Abstract: A processing apparatus for generating route navigation data is provided, to, generate training data based on road network data corresponding to a network of roads in a defined geographical area, and journey data sets, each journey data set comprising data indicative of a journey by a road user through the network of roads and being derived using geolocation transmissions from a communications device of the road user, train a classifier model based on the training data, apply the trained classifier model on road data corresponding to a road in the defined geographical area, for the trained classifier model to predict a direction of traffic flow on the road, and generate the route navigation data indicative of the predicted direction of the traffic flow on the road. A method for generating route navigation data is also provided.

Abstract: The present disclosure relates to an apparatus and methods of estimating a traffic volume of moving objects. In particular, the present disclosure estimates the traffic volume based on amounts of traffic volume of the moving objects observed at observation points based on a routing matrix and a visitor matrix. The routing matrix indicates whether moving objects that pass through specific waypoints are to be observed at an observation point. The visitor matrix indicates whether a moving object departing or arriving at the observation point. The present disclosure enables estimating a traffic volume of moving objects on various routes based on observed data with errors in data and varying lengths in observation periods.

Abstract: Among other things, techniques are described for predicting how an agent (e.g., a vehicle, bicycle, pedestrian, etc.) will move in an environment based on prior movement, the road network, the surrounding objects and/or other relevant environmental factors. One trajectory prediction technique involves generating a probability map for an agent's movement. Another trajectory prediction technique involves generating a trajectory lattice, for an agent's movement. In addition, a different trajectory prediction technique involves multi-modal regression where a classifier (e.g., a neural network) is trained to classify the probability of a number of (learned) modes such that each model produces a trajectory based on the current input.

Abstract: An autonomous farming system (26) comprising one or more ground-based drones (10) and one or more unmanned aerial vehicles (12), whose routes through a field are optimized by an autonomous farming control system (30) that utilizes linearly constrained integer quadratic programming. The farming system (26) is particularly suited for farming steep terrain that is not accessible to conventional farming equipment.

Abstract: Drag Detection is provided. A system includes one or more processors of a vehicle, coupled with memory. The one or more processors can determine, for a vehicle, rolling drag based on energy input to one or more motors of the vehicle and a speed of the vehicle. The one or more processors can select, based on the rolling drag and a friction level associated with a surface on which the vehicle traverses, a slip target for the vehicle. The one or more processors can provide the slip target to a traction control system of the vehicle to control the one or more motors.

Abstract: A system and method for real world autonomous vehicle trajectory simulation may include: receiving training data from a data collection system; obtaining ground truth data corresponding to the training data; performing a training phase to train a plurality of trajectory prediction models; and performing a simulation or operational phase to generate a vicinal scenario for each simulated vehicle in an iteration of a simulation. Vicinal scenarios may correspond to different locations, traffic patterns, or environmental conditions being simulated. Vehicle intention data corresponding to a data representation of various types of simulated vehicle or driver intentions.

Abstract: A cemetery geospatial mapping system and methods are provided for interactive map-based searching of cemetery properties. The cemetery geospatial mapping system comprises a mapping tools system that includes a component systems package. The component systems package comprises a mapping system that enables end-users to add GPS coordinates to cemetery property records, automates mapping and overlaying of the cemetery properties onto satellite imagery, and enables the end-users to visually interact with information associated with the cemetery properties. A dynamic pricing system uses machine-learning algorithms to analyze data so as to provide the end-users with an optimal price recommendation for each property and unit of inventory. The dynamic pricing system maximizes profits based on predefined characteristics associated with the properties and units of inventory. A host site is stored on an application server system and accessible to the end-users by way of a communications network, such as the Internet.

Abstract: A host map system for updating a region of a host map based on sensor data received from a plurality of connected vehicles travelling in the region comprises monitoring a host map region for discrepancies, defining a geo-fence around an area of a discrepancy and setting a schedule for activing the geo-fence. When a connected vehicle enters the geo-fence, the host mapping system transmits the geo-fence to the connected vehicle and requests that it share its sensor data while travelling in the geo-fenced area. The host mapping system receives the sensor data and processes the data to update details of the host map. The host mapping system may transmit the updated map to connected vehicles travelling in the map region.

Abstract: Aspects of the disclosure relate to determining whether a feature of map information. For example, data identifying an object detected in a vehicle's environment and including location coordinates is received. This information is used to identify a corresponding feature from pre-stored map information based on a map location of the corresponding feature. The corresponding feature is defined as a curve and associated with a tag identifying a type of the corresponding object. A tolerance constraint is identified based on the tag. The curve is divided into two or more line segments. Each line segment has a first position. The first position of a line segment is changed in order to determine a second position based on the location coordinates and the tolerance constraint. A value is determined based on a comparison of the first position to the second position. This value indicates a likelihood that the corresponding feature has changed.

Abstract: A system and a method for navigating a robot. The system receives a target location, a field map, sensor data from a robot, and a robot location. The sensor data may include image data and kinetic data. Further, the system may determine a navigation mode based on the sensor data and the robot location. The navigation mode may be one of an under-canopy mode, an out-row mode, and a recovery mode. Further, the system may generate a reference map comprising a path for the robot to follow to reach the target location based on the navigation mode, the field map, and the target location. Finally, the system may be configured to navigate the robot based on the reference map.

Abstract: A method executed by a server for disseminating reports, over a communications network, for a plurality of assets is disclosed. The server receives from at least one first computing device, a first data packet comprising a plurality of asset data associated with a particular asset, and a first computing device signature associated with a first computing device. Further, after authenticating the first computing device signature, the server creates an asset record, wherein a plurality of asset data associated with the particular asset is recorded. Additionally, the server is configured for transmitting an operator interface to a plurality of operator computing devices, accessing the electronic ledger, and generating a response message to the operator request based on the plurality of asset data in the asset record.

Abstract: A system for controlling a flight boundary of an aircraft. The system includes a flight controller communicatively connected to the aircraft. The flight controller is configured to receive a plurality of flight data linked with the aircraft, determine a flight boundary for the aircraft as a function of the plurality of flight data, set an aircraft movement limit as a function of the flight boundary, receive a pilot instruction, and generate a control signal for the aircraft as a function of the aircraft movement limit and the pilot instruction. The control signal is limits the aircraft to remain within the flight boundary. A method for controlling a flight boundary of an aircraft is also provided.

Abstract: A method for navigating and route planning based on a HD map and with reference to other electronic devices moving along a similar route includes setting a start location and an end location; planning at least one navigation route based on the start location and the end location; acquiring locations of own electronic device and of co-travelling external electronic devices based on the HD map; acquiring speeds of the external electronic devices and selecting those moving at low speed; identifying moving directions of the slow-speed target electronic devices; and re-planning and resetting the at least one navigation route when the moving directions of the target electronic devices intersected with a direction of the lane. An electronic device and a server applying the method are also disclosed.

Abstract: Provided is a method of automatically combining a farm vehicle with a work machine including confirming a current position of the work machine, moving a farm vehicle into a range having a predetermined radius around the current position, and controlling the farm vehicle, on the basis of a current position and direction of a first coupling unit included in the work machine, so that the first coupling unit and a second coupling unit included in the farm vehicle are coupled to each other.

Abstract: A railcar acoustic monitoring system including a first trackside frame assembly that includes a first outer frame assembly, a second outer frame assembly, and a first inner frame assembly. The first outer frame assembly including a first microphone assembly positioned on a first outer side of the first rail of the railroad track, the first microphone assembly oriented to receive acoustic signals associated with the passing train. The second outer frame assembly including a second microphone assembly positioned on a second outer side of a second rail of the railroad track, the second microphone assembly oriented to receive acoustic signals associated with the passing train. The first inner frame assembly including a first housing, a third microphone assembly oriented to receive acoustic signals emanating from the first rail, and a fourth microphone assembly oriented to receive acoustic signals associated with the passing train.

Abstract: Aspects of the present disclosure include a navigation system and computer-implemented methods for proactively re-routing vehicles to control traffic flow. Consistent with some embodiments, the navigation system seeks to reduce traffic flow along primary navigation routes (e.g., routes with relatively short travel times) by re-routing vehicles to alternative navigation routes (e.g., routes with relatively longer travel times) using incentives. As an example, upon detecting a vehicle traveling along an alternative route instead of a primary route, the navigation system updates a data structure that represents a user account of a vehicle occupant to reflect an increased account balance. Consistent with some embodiments, the amount of value provided to an occupant of a vehicle traveling along an alternative routes may be obtained from user accounts of occupants of other vehicles that are traveling along a primary route.

Abstract: A battery diagnosis apparatus for diagnosis of a cell group including a plurality of battery cells connected in series, includes a voltage sensing circuit configured to periodically generate a voltage signal indicating a cell voltage of each battery cell, and a control circuit configured to generate time series data indicating a change in cell voltage of each battery cell over time based on the voltage signal. The control circuit is configured to (i) determine a first average cell voltage and a second average cell voltage of each battery cell based on the time series data, wherein the first average cell voltage is a short term moving average, and the second average cell voltage is a long term moving average, and (ii) detect an abnormal voltage of each battery cell based on a difference between the first average cell voltage and the second average cell voltage.

Abstract: A system allows an end-user to locate and gain access to an access-controlled facility or resource, such as a restroom, phone charging station, or Wi-Fi hot spot. Some implementations of the system monitor the formation and concentration of individuals into crowds that may place a higher demand on facilities and resources located near the crowd. The system may distribute mobile facilities to areas that offer convenient access to potential developing crowds, and when the system determines that there is a disparity between available resources and crowd demand reaches a certain level it may deploy one or more mobile facilities to positions proximate to that crowd. A mobile facility may also be requested on demand by a user or organizer, and some implementations provide cost sharing mechanisms and other user benefits related to requesting and accessing the facility.

Abstract: One or more devices in a data analysis computing system may be configured to receive and analyze movement data and driving data, and determine driving trips and associated drivers based on the received data. Movement data may be collected by one or more mobile devices, such as smartphones, tablet computers, and on-board vehicle systems. Drivers associated with driving trips may be identified based on the movement data collected by the mobile devices, such as speed data, acceleration data, or distance data.

Abstract: A method and system for controlling high voltage power of an electric vehicle to efficiently control outputs of power control object parts by controlling low-level controllers provided in the power control object parts through a high-level controller having various types of vehicle information, may include a power state monitoring step in which a high-level controller detects power variations in power control object parts through low-level controllers provided in the power control object parts, a power state determination step in which the high-level controller determines a stable power supply state and an unstable power supply state for the power control object parts on the basis of a preset power reference value, and a load output control step in which the high-level controller controls all load outputs for the power control object parts according to the stable power supply state and the unstable power supply state.