脑机接口临床试验取得新进展

Core Insights - The research team from the Chinese Academy of Sciences has successfully completed the second clinical trial of an invasive brain-machine interface (BMI) that allows a high-level paraplegic patient to control a smart wheelchair and robotic dog using brain signals [1][2] - The technology aims to establish a direct communication channel between the brain and external devices, overcoming challenges in integrating this technology into patients' daily lives [1] Group 1: Technological Breakthroughs - The research team developed a high-compression, high-fidelity neural data compression technology, enhancing brain control performance by 15% to 20% even in noisy environments [2] - The introduction of "neural manifold alignment technology" allows for the extraction of stable low-dimensional features from high-dimensional dynamic neural signals, improving the decoder's adaptability to environmental changes [2] Group 2: Performance Enhancements - The end-to-end delay from signal acquisition to command execution has been reduced to under 100 milliseconds, providing a smoother and more natural control experience for patients [2] - The team has innovated an "online recalibration technology" that allows real-time adjustments to decoding parameters during daily use, ensuring sustained high performance without interrupting the patient's operation [2] Group 3: Future Developments - A new upgraded version of the system (WRS02) has been launched, with further performance improvements, and the team plans to conduct the first clinical trial of this version soon [2]