Abstract: Provided is a robotic device, including: a chassis; a set of wheels; one or more motors to drive the set of wheels; a controller in communication with the one or more motors; one or more surface cleaning tools; at least one sensor; a camera; one or more processors; a medium storing instructions that when executed by the one or more processors effectuate operations including: capturing, with the camera of the robotic device, spatial data of surroundings of the robotic device; generating, with the one or more processors of the robotic device, a movement path based on the spatial data of the surroundings; inferring, with the one or more processors of the robotic device, a location of the robotic device; and updating, with the one or more processors of the robotic device, the movement path to exclude locations of the movement path that the robotic device has previously been located.

Abstract: An engine control system includes an electronic hardware engine controller in signal communication with an actuator and an engine sensor. The actuator operates at a plurality of different positions to control operation of an engine. The engine sensor measures an engine operating parameter. The engine controller generates a synthesized engine operating parameter, and adjusts the position of the actuator based on the synthesized engine operating parameter in response to detecting a faulty engine sensor.

Abstract: A control system 1 includes a first controller, and a second controller. The second controller includes a program storage module that stores two or more coordinate conversion programs, and a control processing module 240 that acquires program designation information for designating one of two or more coordinate conversion programs from the first controller. Additionally, the control processing module may acquire a first operation command in the coordinate system for the first controller from the first controller, and convert the first operation command to an operation target value of two or more joint axes of a multi-axis robot using the coordinate conversion programs according to the program designation information. Driving power according to the operation target value may be output to the joint axes.

Abstract: A vertiport system dynamically updates configuration of a vertiport based on predicted usage of the vertiport during a given time frame. The vertiport system predicts vertiport usage using flight data and estimated passenger demands and determines a desired number of parking pads and a desired number of final approach and takeoff (FATO) pads for the vertiport during the time frame. Based on the desired number of parking pads and the desired number of FATO pads for the vertiport, the vertiport system determines an updated configuration of the vertiport. According to the updated configuration, the vertiport system updates the configuration of the vertiport for at least a portion of the time frame.

Abstract: A method for controlling vehicle travelling includes: detecting a plurality of travelling states of a vehicle, the plurality of travelling states includes a plurality of travelling directions; respectively previewing the vehicle travelling along the plurality of travelling directions from an original position in a lane to obtain a plurality of previewing paths; fitting a plurality of turning paths of the vehicle travelling from the original position to a target path in the lane according to the plurality of previewing paths; using the plurality of turning paths to calculate change information of a plurality of steering wheel angles; and adjusting the plurality of travelling directions according to the change information of the steering wheel angles, so as to control the vehicle to travel from the original position to the target path along the turning path.

Abstract: A data driven approach for fault detection in robotic actuation is disclosed. Here, a set of robotic tasks are received and analyzed by a Deep Learning (DL) analytics. The DL analytics includes a stateful (Long Short Term Memory) LSTM. Initially, the stateful LSTM is trained to match a set of activities associated with the robots based on a set of tasks gathered from the robots in a multi robot environment. Here, the stateful LSTM utilizes a master slave framework based load distribution technique and a probabilistic trellis approach to predict a next activity associated with the robot with minimum latency and increased accuracy. Further, the predicted next activity is compared with an actual activity of the robot to identify any faults associated robotic actuation.

Abstract: The invention relates to a method for controlling a plurality of mobile driverless manipulator systems (10, 20), in particular driverless transport vehicles in a logistics environment (40) for manipulating objects (30). In the method, ambient information is provided by a central control device (50), and in one step, an object to be moved (30) in the surroundings is detected. The position and the pose of the detected object are used for updating the ambient information and are taken into account in the path planning of the mobile driverless manipulator systems (10, 20) in that, prior to a movement of the detected object (30), a first mobile driverless manipulator system (10) is used to check whether the detected object (30) is needed for the orientation of a second mobile driverless manipulator system (20).

Abstract: A work machine management system includes: an input data acquisition unit that acquires input data generated by an operation of an input device; a turn signal data setting unit that sets turn signal data for controlling a direction indicator of a work machine to each of a plurality of courses branching from an intersection based on the input data; and an output unit that outputs the turn signal data to the work machine.

Abstract: A method for determining whether hands of an operator of a vehicle are positioned on a hand wheel of the vehicle is provided. The method generates a first frequency content below a first frequency from a hand wheel torque signal. The method generates a second frequency content above a second frequency from the first frequency content of the hand wheel torque signal. The method generates a hands on wheel (HOW) estimate signal based on the first frequency content and the second frequency content by determining a first contribution of the first frequency content to the HOW estimate signal, determining a second contribution of the second frequency content to the HOW estimate signal, and combining the first contribution and the second contribution to generate the HOW estimate signal. The method causes a system in a vehicle to operate based on the HOW estimate signal.

Abstract: A vehicle control unit includes: a lane change control unit that performs lane change control in which a host vehicle changes lanes on the basis of a surrounding situation of the host vehicle; and a lane change control suppression unit that allows the lane change control in a case where there is no operation history indicating that an operation of a notification unit for notifying a direction to which a traveling direction of the host vehicle is changed is not normal, and suppresses the lane change control in a case where the operation history indicating that the operation of the notification unit is not normal is present.

Abstract: A slope detection system (10, 19, 185C) for a vehicle (100) is provided. The system has a processor (10, 19) that receives, from one or more sensors (185C) arranged to capture data in respect of terrain ahead of the vehicle, terrain information indicative of the topography of an area extending ahead of the vehicle (100). The processor (10, 19), in dependence upon a predicted path of the vehicle (100) over the terrain extending ahead of the vehicle (100), generates, for the predicted path of the vehicle (100), information indicative of an angle of slope of the predicted path, being the slope of the predicted path along a direction of travel of the vehicle (100).

Abstract: Training and/or use of a machine learning model for placement of an object secured by an end effector of a robot. A trained machine learning model can be used to process: (1) a current image, captured by a vision component of a robot, that captures an end effector securing an object; (2) a candidate end effector action that defines a candidate motion of the end effector; and (3) a target placement input that indicates a target placement location for the object. Based on the processing, a prediction can be generated that indicates likelihood of successful placement of the object in the target placement location with application of the motion defined by the candidate end effector action. At many iterations, the candidate end effector action with the highest probability is selected and control commands provided to cause the end effector to move in conformance with the corresponding end effector action.

Abstract: A system includes a processor that, for example, by executing a computer program, performs a method for generating parking space for vehicles, the method including ascertaining whether a need exists for parking space for vehicles within a geographical area that includes a roadway, if the need is determined to exist, ascertaining whether a side area of the roadway is usable as parking space, and, responsive to a positive result of the determination, designate the side area as the parking space, and control a signaling device to signal the availability of the side area for vehicle parking.

Abstract: The present disclosure provides an obstacle avoidance method and system for a robot having ranging sensors as well as a robot using the same. The method includes: obtaining detection data collected by the plurality of ranging sensors; obtaining a current position of the robot based on the collected detection data; determining whether historical detection data corresponding to the current position has been stored; planning a movement path of the robot based on the collected detection data and the historical detection data and generating movement path information of the movement path, if the historical detection data corresponding to the current position has been stored; and controlling the robot to move along an obstacle-free path based on the movement path information. The present disclosure can effectively break through the limitation of the sensor technology, reduce the detection blind zone, and effectively improve the obstacle avoidance efficiency of a robot.

Abstract: A system includes a first sensor configured to detect a rotational position of a first wheel. The system includes a second sensor configured to detect a rotational position of a second wheel. The system includes a third sensor configured to detect a rotational speed of a driveline operatively coupled to the first wheel and the second wheel. The system includes a computer in communication with the first sensor, the second sensor, and the third sensor. The computer is programmed to detect a fault associated with the first wheel or the second wheel based on a correlation between an oscillation in the rotational speeds of the driveline and the rotational positions of the first wheel or the rotational positions of the second wheel.

Abstract: According to an aspect of some embodiments of the present invention there is provided a method for generating a dataset mapping visual features of each of a plurality of objects, comprising: for each of a plurality of different objects: instructing a robotic system to move an arm holding a respective the object to a plurality of positions, and when the arm is in each of the plurality of positions: acquiring at least one image depicting the respective object in the position, receiving positional information of the arm in respective the position, analyzing the at least one image to identify at least one visual feature of the object in the respective position, and storing, in a mapping dataset, an association between the at least one visual feature and the positional information, and outputting the mapping dataset.

Abstract: An automatic driving system includes at least one electronic control unit configured to: generate a traveling plan so as to moderate a change in behavior of a vehicle at a time when an automatic driving control of the vehicle is started by an automatic engagement compared to a change in the behavior of the vehicle at a time when the automatic driving control is started by a triggered engagement, the automatic engagement being an engagement in which the automatic driving control is automatically started when an automatic engagement condition is satisfied, the triggered engagement being an engagement in which the automatic driving control is started when an automatic driving start condition is satisfied and an automatic driving start trigger is input by an occupant; and execute the automatic driving control by controlling the behavior of the vehicle based on the traveling plan, using an actuator equipped in the vehicle.

Abstract: A method for operating a self-traveling robot, wherein an environment map of an environment of the robot is generated based on measuring data recorded within the environment, wherein a position of the robot within the environment is estimated, and wherein the robot travels within the environment based on the environment map and its known position. In order to extend the maximum range of the robot within the environment, an environment map, which is currently not needed for the navigation of the robot, is detected and transmitted to an external memory unit.

Abstract: A processing system includes a robot including at least one arm each including a hand at an end of the at least one arm; a first position measurement sensor, which is to be grasped by the hand and moved by the at least one arm, and is configured to measure a position of a device to be used when the robot processes a processing target; and a robot control device configured to: cause the hand to grasp the first position measurement sensor; and cause the first position measurement sensor to measure the position of the device.

Abstract: A system includes a processor and a memory. The memory stores instructions executable by the processor to select a technique, from a plurality of techniques, to identify a vehicle location by sensor and map data based on features detected in sensor data of an area in which the vehicle is located, to determine a location of the vehicle based on the selected technique; and to navigate the vehicle based at least in part on the identified location.