China targets air, land and sea integration for its next-generation drone swarms

China is moving beyond large formations of identical drones toward a more ambitious goal: a network that can coordinate uncrewed systems across the air, land and sea, according to the country’s leading developer of drone-swarm technology. In a recent article published through China Electronics Technology Group Corporation (CETC), its Intelligent Technology Research Institute described drone swarms as more than large numbers of aircraft flying together. Instead, it characterized them as distributed systems in which individual platforms communicate, coordinate, make local decisions, and collectively generate capabilities. The assessment provides a rare look at how Chinese researchers view the current state and future direction of the country’s swarm technology. From hundreds of drones to an intelligent network China has made significant progress with homogeneous swarms, where large numbers of similar drones operate together. CETC says these systems have demonstrated decentralized networking, dynamic reconfiguration, and adaptive algorithms that allow formations to recover from individual losses, communication disruptions, and electromagnetic interference. CETC identifies five capabilities that determine whether such systems can function effectively in a battlefield: survivability, situational awareness, planning and decision-making, mission execution, and autonomous learning and evolution. The institute says China has developed mature capabilities in several of these areas, but also acknowledges that significant challenges remain. In survivability, for example, homogeneous swarms can reportedly reconfigure their networks and continue operating after losing individual nodes or experiencing communications disruption. However, maintaining that resilience when different types of uncrewed systems operate together across multiple domains remains a challenge. Sharing what individual drones cannot see One of the principal advantages of a swarm is its ability to combine information from multiple platforms. CETC says China’s distributed sensing systems can fuse data collected by multiple drones to overcome the limitations of individual aircraft. The swarms can autonomously screen targets, identify camouflage, and determine target locations while building a broader picture of their surroundings. But the researchers acknowledge that detecting and identifying small, concealed objects with weak signatures becomes much harder amid heavy background clutter and intense electronic interference. The same pattern appears in decision-making. Chinese swarm systems have demonstrated autonomous formation changes, route planning, collision avoidance, and dynamic task allocation, but more advanced capabilities, such as developing novel tactics in unfamiliar environments against capable adversaries, remain under development. The difficult step is mixing different machines According to SCMP, CETC describes the ultimate objective as a heterogeneous, all-domain swarm, in which different uncrewed platforms can cooperate across air, land and sea. That could eventually allow aerial drones, ground vehicles and maritime systems to contribute different sensors, mobility and payloads to the same network rather than operating as separate systems. Getting there, however, is substantially harder than coordinating identical drones. Different platforms have different communications requirements, sensors, movement characteristics and operating environments. They must also work together with military units from different services. CETC says current systems can support a broad operational cycle ranging from reconnaissance and electromagnetic suppression to precision strikes and battle-damage assessment, but air-ground-sea coordination and joint-service adaptability remain gaps. The institute also says swarm AI has progressed beyond fixed programming toward adaptive optimization and experience accumulation through reinforcement learning and adversarial iteration. Fully autonomous real-time evolution and more advanced forms of collective intelligence, however, remain future goals. China’s swarm roadmap The development path outlined by CETC is relatively clear: first mature systems composed of the same type of drone, then solve the technical problems involved in coordinating different platforms, and ultimately connect uncrewed systems across operational domains. Recent demonstrations illustrate why the technology is attracting attention. Global Times reported that CCTV showed China’s Atlas drone-swarm operations system in March, comprising the Swarm-2 ground combat vehicle, a command vehicle and a support vehicle. In July, Chinese researchers also used drone swarms to conduct multi-dimensional observations of a typhoon’s landfall. CETC simultaneously warned that rapid growth in the sector has produced overlapping projects, redundant development and an excessive focus on demonstrations rather than measurable capabilities. The institute says future progress will therefore depend not only on better algorithms, but also on common standards, interoperable interfaces, realistic testing and improved resistance to electronic interference.For now, China’s most mature capability appears to be the coordination of large numbers of similar drones. The much harder goal is turning those formations into a distributed network of different autonomous systems operating together across air, land and sea.Get the latest in engineering, tech, space & science - delivered daily to your inbox.Kaif Shaikh is a journalist and writer passionate about turning complex information into clear, impactful stories. His writing covers technology, sustainability, geopolitics, and occasionally fiction. A graduate in Journalism and Mass Communication, his work has appeared in the Times of India and beyond. After a near-fatal experience, Kaif began seeing both stories and silences differently. Outside work, he juggles far too many projects and passions, but always makes time to read, reflect, and hold onto the thread of wonder.