Advancements in Coordination Strategies for Multiple Drones

Controlling unmanned vehicles to prevent collisions and reduce user burden when multiple vehicles are operated. It provides autonomous control for commercial off-the-shelf unmanned vehicles via an add-on controller that receives user inputs and generates modified control signals to instruct the vehicles to follow pre-determined routes. The controller analyzes the user inputs and extracts the intended maneuvering commands while discarding velocity changes. To avoid collisions, the routes are generated by a server based on sensor data and deconflicting with other vehicles.

Source

Centralized management of a plurality of unmanned aerial vehicles (UAVs) of different types for preventing complication of processing related to information acquisition from each UAV, even in a case where flight management of a plurality of types of UAVs different from each other is performed. The technique involves using an information communication device attached to the UAVs that acquires flight status information and transmits it wirelessly in a predetermined data format. A centralized management device receives and monitors the UAVs using the flight status information transmitted from the information communication device. This standardized format allows uniform acquisition of flight status from different UAV types.

Source

Using reinforcement learning to generate optimal operation plans for multi-drone networks performing cooperative tasks like data sensing and communication relay. The approach trains actor neural networks for each drone to learn policies for state-based decision making. These policies are then used to generate a plan by simulating the game state, obtaining observations, inferring actions, and recording the history. The resulting plan provides coordinated task execution that maximizes efficiency while maintaining network connections.

Source

Detecting, quantifying and GPS-locating trace gases using unmanned aerial vehicles (UAVs) to monitor the presence of gases like methane, propane, carbon dioxide, and volatile organic compounds in real time. The UAV carries gas sensors along with environmental sensors like temperature, humidity, and barometric pressure sensors. The UAVs are flown in coordinated patterns to simultaneously detect gases at different locations in an area of interest. This enables efficient, periodic monitoring of ambient air quality as well as detecting point source pollution events. The system can detect both anthropogenic and biogenic sources of pollution.

Source

Autonomous vehicle (AV) team coordination system that allows AVs to continue functioning as a team even when communication is disrupted. The system uses controllers on each AV to store mission data including objectives and default trajectories. If communication is lost, AVs can estimate teammate trajectories based on the stored mission data.

Source

An autonomous vehicle team coordination system that facilitates efficient search operations with multiple autonomous vehicles. The system involves capturing measurement data from sensors on each vehicle, matching time slices of data between vehicles, and using that to build a synchronized occupancy map of the environment. This allows the vehicles to share what areas have been searched or not, even when communication is intermittent due to the changing environment.

Source

A system and method for managing unmanned aerial vehicle (UAV) data transmission in a smart city using the Internet of Things (IoT). The system involves a management platform that coordinates multiple UAVs performing different missions by assigning them to specific time domains and airspaces. This allows efficient data collection without interference. The platform also uses techniques like relay transmission, split transmission, and merging transmission to improve transmission efficiency based on the data requirements and features.

Source

Automated modular multi-vehicle teaming for unmanned systems with payloads like sensors, weapons, and cargo. It enables efficient and survivable missions with a team of unmanned vehicles. The team is led by a primary asset with critical payload, surrounded by secondary assets. They fly in a formation that provides surveillance and protection. If secondary assets are lost, the primary can continue. The secondary assets autonomously reposition based on mission priorities or losses. The team uses algorithms to navigate airspace safely against threats. The guidance commands are computed in real-time to enable complex missions with diverse payloads.

Source

Coordinated swarms of UAVs that can autonomously detect, intercept and capture rogue drones to neutralize threats from unauthorized or dangerous drones. The system uses multiple counter-attack UAVs equipped with nets that can be deployed to capture target drones. An external drone detection system provides target tracking data to the counter-attack UAVs. The coordinated swarm intercepts the target drone and captures it in the net, effectively neutralizing the threat. The counter-attack UAVs autonomously coordinate their flight to surround and capture the target drone in the net.

Source

Autonomous control system for unmanned aerial vehicle (UAV) swarms that allows dynamic, adaptive control of the swarm while avoiding collisions and failures. The system receives flight commands from operators, generates fleet configuration instructions and safety information for each UAV, and only transmits the instructions if all UAVs can safely carry them out. Each UAV checks for collision risks and modifies instructions if necessary. This allows direct control of the swarm while mitigating risks.

Source

Dynamic anchor selection for swarm localization that allows a swarm of robotic agents to accurately estimate their positions relative to each other using a subset of the robots as stationary anchor points. The anchors are intelligently selected based on metrics like localization confidence, connectivity, capability, task criticality, and history. This improves accuracy over time compared to iterative estimation methods that can suffer from drift. The anchors help estimate positions of the non-anchor robots. The robots take turns being anchors based on confidence metrics.

Source

Orchestrating drone swarms that can autonomously coordinate their actions. The orchestration involves a lead drone evaluating and adapting to add new drones that request to join the swarm. The lead drone sends a swarm directive to the candidate drone and evaluates its capabilities and objectives to determine compatibility. If compatible, the swarm directive is adjusted to add the candidate drone to the swarm. This allows heterogeneous drones to join and collaborate in coordinated swarms.

Source

Dynamic coordination of a swarm of unmanned aerial vehicles (UAVs) that can adapt their flight formations in real time while avoiding collisions and staying on a designated path. The UAVs form a spatially constrained swarm with a centroid that must stay within a certain radius of the path centroid. On-board sensors and processors detect and avoid other UAVs entering their inner bubble. A ground station plans the path and monitors the swarm centroid location.

Source