A team led by Professor Xu Guanghua at Xi'an Jiaotong University has created a method to control a robot dog using thought.
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, which captures neural activity signals using specialized sensors, allowing precise control of mechanical devices.
Xu described the system as a kind of "remote control in the mind."
When a user intends to move forward, the brain generates corresponding EEG signals. The system collects and decodes these signals, identifies the intended command, converts it into a control instruction, and sends it to the robot dog, which then executes the task.
Currently, the system supports 11 basic commands, including moving forward, backward, and turning. The recognition accuracy exceeds 95%, with a delay of about one second between thought and action.
Invasive BCI technologies offer high precision but require surgical implantation in the brain, which carries risks of injury, infection, immune rejection, and signal degradation over time.
Xu's approach is considered safer, more cost-effective, and user-friendly. However, non-invasive signals are less precise, making continuous and fine control in real-time challenging.
The team opted for a hybrid approach that employs a model of human-machine collaboration.
“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 executing movements, are handled by the machines' own intelligent systems,” said Xu.
This approach enhances the efficiency and stability of the solution, allowing it to overcome the limitations associated with the accuracy of non-invasive signals.
The scientist noted that the development of BCI requires regular breakthroughs in fundamental technologies and deep integration with advanced fields like artificial intelligence and autonomous navigation.
According to Xu, the robot dog could serve as a valuable assistant for people with disabilities.
It is worth mentioning that from March 25 to 29, the ZGC Forum was held in Beijing, where developers showcased a wide range of BCI products, from specialized chips to rehabilitation systems.