TREE NEWS update: NeuroXess disclosed on Nov. 16 that a fully implanted, fully wireless brain-computer interface paired with an AI system let a clinically paralyzed participant complete continuous real-world tasks — commuting, home, social and work — in a simulated-life testbed. The core decoding latency is under 50 milliseconds, and first-attempt completion of tasks such as going out, obstacle avoidance and walking forward reached 84%. Training time for new tasks like shopping fell from 10.5 hours to 2 hours on average.
NeuroXess reports 84% success rate in continuous BCI daily-task trial
The headline number matters less than the setting: this is a simulated-life testbed with a single participant, so the 84% first-attempt figure describes feasibility under controlled conditions rather than reliability in uncontrolled environments. The more telling metric is the drop in new-task training time, which hints at a generalizable decoding approach rather than per-task tuning — the kind of gain that determines whether BCI use scales beyond lab demos. Whether these results hold across more participants and unscripted settings is the open question.
Generated by AI for reference only.
Share on WeChat
Open WeChat → Scan → then tap "…" to send to a chat or Moments.
Tap "…" in the top-right corner to send to a chat or share to Moments.