Only 0.3% chance: Chinese Navy could avoid use of lethal weapons in disputed waters

A new AI system developed by Chinese researchers has reduced the simulated risk of a Chinese coastguard vessel using weapons during disputed-water encounters from 0.3% to zero. The system was designed to help commanders distinguish between routine maritime activity and deliberate probing or harassment, a difficult task in the so-called “grey zone” between peace and open conflict. In simulations, the AI correctly identified vessel intentions 89.6% of the time, compared with 68.5% for a conventional rule-based system. Researchers claim the technology could help reduce accidental escalation by recommending measured responses such as using water cannons instead of lethal force. Teaching AI to read vessels’ intentions The research was conducted by a team led by Sun Shengzhi, a professor at the China Coast Guard Academy, and published earlier this month in the Chinese journal Command Control & Simulation. The researchers built a computer war game around a scenario involving a Chinese coastguard vessel protecting fishing boats from simulated foreign vessels carrying out low-intensity harassment and reconnaissance. The scenario is constructed around the type of encounters that frequently occur in disputed waters, where vessels can operate aggressively without crossing the threshold into conventional military conflict, the South China Morning Post reported. The simulated vessels were required to maintain a minimum separation of 0.5 nautical miles, or about 3,000 feet, while following restrictions governing the use of weapons. Under the existing rule-based command system, the simulated coastguard vessel used lethal weapons in 0.3% of scenarios. While that figure was low, the researchers argued that even a small risk of unintended weapons use could be unacceptable in sensitive maritime confrontations. Instead, the AI system continuously calculated the probability of different vessel intentions, including harmless transit, fishing activity and coordinated probing. From radar tracks to tactical decisions The system combines radar and other sensor information with a causal model designed to determine why a vessel might be manoeuvring in a particular way. In one simulation, the AI initially assigned a 72% probability that a nearby vessel was simply passing through. When three vessels formed a wedge and began approaching from different directions, the system raised the probability of coordinated probing to 68%. Rather than escalating immediately, it ordered the use of a water cannon to deter the vessels. The researchers said the AI never triggered a weapons-use violation across the simulated scenarios. It also reduced other rule violations, such as vessels moving too close to one another, from 1.2% to 0.8%. The technology was also tested against deceptive behaviour, an in a different scenario, fishing boats appeared to retreat while vessels from another direction accelerated toward the coastguard ship. The AI interpreted the manoeuvre as a potential deception and maintained its position rather than reacting to the apparent retreat. Researchers point out that this ability could make maritime simulations more realistic while helping identify weaknesses in operational plans. While the system is not intended to completely remove human commanders from the decision-making process, the researchers envision AI supporting human operators by combining intention recognition, constrained decision-making and adaptive simulations. Get the latest in engineering, tech, space & science - delivered daily to your inbox.Bojan Stojkovski is a freelance journalist based in Skopje, North Macedonia, covering foreign policy and technology for more than a decade. His work has appeared in Foreign Policy, ZDNet, and Nature.