The invention proposes a method for the automated discharge of loose transport material from a container, transported by means of a self-driving vehicle, into a collection container, where the unloading takes place in a spatially defined unloading cone within an unloading station. Furthermore, an unloading station for automated discharge according to the method is proposed.

A slipform paver includes at least one machine frame and at least three travelling devices connected to the machine frame. At least one conveyor is connected to the machine frame such that the conveyor is pivotable relative to the machine frame about a horizontal axis and about a vertical axis. At least one first actuator is configured to pivot the conveyor about the horizontal axis and at least one second actuator is configured to pivot the conveyor about the vertical axis, such that the conveyor is movable by at least the first actuator and the second actuator within a zone of movement defined relative to the machine frame. A controller is configured to define at least one area of collision within the zone of movement and to determine a position of the conveyor relative to the area of collision.

There is provided a mobile autonomous agricultural system comprising: a powered mobile unit for carrying agricultural equipment, and configured to move along rows of crops; at least one laser curtain sensor configured to project a laser curtain away from the mobile unit; a location module configured to monitor a location of the mobile unit relative to a row; a controller configured to control the travel of the mobile unit; a safety module configured to: receive a location signal from the location module related to the location of the mobile unit relative to a row, select a mode of operation to process the laser curtain in a predefined laser curtain pattern, based on the received location signal, each mode of operation corresponding to a different predefined laser curtain pattern, and to generate a safety output in response to determining that the laser curtain is interrupted within the laser curtain pattern.

The present disclosure provides a method for operating an autonomous mobile device and a storage medium. The method includes: performing re-localization for the autonomous mobile device; detecting a first feature of an identifier; calculating a first relative location of an object having the identifier relative to the autonomous mobile device; calculating, based on the first relative location and a real time location of the autonomous mobile device, a current global location of the object; retrieving a prior global location of a charging station; comparing the current global location and the prior global location; when a difference between the current global location and the prior global location is greater than or equal to a predetermined difference threshold: detecting a second feature of the object and determining whether the object is the charging station; when the object is the charging station, setting a temporary restricted zone.

A mobile autonomous agricultural system including a powered mobile unit for carrying agricultural equipment, and configured to move along rows of crops; at least one laser curtain sensor configured to project a laser curtain away from the mobile unit; a location module configured to monitor a location of the mobile unit relative to a row; a controller configured to control the travel of the mobile unit; a safety module configured to: receive a location signal from the location module related to the location of the mobile unit relative to a row, select a mode of operation to process the laser curtain in a predefined laser curtain pattern, based on the received location signal, each mode of operation corresponding to a different predefined laser curtain pattern, and to generate a safety output in response to determining that the laser curtain is interrupted within the laser curtain pattern.

A map generation method including receiving a map editing request for a specific floor among a plurality of floors of a building, providing an editing interface on a display unit of an electronic device in response to the map editing request, the editing interface including at least a part of a specific map corresponding to the specific floor, specifying at least one node group allocatable on the specific map based on first node rules, the first node rules corresponding to spatial characteristics of the specific floor, and performing a node placement process such that first nodes included among the at least one node group are placed on the specific map.

A mobile robot can have a safety system that is configured to stop the mobile robot when an object is detected inside of a safety zone. The size of the safety zone can change based on the speed of the robot. The robot can predict future safety zones and determine whether objects would be inside of the predicted future safety zones. The robot can change its trajectory, such as by slowing down, so that the actual safety zone of the robot avoids the object. Accordingly, the mobile robot can avoid the object without stopping and without triggering the safety system of the robot. The mobile robot is configured to look ahead and predict likely safety events, and then take action to avoid the predicted safety events.

The present invention discloses a method for UAV path planning in urban airspace based on a safe reinforcement learning (RL) algorithm called shield-DDPG, which combines a shield model with a DDPG algorithm and pertains to the field of UAV technologies. The method takes an attractive force from the destination point into account when an action is selected, which improves the convergence speed of the algorithm and also improve the efficiency of UAV path planning. More importantly, the method provided by the present invention can effectively verify safety of an action in terms of the air collision risk and the ground impact risk, and ensure that a final output of the algorithm is a safe optimal solution. Therefore, the present invention can effectively solve the problem that when the RL algorithm is used for UAV path planning, it is difficult to ensure the safety of the learning or execution process due to the lack of hard constraints.

A method includes obtaining data associated with a specified airspace indicating or identifying manned flights within the specified airspace and identifying one or more exclusion zones associated with one or more manned flights within the specified airspace based on the data. Each exclusion zone identifies a volume from which one or more flight vehicles are excluded from operating within the specified airspace. The method also includes modifying each exclusion zone in order to randomly change a shape of exclusion zone and generate one or more modified exclusion zones. In addition, the method includes providing information defining the modified exclusion zone(s) to one or more flight vehicle operators so that the one or more flight vehicle operators are able to avoid operating the flight vehicle(s) in the modified exclusion zone(s). The information defining modified exclusion zone(s) lacks information identifying the manned flights within the exclusion zone(s).

The present invention discloses a method for UAV path planning in urban airspace based on a safe reinforcement learning (RL) algorithm called shield-DDPG, which combines a shield model with a DDPG algorithm and pertains to the field of UAV technologies. The method takes an attractive force from the destination point into account when an action is selected, which improves the convergence speed of the algorithm and also improve the efficiency of UAV path planning. More importantly, the method provided by the present invention can effectively verify safety of an action in terms of the air collision risk and the ground impact risk, and ensure that a final output of the algorithm is a safe optimal solution. Therefore, the present invention can effectively solve the problem that when the RL algorithm is used for UAV path planning, it is difficult to ensure the safety of the learning or execution process due to the lack of hard constraints.