In a method of transporting cargo suspended by multiple UAVs, each of the multiple UAVs flies such that a relative positional relationship of each of the multiple UAVs to the cargo is maintained. This method of transporting cargo is achieved by one or both of a ground position control mode in which flight of each of the multiple UAVs is controlled to follow a change in a position of the cargo relative to the ground, and an interval control mode in which the flight of each of the multiple UAVs is controlled so as to maintain an interval of each of the multiple UAVs to the cargo.

A method includes operating a driverless transport system with a plurality of battery-operated and driverless vehicles for transporting a consignment of goods over a drivable logistics region having a supply device. The supply device has at least one receptacle which receives at least one vehicle and is movable in at least one vertically oriented plane in a storage region. The method includes the steps of: supplying at least one vehicle by means of the receptacle in the logistics region; positioning the at least one vehicle at the consignment of goods; coupling the consignment of goods to the at least one vehicle and transporting the consignment of goods by the at least one vehicle from a first location to a second location; depositing the consignment of goods; receiving the at least one vehicle by the receptacle of the supply device; and moving the at least one receptacle with the vehicle.

A moving object operation management device for managing the operation of moving objects that move in a passage provided in an area and perform work at a specific place. When the work of a certain moving object hinders the movement of another moving object in a passage, the exclusive section and the exclusive section for one of the two moving objects are adjacent to each other, and when the movement of the shortest path to the next destination is hindered by the other exclusive section, the first operation instruction for moving one to the next exclusive section and after the exclusive section of the other section is released. And a second operation instruction to move the one moving object to the next destination by the shortest path, by comparing the arrival time to the one of the next destination in accordance with the instructions, configured to selectively emit.

One aspect of an autonomous traveling device includes: a recognition unit that recognizes an obstacle for each of right and left regions sandwiching a body of the autonomous traveling device; a direction calculation unit that calculates a direction along the obstacle for each of the right and left regions; and a deviation control unit that causes the body to move away from the obstacle by combining a rotational movement that changes orientation of the body toward an intermediate direction of each of the directions calculated by the direction calculation unit and a backward movement that causes the body to move backward.

Provided are a remote driving control method and apparatus, a computer device, and a storage medium, belonging to the field of remote driving technologies. The method may include: predicting network quality between a remotely driven vehicle and a remote driving server within a target time period, the network quality prediction including a predicted network parameter corresponding to each time point within the target time period; determining, from the target time period according to the predicted network parameter corresponding to each time point within the target time period and a current network parameter between the remotely driven vehicle and the remote driving server, a target time point at which network quality changes; and adjusting a driving control policy of the remotely driven vehicle based on a predicted network parameter corresponding to the target time point, to control the remotely driven vehicle according to an adjusted driving control policy.

Systems and methods for vehicle localization are provided for a robotic vehicle, such as an autonomous mobile robot. The vehicle can be configured with multiple localization modes used for localization and/or pose estimation of the vehicle. In some embodiments, the vehicle comprises a first set of exteroceptive sensors and a second set of exteroceptive sensors, each being used for a different localization modality. The vehicle is able to disregard at least one localization modality for a number of different reasons, e.g., the disregarded location modality is adversely affected by the environment, to use less than the full complement of localization modalities to continue to stably localize the vehicle within an electronic map. In some embodiments, a localization modality may be disregarded for pre-planned reasons.

An autonomous vehicle which includes multiple independent control systems that provide redundancy as to specific and critical safety situations which may be encountered when the autonomous vehicle is in operation.

A control device for a moving body includes a storage medium configured to store computer-readable instructions, and a processor connected to the storage medium, wherein the processor executes the computer-readable instructions to recognize a surrounding situation of a moving body based at least on an image of the surrounding situation of the moving body, to generate a route from the moving body to a destination based on the recognized surrounding situation and the set destination, to determine whether or not the generated route is within a predetermined region defined by a current position of the moving body and the destination, to control the moving body so that the moving body moves along the generated route to the destination, and to turn the moving body on a spot and to regenerate a route from the moving body that has turned on the spot to the destination when it is determined that the route deviates from the predetermined region.

A system for faster object attribute and/or intent classification may include an machine-learned (ML) architecture that processes temporal sensor data (e.g., multiple instances of sensor data received at different times) and includes a cache in an intermediate layer of the ML architecture. The ML architecture may be capable of classifying an object's intent to enter a roadway, idling near a roadway, or active crossing of a roadway. The ML architecture may additionally or alternatively classify indicator states, such as indications to turn, stop, or the like. Other attributes and/or intentions are discussed herein.

Systems and techniques are provided for management of autonomous cargo by autonomous vehicles (AVs). An example method can include determining, based on data from one or more sensors, a location for deploying a ramp that enables robots to enter the AV, the location comprising an area free of obstacles having one or more dimensions above a threshold; generating an instruction configured to trigger the AV to stop at the location; based on a determination that the AV is at the stopping position, deploying the ramp; sending, to the robots, a message instructing the robots to enter a cabin of the AV via the ramp and guiding each robot to a respective location within the cabin; and based on a determination that the AV has reached a destination of one or more robots, deploying the ramp and guiding the one or more robots to exit the cabin via the ramp.