Abstract: An autonomous vehicle is described herein. The autonomous vehicle includes a lidar sensor system. The autonomous vehicle additionally includes a computing system that executes a lidar segmentation system, wherein the lidar segmentation system is configured to identify objects that are in proximity to the autonomous vehicle based upon output of the lidar sensor system. The computing system further includes a deep neural network (DNN), where the lidar segmentation system identifies the objects in proximity to the autonomous vehicle based upon output of the DNN.

Abstract: An electrically powered work vehicle includes a left driving wheel and a right driving wheel that are supported to a vehicle body, a left motor for driving the left driving wheel and a right motor for driving the right driving wheel, a steering wheel, an acceleration operation tool, a turning command calculation section for calculating a turning command based on a steering operation amount of the steering wheel, a turning torque calculation section for calculating a turning torque based on the turning command, a vehicle speed command calculation section for calculating a vehicle speed command based on an acceleration operation amount of the acceleration operation tool, a vehicle speed torque calculation section for calculating a vehicle speed torque based on the vehicle speed command, and a speed command calculation section for calculating a left motor speed command and a right motor speed command based on the turning torque and the vehicle speed torque.

Abstract: A parking assistance method provides parking assistance when parking a vehicle in a parking space equipped with a ground coil for supplying electric power via a wireless connection to a vehicle coil mounted on the vehicle, at least two ground marks indicating a position of the ground coil, and a parking frame. The parking assistance method switches from a bird's-eye image including the vehicle and a circumference of the vehicle as viewed from above the vehicle to an enlarged image showing a relative position between the ground coil and the vehicle coil on a larger scale than the bird's-eye image when an absolute value of a relative angle between a longitudinal direction of the parking frame and a front-rear direction of the vehicle is a predetermined value or smaller.

Abstract: Multivariate position estimation can be performed to provide a position estimate of a moving object. The multivariate position estimation approach can employ multiple types of information including time of arrival (or time difference of arrival), angle of arrival, Doppler, and/or prior location information in an iterative process to calculate a location estimate that is highly accurate. In particular, the multivariate position estimation approach can employ the statistical quality of each of these types of information to quickly arrive at a highly accurate position estimate within a 3D coordinate system. The multivariate position estimation approach can be implemented in environments where a single receiver is available as well as in environments where multiple receivers exist.

Abstract: The present invention provides a calculation method for visual navigation integrity monitoring. With the method, by use of an appropriate visual positioning model, a mathematical algorithm and rich navigation measurements, the positioning accuracy and availability of positioning results are improved, and the problem of insufficient performance of satellite integrity algorithms caused by impossible guarantee of availability of a GNSS in complex environments is solved, which is helpful to realize aircraft accurate approach and automatic landing and of great significance to ensure the safety of aviation flight.

Abstract: An information processing system that appropriately estimates a driving conduct includes: a detector that detects a vehicle environment state, which is at least one of surroundings of a vehicle and a driving state of the vehicle; a behavior learning unit configured to cause a neural network to learn a relationship between the vehicle environment state detected by the detector and a behavior of the vehicle implemented after the vehicle environment state; and a behavior estimation unit configured to estimate a behavior of the vehicle by inputting, into the neural network that learned, the vehicle environment state detected at a current point in time by the detector.