The invention relates to a method for detecting an occurring deadlock conflict in a robot fleet of autonomous mobile robots. The method comprises the steps of: designating a plurality of robot resource zones to respective physical zones in a physical environment; operating said robot fleet such that autonomous mobile robots of said robot fleet individually and dynamically block different resource zones of said plurality of robot resource zones; monitoring said robot fleet to identify deadlock-relevant robot states associated with at least two mobile robots of said robot fleet, wherein said at least two mobile robots comprises at least a first robot and a second robot; and identifying that said first robot is being operated towards a resource zone of said plurality of robot resource zones blocked by said second robot to detect said occurring deadlock conflict. The invention further relates to a deadlock detection system.

A state determination method and apparatus for a cleaning robot are provided. The method includes: acquiring a working mode of the cleaning robot in real time; based on the working mode, acquiring a target accumulation threshold corresponding to the working mode; based on the target accumulation threshold, performing selection and accumulation of respective angle change values detected within a preset duration to obtain an accumulated change value; and determining a state of the cleaning robot based on the accumulated change value.

The vehicle travel control device includes: an absolute position calculation unit configured to acquire GNSS information through a GNSS receiver mounted on a vehicle and calculate an absolute position of the vehicle by the standalone positioning; a reception determination unit configured to determine whether GNSS correction information required for relative positioning can be received from an external reference station; a relative position calculation unit configured to calculate a relative position of the vehicle by the relative positioning; and a communication unit configured to transmit the current position information of the vehicle to a remote control device. The communication unit is configured to: transmit position information based on the relative position in a case in which the GNSS correction information can be received; and transmit position information based on the absolute position in a case in which the GNSS correction information cannot be received.

Example computer-implemented methods and systems for anomaly-sensing based multi-agent navigation are disclosed. One example computer-implemented method includes: receiving relative distance data specifying distance between at least one pair of agents of a plurality of agents, each of a subset of the plurality of agents having an anomaly sensor subsystem; receiving anomaly data from at least one anomaly sensor subsystem of one of the plurality of agents; obtaining pre-surveyed map data; and determining global pose data of the plurality of agents based on the relative distance data and based on comparing the anomaly data to the pre-surveyed map data.

Systems and methods of aircraft modal suppression informed by an underlying non-uniform vertical turbulence model and uniform lateral turbulence model. The systems and methods include receiving a plurality of signals from on-board inertial sensors of an aircraft, utilizing the plurality of signals to generate a plurality of observers, utilizing the observers to determine a control law command for controlling one or more control surfaces of the aircraft, and moving the one or more control surfaces of the aircraft in accordance with the determined control law command such that lateral mode vibrations of the aircraft are diminished.

An apparatus and method for controlling driving of a moving object that climbs up or down stairs comprises a tilt sensor configured to sense a slope of the moving object in a pitch direction, and a processor configured to reduce a speed of the moving object in a specific section while the moving object climbs up or down the stairs, based on the sensed slope.

The present application relates to a threshold-type obstacle recognition method, an orientation recognition method of a threshold-type obstacle, and a robot control method. With the robot control method of the present application, using the recognition results of the threshold-type obstacle and the recognition results of the orientation of the threshold-type obstacle, a corresponding operation of passing through the threshold obstacle is matched according to the relative relationship between a direction of travel of the robot and the orientation of the threshold-type obstacle, and the orientation of the threshold-type obstacle is used as a guide to provide the robot with a matching operation of passing through the threshold-type obstacle, so as to improve the success rate of the robot passing through the threshold-type obstacle.

A safety system and a method for the localization of at least two vehicles have at least one control and evaluation unit and at least one radio location system. The radio location system has at least three arranged radio stations. At least one device has at least one radio transponder arranged at the vehicles. The radio location system is configured to determine position data of the radio transponder and thus to determine position data of the vehicles. The position data can be transmitted from the radio station of the radio location system to the control and evaluation unit and/or the position data can be transmitted from the radio transponder to the control and evaluation unit. The control and evaluation unit is configured to cyclically detect the position data of the radio transponder. The radio transponder has an identification and the control and evaluation unit is configured to distinguish the vehicles.

Hardware and computational systems for measuring plant weight in hydroponic grow systems. The combined weight of hydroponic grow modules that grow plants using a small amount of water covering the roots is accessible via automated robotic systems. The individual weights of grow infrastructure, plant mass, and available water are convolved. The amount of water in a growing tray can be estimated separately by slightly tipping the module, allowing water to move to one side, and measuring the weight at each of the corners of the module. After controlling for unevenness of the surface where the module is held, a machine learning model predicts the amount of water in a grow module and, subsequently, the plant mass. Reliable estimation of plant mass and water volume allows for both maintenance of precise amounts of water in growing trays and estimation of harvestable product in the grow space.

A method includes creating a digital map of an environment, loading the digital map on a moveable robot, wherein the robot is placed in the environment, generating a trajectory path plan from a current position to a desired position using the digital map, the trajectory path having a plurality of waypoints, causing the robot to traverse within the environment in accordance with the trajectory path plan, collecting sensor data in real time while the robot is traversing within the environment, detecting, based on the collecting step, at each waypoint, whether an anomaly is present between an existing waypoint and a subsequent waypoint, and performing a corrective action of the robot based on the detecting step.