Brain organoid computing for robotic decision-making
Hongwei Cai, Chunhui Tian, Yang Yang, Yantao Xing, Zichen Hong, Huiyu Chu, Jiansen Wang, Zheng Ao, Jason S. Meyer, James Robert Friend, Jason Tchieu, Mingxia Gu, Insoo Hyun, Ken Mackie, Lantao Liu, Feng Guo · bioRxiv (Cold Spring Harbor Laboratory) · 2026
Biomimicry has inspired the evolution of robotics toward greater autonomy, adaptability, and symbiosis with humans and dynamic environments. However, current robotic systems still face major challenges in recapitulating the high-efficiency decision-making capabilities of the human brain under complex and dynamic conditions. Here, we present Brainobot, a biohybrid robotic system that establishes a brain organoid controller as a high-level robotic decision-making layer for closed-loop embodiment. By leveraging brain organoid reservoir computing, Brainobot interacts with dynamic environments by receiving and processing sensory inputs and generating motor actions. As a proof-of-concept demonstration, Brainobot is implemented in a humanoid robotic system to perform real-world tasks, including object grasping and laser chasing. Interestingly, Brainobot exhibits unique features, including cross-task adaptivity, high computing efficiency, and low energy consumption. Thus, our approach may provide insights for advancing robotic embodiment and understanding biological decision-making.