用AI智能体在仿真中教Microduck机器人行走
原标题：Using AI Agents to Teach Robots Like Microduck to Walk in Simulation
AI 摘要
NVIDIA 技术博客介绍了一套在仿真中训练机器人行走的工作流，以 Microduck 机器人为例。该流程使用 NVIDIA RTX Spark 作为本地开发枢纽，Hermes 和 Nemotron 3.5 Bolt 负责规划，Astra 负责资产生成与仿真，并结合 Isaac Lab、Newton 和 Omniverse 进行强化学习训练与视觉观测生成。文章展示了从提示词到障碍赛道搭建、策略训练和本地评估的完整步骤，为物理部署奠定基础。
正文节选
Teaching a robot to navigate an obstacle course requires more than a walking policy. It must perceive its surroundings, maintain balance, and adjust its actions when obstacles block the path ahead. Developing these capabilities connects several stages: creating assets and an environment, using physics simulation to model how the robot interacts with its environment, and training and evaluating policies in simulation. NVIDIA RTX Spark serves as a local development hub, supporting AI-assisted plan