cost, and/or an occlusion cost associated with each action. The vehicle computing system may select the action for the vehicle to perform based on an optimal cost being associated therewith.