Abstract: A position estimation device includes an ECU. The ECU is configured to estimate the position of a vehicle using at least a traveled distance of the vehicle. The ECU calculates correction factors for a reference tire rolling radius and stores the correction factors in a storage device. Each of the correction factors is set for a corresponding one of a plurality of vehicle speed ranges. The ECU calculates the traveled distance of the vehicle based on a rotation parameter and the corrected reference tire rolling radius obtained by correcting the reference tire rolling radius using the correction factor.

Abstract: An autonomous power trowel includes a frame supported by at least one rotor having a plurality of troweling blades, at least one power source for selectively rotating the rotor to finish an upper surface of the concrete, at least one actuator onboard the frame for selectively tilting the rotor, and a communication system onboard the frame for communicating with at least one remote communication device. Also included are a plurality of sensors onboard the frame for sensing exterior boundaries of the concrete, and at least one inspection camera for viewing the upper surface of the concrete. A controller onboard the frame is configured to selectively operate the power source, to selectively operate the actuator, to receive communications from the remote communication device, to receive signals from the sensors, and to receive signals from the inspection camera to detect any surface blemish in the concrete.

Abstract: A method is disclosed. The method includes providing a sensor attached to a vehicle, controlling the vehicle to move toward a system, using the sensor to sense data, providing the sensed data to a detection module including computer-executable code stored in non-volatile memory, and controlling the sensor and the vehicle to perform a raster scan when the detection module detects a variation in the sensed data. The method also includes providing sensed raster scan data to the detection module, using the detection module to generate a plurality of probability distribution curves based on the sensed raster scan data, and using the detection module to generate a vector based on the plurality of probability distribution curves. The vector points to a location of the system.

Abstract: A machine learning apparatus that can determine the state of a tool from a force applied from the tool to a robot while the robot performs a work using the tool. A machine learning apparatus for learning a state of a tool used for a work by a robot includes a learning data acquisition section that acquires, as a learning data set, data of a force applied from the tool to the robot while the robot causes the tool to perform a predetermined operation, and data indicating the state of the tool during the predetermined operation, and a learning section that generates a learning model representing a correlation between the force and the state of the tool, using the learning data set.

Abstract: An adaptive robot grasp planning technique for bin picking. Workpieces in a bin having random positions and poses are to be grasped by a robot and placed in a goal position and pose. The workpiece shape is analyzed to identify a plurality of robust grasp options, each grasp option having a position and orientation. The workpiece shape is also analyzed to determine a plurality of stable intermediate poses. Each individual workpiece in the bin is evaluated to identity a set of feasible grasps, and the workpiece is moved to the goal pose if such direct movement is possible. If direct movement is not possible, a search problem is formulated, where each stable intermediate pose is a node. The search problem is solved by evaluating the feasibility and optimality of each link between nodes. Feasibility of each link is evaluated in terms of collision avoidance constraints and robot joint motion constraints.

Abstract: A method of determining a reference direction for an angular measurement device, comprising: providing a rigid structure having an antenna for a global navigation satellite system (GNSS) fixed at a first point thereof; fixing the angular measurement device to a second point on the rigid structure, separated from the first point by at least 0.5 meters; while rotating the rigid structure so as to cause rotational movement of the antenna around the sensitive axis, acquiring velocity measurement data from the GNSS and angular velocity measurement data from the angular measurement device; and using the velocity measurement data and the angular velocity measurement data to determine a reference direction for the angular measurement device.

Abstract: Techniques for calculating a geospatial position of a point of interest using a portable electronic device. A camera of the portable electronic device may observe the point of interest. An EDM device of the portable electronic device may capture a distance to the point of interest. An angle sensor may detect an orientation of the EDM device. A geospatial position of a GNSS receiver of the portable electronic device may be detected. A geospatial position of the EDM device may be calculated based on the geospatial position of the GNSS receiver. The geospatial position of the point of interest may be calculated based on the geospatial position of the EDM device, the orientation of the EDM device, and the distance to the point of interest.

Abstract: A robot control method for controlling a robot including a robot arm that performs predetermined work on a work target object, the robot control method including a target-position setting step for setting, on simple shape data predicted from a plurality of projection shapes obtained by projecting the work target object from different directions, a plurality of target positions to which a control point of the robot arm in performing the predetermined work is moved and a driving step for driving the robot arm with force control based on the plurality of target positions set in the target-position setting step and force applied to the robot arm and performing the predetermined work.

Abstract: A method of controlling rear wheel steering in a vehicle including determining a stability state of the vehicle from a plurality of vehicle sensor inputs, determining a target vehicle performance based on the stability state of the vehicle, and determining a target rear angle of rear vehicle wheels based on a difference between a target vehicle characteristic and a model vehicle characteristic, wherein the target vehicle performance promotes agility and stability to a target model at different times based on the stability state of the vehicle.

Abstract: A method of teaching a robot including providing a pin at a location within a work station, and the robot in an area adjacent to the station. The robot having an arm and an end effector that pivots. The end effector has a through-beam sensor including a light emitter and a light receiver to sense when an object is present therebetween. The robot is moved to perform sensing operations in which the sensor senses the pin, such operations are performed while a position and/or an orientation of the end effector are varied to gather sensed position and orientation data. The sensing operations are performed such that the pin is located at different distances between the emitter and the receiver as the robot moves the sensor across the pin. Calculations are performed on the data to determine the location of the pin with respect to a coordinate system of the robot.

Abstract: A method of controlling a robot includes obtaining a first image and a second image of a plurality of objects, the first and second image being captured from different positions; obtaining, from the first and second images, a plurality of candidate positions corresponding to each of the plurality of objects, based on a capturing position of each of the first and second images and a direction to each of the plurality of objects from each capturing position; obtaining distance information between each capturing position and each of the plurality of objects in the first and second images by analyzing the first and second images; and identifying a position of each of the plurality of objects from among the plurality of candidate positions based on the distance information.

Abstract: A method, performed by a robot vacuum cleaner, of planning a cleaning route includes: dividing an indoor space into at least one cleanable region based on an indoor space map generated using at least one sensor included in the robot vacuum cleaner; dividing the at least one cleanable region into a plurality of partial regions based on a cleaning mode of the robot vacuum cleaner; and planning a first cleaning route to control a number of direction changes of the robot vacuum cleaner with respect to each of the plurality of partial regions based on the cleaning mode being a first mode.

Abstract: A main body of a ball collecting and discharging machine includes a traveling portion and a ball collecting and discharging portion to collect and discharge balls. A controller causes the ball collecting and discharging portion to collect the balls scattered in a ball scattered area while causing the traveling portion to cause the main body to travel along a ball collecting route in the ball scattered area. When the ball collecting and discharging portion reaches a state of being ready to discharge balls during or after ball collecting work, the controller causes the traveling portion to cause the main body to travel along the ball discharging route and causes the ball collecting and discharging portion to discharge balls at the ball discharging site.

Abstract: Embodiments described herein disclose methods and systems for adversarial learning in autonomous vehicle path modeling. The systems and methods collect states of the vehicle in the environment to predict a path. The predicted path is compared for variance from an actual path. The variance between the paths, in light of other data, is used to modify the driving models, to create more accurate representations of expert driving in autonomous vehicle path generation.

Abstract: Embodiments of the present disclosure relate to a method and apparatus for generating information. The method can include: acquiring first driving environment data of a target road segment; comparing the first driving environment data with pre-stored second driving environment data of the target road segment, and determining a difference between the first driving environment data and the second driving environment data; and generating, in response to determining the difference satisfying a preset condition, road abnormality information.

Abstract: Systems, methods, and computer-readable media are provided for detecting a pavement marking around an autonomous vehicle, comparing the detected pavement marking with a pavement marking present in a semantic data map, determining whether a change has occurred between the detected pavement marking and the pavement marking present in the semantic data map, and updating the semantic data map based on the determining of whether the change has occurred between the detected pavement marking and the pavement marking present in the semantic data map.

Abstract: According to one embodiment, an information processing device includes: a first memory; a first receiver; a first determination section; and a first transmitter. The first memory is configured to store first image data of interior of a vehicle at a first point in time. The first receiver is configured to receive second image data of the interior of the vehicle at a second point of time from the vehicle. The first determination section is configured to determine whether a change has been caused in the interior of the vehicle between the first point in time and the second point in time. The first transmitter is configured to transmit first data based on the determination result.

Abstract: A computer is programmed to determine a localization of a first vehicle, including location coordinates and an orientation of the first vehicle, based on first vehicle sensor data, and to wirelessly receive localizations of respective second vehicles, wherein a first vehicle field of view at least partially overlaps respective fields of view of each of the second vehicles. The computer is programmed to determine pair-wise localizations for respective pairs of the first vehicle and one of the second vehicles, wherein each of the pair-wise localizations defines a localization of the first vehicle relative to a global coordinate system based on a (a) relative localization of the first vehicle with reference to the respective second vehicle and (b) a second vehicle localization relative to the global coordinate system, and to determine an adjusted localization for the first vehicle that has a minimized sum of distances to the pair-wise localizations.

Abstract: A method is described for creating observation data, in particular by at least one vehicle, traveled road segments being ascertained by the vehicle, lanes of the road segments traveled by the vehicle being ascertained by the vehicle, and the ascertained road segments together with the ascertained traveled lanes being transmitted as observation data from the vehicle to an external server unit. A method for ascertaining a number of traffic lanes, to a system, to an external server unit, and to a control unit are also described.

Abstract: In one embodiment, a method includes accessing global positioning system (GPS) data indicating a raw location associated with the computing system; accessing, based on the raw location, environmental model data including one or more structures; generating GPS correction data by processing the GPS data and the environmental model data using a machine-learning (ML) model that has been trained to compensate inaccurate GPS readings due to environmental interference; and determining an accurate location by correcting the raw location using the GPS correction data.