The advancement of insect-computer hybrid robots holds significant promise for navigating complex terrains and enhancing robotics applications. This study introduced an automatic assembly method for insect-computer hybrid robots, which was accomplished by mounting backpack with precise implantation of custom-designed bipolar electrodes. We developed a stimulation protocol for the intersegmental membrane between pronotum and mesothorax of the Madagascar hissing cockroach, allowing for bipolar electrodes' automatic implantation using a robotic arm. The assembly process was integrated with a deep learning-based vision system to accurately identify the implantation site, and a dedicated structure to fix the insect (68 s for the whole assembly process). The automatically assembled hybrid robots demonstrated steering control (over 70 degrees for 0.4 s stimulation) and deceleration control (68.2% speed reduction for 0.4 s stimulation), matching the performance of manually assembled systems. Furthermore, a multi-agent system consisting of 4 hybrid robots successfully covered obstructed outdoor terrain (80.25% for 10 minutes 31 seconds), highlighting the feasibility of mass-producing these systems for practical applications. The proposed automatic assembly strategy reduced preparation time for the insect-computer hybrid robots while maintaining their precise control, laying a foundation for scalable production and deployment in real-world applications.

翻译：昆虫-计算机混合机器人的发展为复杂地形导航和机器人应用拓展带来了重要前景。本研究提出了一种昆虫-计算机混合机器人的自动装配方法，该方法通过搭载背包并精确植入定制设计的双极电极实现。我们针对马达加斯加发声蟑螂的前胸背板与中胸节间膜开发了电刺激方案，使双极电极能够通过机械臂实现自动植入。装配过程集成了基于深度学习的视觉系统以精确定位植入位点，并采用专用结构固定昆虫（完整装配流程耗时68秒）。自动装配的混合机器人展现出转向控制（0.4秒刺激下转角超过70度）与减速控制（0.4秒刺激下速度降低68.2%）能力，其性能与手动装配系统相当。此外，由4台混合机器人组成的多智能体系统成功覆盖了存在障碍物的室外地形（10分31秒内覆盖率达80.25%），凸显了大规模生产此类系统并投入实际应用的可行性。所提出的自动装配策略在保持精确控制能力的同时，显著缩短了昆虫-计算机混合机器人的制备时间，为实际应用中的规模化生产与部署奠定了基础。