Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving, at each of multiple time steps, sensor data captured by an onboard sensor of a drone at the time step, providing an input including the sensor data to a drone control neural network having a brain emulation sub-network with an architecture that is specified by synaptic connectivity between neurons in a brain of a biological organism, including instantiating a respective artificial neuron in the brain emulation sub-network corresponding to each of multiple biological neurons in the brain of the biological organism, and instantiating a respective connection between each pair of artificial neurons, processing the input using the drone control neural network to generate an action selection output, and selecting an action to be performed to control the drone at the time step based on the action selection output.

Methods and associated systems for autonomous package delivery utilize a UAS/UAV, an infrared positioning senor, and a docking station integrated with a package delivery vehicle. The UAS/UAV accepts a package for delivery from the docking station on the delivery vehicle and uploads the delivery destination. The UAS/UAV autonomously launches from its docked position on the delivery vehicle. The UAS/UAV autonomously flies to the delivery destination by means of GPS navigation. The UAS/UAV is guided in final delivery by means of a human supervised live video feed from the UAS/UAV. The UAS/UAV is assisted in the descent and delivery of the parcel by precision sensors and if necessary by means of remote human control. The UAS/UAV autonomously returns to the delivery vehicle by means of GPS navigation and precision sensors. The UAS/UAV autonomously docks with the delivery vehicle for recharging and preparation for the next delivery sequence.

Various embodiments relate to unmanned vehicle navigation. A navigation system may include one or more processors configured to communicatively couple with an unmanned vehicle. The one or more processors may be configured to receive an image from the unmanned vehicle and detect a feature within the image. The one or more processors may be further be configured to determine a location of the unmanned vehicle based on the feature and convey one or more commands to the unmanned vehicle based on the location of the unmanned vehicle. Associated methods and computer-readable medium are also disclosed.

A delivery system including a vehicle in which a package addressed to a specific user is stored, and a moving body deployed at a delivery site of the package: the moving body including: a first memory, and a first processor that is connected to the first memory; and the first processor being configured to: transmit and receive predetermined information, and perform control, in a case in which the vehicle is proximate to the delivery site, to move the moving body from the delivery site toward the vehicle, to retrieve the package, and then to move the moving body back to the delivery site.

Systems and methods are disclosed for transporting people using air vehicles.

In order for a mobile terminal to land at an appropriate landing point in reaction to a change of an incident that may occur while the mobile terminal flies along a flight path, a control apparatus 100 includes: an information acquisition section 131 configured to acquire, according to a flight of a first mobile terminal (mobile terminal 200a) performed based on a flight path to a first landing point, information on one or more second landing points associated with the flight path to the first landing point; and a first communication processing section 133 configured to transmit the information on the one or more second landing points to the first mobile terminal (mobile terminal 200a) via a mobile communication network 300.

An automated modular vehicle configuration system and method that comprises a Configuration Management Unit in the vehicle that detects assemblies attached to the vehicle and configures the vehicle's autopilot based on the detected assemblies. Each attached assembly comprises mechanical and electrical components, ports and a memory device that contains identification information and data related to the assembly, such as assembly type, propulsion type, position, flight time, manufacturing date. Users can swap assemblies on the vehicle in order to provide different features to the vehicle. In particular this invention relates to drone vehicles that can be configured with different types of propulsion systems with different performance profiles and equipment such as gimbals, cameras, landing gear, measurement payloads and such. The invention also automatically downloads vehicle configuration parameters and autopilot firmware updates. Vehicle configuration and logs can be sent to the cloud for safekeeping and further analysis.

In the method, an unmanned aerial system application enabler (UAE) server can determine that a first UAV (UAV-1) is to be replaced with a second UAV (UAV-2) based on a received request. The UAV-2 is recognized by the UAE server based on a Civil Aviation Authority (CAA) level identity (ID) of the UAV-2. A request to perform a group membership update is sent by the UAE server to a SEAL group management (GM) server. The group membership update replaces the UAV-1 with the UAV-2. A response message is received by the UAE server from the SEAL GM server. The request to perform the group membership update includes (i) an ID of an UAE client that corresponds to the group of the UAV-1 and the UAV-C, (ii) a user equipment (UE) ID of the UAV-1, (iii) a UE ID of the UAV-2, and (iv) the CAA-level ID of the UAV-2.

Localization systems and methods for transmitting timestampable localization signals from anchors according to one or more transmission schedules. The transmission schedules may be generated and updated to achieve desired positioning performance. For example, one or more anchors may transmit localization signals at a different rate than other anchors, the anchor transmission order can be changed, and the signals can partially overlap. In addition, different transmission parameters may be used to transmit two localization signals at the same time without interference. A self-localizing apparatus is able to receive the localization signals and determine its position. The self-localizing apparatus may have a configurable receiver that can select to receive one of multiple available localization signals. The self-localizing apparatuses may have a pair of receivers able to receive two localization signals at the same time. A bridge anchor may be provided to enable a self-localizing apparatus to seamlessly transition between two localization systems.

An autonomous vehicle that is equipped with image capture devices can use information gathered from the image capture devices to plan a future three-dimensional (3D) trajectory through a physical environment. To this end, a technique is described for image-space based motion planning. In an embodiment, a planned 3D trajectory is projected into an image-space of an image captured by the autonomous vehicle. The planned 3D trajectory is then optimized according to a cost function derived from information (e.g., depth estimates) in the captured image. The cost function associates higher cost values with identified regions of the captured image that are associated with areas of the physical environment into which travel is risky or otherwise undesirable. The autonomous vehicle is thereby encouraged to avoid these areas while satisfying other motion planning objectives.