At Xi’an Jiaotong University, Professor Xu Guanghua’s team has devised a method to control a robot dog using thought power.
Mind-controlled robot dogs? They’re real now at China’s Xi’an Jiaotong University. Just think “forward” — and the robot dog moves. Professor Xu Guanghua’s team made it happen with the non-invasive brain-computer interface technology. #FutureChina pic.twitter.com/3pIL7FffRv
— China Xinhua Sci-Tech (@XHscitech) March 29, 2026
The solution is based on non-invasive brain-computer interface (BCI) technology. It captures neural activity signals using special sensors, allowing precise control of mechanical devices.
Xu described the system as a kind of “remote control in the mind.”
When a user forms an intention like “move forward,” the brain generates corresponding EEG signals. The system collects and decodes them, identifies the intended command, converts it into a control instruction, and sends it to the robot dog, which executes the task.
At the current stage, the solution supports 11 basic commands such as moving forward, backward, and turning. The recognition accuracy exceeds 95%, and the delay between thought and action is about one second.
Invasive BCI technologies offer high accuracy but require surgical implantation in the brain. This carries certain risks of injury, infection, immune rejection, and signal quality degradation over time.
Guanghua’s approach is considered safer, more economical, and user-friendly. However, non-invasive signals are less precise, complicating continuous and fine real-time control.
The team decided to apply a hybrid approach, employing a human-machine collaboration model.
“Humans are responsible only for formulating high-level intentions like ‘where to go.’ Meanwhile, high-precision, high-speed, and repetitive tasks such as autonomous navigation, environmental perception, dynamic obstacle avoidance, and movement execution are performed by the machines’ own intelligent systems,” said Guanghua.
This approach enhances the efficiency and stability of the solution, allowing it to overcome limitations associated with the accuracy of non-invasive signals.
The scientist noted that the development of BCI requires regular breakthroughs in basic technologies and deep integration with advanced fields such as artificial intelligence and autonomous navigation.
According to Guanghua, the robot dog could become a valuable assistant for people with disabilities.
Earlier in March, the ZGC Forum was held in Beijing from the 25th to the 29th, where developers showcased a wide range of BCI products—from specialized chips to rehabilitation systems.