PORTLAND, Ore.–A new strategy for coordinated flight of unmanned aerial vehicles (UAVs) devised by the Swiss Federal Institute of Technology uses coordinated communications to allow a single operator to control an entire swarm of ultra-cheap robotic planes, rather than depending on expensive radar or lasers to locate and coordinate the flight of swarms or UAVs.
Created in the Laboratory of Intelligent Systems at the Ecole Polytechnique Federale de Lausanne (EPFL), the Swarming Micro Air Vehicle Network (SmavNet) project uses small (32-inch wingspan), lightweight (under 1 pound) UAVs with an electric motor and two control surfaces (ailerons and elevators) running on a single lithium-polymer battery with a flight-time of 30 minutes. The UAVs use GPS for location and WiFi for communications plus only three inexpensive sensors—a single MEMS gyroscope and two pressure sensors.
The swarm-interface requires only the simplest directions from a single operator on a ground-based computer, where algorithms send the control signals to each UAV—consisting of altitude, airspeed and turning rates. Currently the team is experimenting with two control algorithms. One is derived from the observation of ants, who use pheromone to coordinate swarms. The second uses machine learning to evolve unique algorithms for specific tasks.
Unmanned aerial vehicles communicate with each other and the ground to fly in coordinated swarms for search and rescue operations.
The ant-derived approach uses airborne pheromones to set up a grid of responsibility for each UAV which patrols its sector while flying a circular pattern. The second approach uses unique flight patterns discovered by a machine learning algorithm, which are then reverse-engineered into a controller. Reverse-engineered controllers have so far demonstrated several useful behaviors not exhibited by the ant-derived algorithm, including exploration, synchronization and relayed communications.
UAVS run Linux on a lithium-polymer battery powered single-board computer with an off-the-shelf WiFi receiver, a GPS module and a ZigBee transmitter.
Still in the development stage, the safety issues of controlling swarms of UAVs has been demonstrated to the satisfaction of the Swiss Federal Office for Civil Aviation, from whom official authorization for beyond-line-of-sight swarm operation has been granted for the tests.
Very interesting topic and briefing, I wonder if there is any form of redundancy, in case there are single or multiple vehicle failures ( due to obstacles, wind sheer or other forces that could knock off the comm, or the complete functionality ). I see a very challenging effort to keep it robust!
In-air collision avoidance was one of the criteria used by the Swiss Federal Office for Civil Aviation when issuing its license to operate beyond line-of-sight. Different algorithms are used, but one aspect is to make sure that UAVs in adjacent sectors are flying at different heights--similar to airliner requirements.
The missing element in the description seems to be how obstacles are avoided. If ants bump into an unexpected obstacle (slowly enough that no damage is done), their sense of touch enables them to detect the impact, reroute slightly, and continue in the intended direction. They remain firmly grounded throughout the process. Aircraft are much less forgiving about bumping into obstacles and then continuing on a slightly modified routing.
What an interesting idea! I am very curious to learn what form the airborne pheromones take. I could imagine a number of possible solutions but would like to know more from the designers. There is a lot of detail in the article and pictures but no sensors for use by the swarm? I was expecting video camera or airborne gas type sensors but could not discern any type of sensors in the diagrams. The pressure sensors would be used (I imagine) for flight / altitude control while the GPS for navigation. Still, a very neat idea to mimic ants, perhaps bee behavior would be a better model (given flight).
David Patterson, known for his pioneering research that led to RAID, clusters and more, is part of a team at UC Berkeley that recently made its RISC-V processor architecture an open source hardware offering. We talk with Patterson and one of his colleagues behind the effort about the opportunities they see, what new kinds of designs they hope to enable and what it means for today’s commercial processor giants such as Intel, ARM and Imagination Technologies.