China developed a drone swarm that can fly effortlessly through an entire forest

Researchers at Zhejiang University in China have developed the necessary technology for a drone swarm to fly through uncontrolled environments completely autonomously, Science Alert reported. 

The world has gone quickly from using single drones to drone swarms, at least in military settings. While some countries are still getting used to drones in warfare, we reported that Israel had flown a drone swarm using artificial intelligence (AI) last year. While most technology is not in the public domain, the video above shows that it is not very difficult either. 

Inspired by birds, built by university researchers

Luckily, the developers of this technology are part of a research group, which was inspired by bird swarms flying through dense woods, and aims to use the technology for conservation and disaster relief work. Since human-operated drones are currently doing these tasks, one might argue the need for a swarm. The answer is simple: efficiency. 

Despite all their technological developments, drones are still limited by their flight times. So, instead of flying a drone multiple times over to get a task done, a swarm could map an area or survey damage quickly and improve response rates. 

For instance, having a drone swarm surveil earthquake-hit zones or buildings deemed unsafe for people could generate a more comprehensive map of the relief measures needed than what a single human-operated drone would ever provide. 

Previous reports of drone swarm testing have occurred either in controlled environments or with details of obstacles programmed in. So, the flight of the drone swarm through a bamboo forest is quite remarkable. We have seen disasters with drone swarms before. 

How does the swarm work?

The swarm consists of palm-sized robots equipped with altitude sensors, depth cameras, and an onboard computer. Unlike the Israeli drone swarm cited above, this drone swarm does not rely on a global positioning system (GPS) or external guidance. So, collision avoidance, swarm coordination, and flight efficiency are all encoded into this algorithm, which is quite a feat. 


Apart from the forest, the team has also tested the swarm by asking it to follow a person’s lead and avoid other drones in high traffic zones experiment, Science Alert reported. 

The challenge of operating in a city with people and vehicles is undoubtedly a big one up ahead. Details of the research for the swarm are in the public domain and were published in Science Robotics


Aerial robots are widely deployed, but highly cluttered environments such as dense forests remain inaccessible to drones and even more so to swarms of drones. In these scenarios, previously unknown surroundings and narrow corridors combined with requirements of swarm coordination can create challenges. To enable swarm navigation in the wild, we develop miniature but fully autonomous drones with a trajectory planner that can function in a timely and accurate manner based on limited information from onboard sensors. The planning problem satisfies various task requirements including flight efficiency, obstacle avoidance, and inter-robot collision avoidance, dynamical feasibility, swarm coordination, and so on, thus realizing an extensible planner. Furthermore, the proposed planner deforms trajectory shapes and adjusts time allocation synchronously based on spatial-temporal joint optimization. A high-quality trajectory thus can be obtained after exhaustively exploiting the solution space within only a few milliseconds, even in the most constrained environment. The planner is finally integrated into the developed palm-sized swarm platform with onboard perception, localization, and control. Benchmark comparisons validate the superior performance of the planner in trajectory quality and computing time. Various real-world field experiments demonstrate the extensibility of our system. Our approach evolves aerial robotics in three aspects: capability of cluttered environment navigation, extensibility to diverse task requirements, and coordination as a swarm without external facilities.