Fiatlux：人形机器人爬梯与更换灯泡的长时程基准
Fiatlux: A Long-Horizon Benchmark for Humanoid Ladder Climbing and Light-Bulb Replacement
查看机构详情
- Purdue University（普渡大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
Fiatlux是一个基于Isaac Lab的长期基准，用于评估人形机器人在单个回合中完成爬梯和更换灯泡任务，包含十二个子任务和难度加权评分，并提供多种基线实现。
中文摘要 AI 辅助
现有基准将桌面操作、平地家庭活动或人形机器人的运动与操作作为独立任务组进行评估；没有一个基准在单个长时程回合中同时评估垂直移动能力和对易碎负载的灵巧操作。我们提出了Fiatlux，一个基于NVIDIA Isaac Lab构建的更换灯泡基准。在一个回合中，Unitree G1人形机器人将折叠梯放置在天花板或墙壁灯具下方，爬上梯子，将插座中的旧灯泡更换为新灯泡，并将旧灯泡放入处理箱。我们将该回合分解为十二个子任务环境，并根据难度加权门限进行评分。目标是成功更换灯泡，新灯泡正确安装，旧灯泡被处理，两者均未掉落，且未超过易碎性限制。未完全成功的运行可获得部分分数。观测分为标准模式（物理机器人可感知或估计的信号）和特权模式（精确的模拟器状态）。我们规定了评估协议，并提供了参考基线实现，涵盖RSL-RL PPO、零样本NVIDIA GR00T N1.7视觉-语言-动作（VLA）模型以及全身控制器。此外，我们提供了用于指定和检查成功门限的遥操作记录。基准代码和遥操作记录可在该http URL获取。
英文摘要
Existing benchmarks evaluate tabletop manipulation, flat-floor household activity, or humanoid locomotion and manipulation as separate task groups; none scores vertical mobility and dexterous work on a fragile payload in one long-horizon episode. We present Fiatlux, a light-bulb replacement benchmark built on NVIDIA Isaac Lab. In one episode, a Unitree G1 humanoid positions a step ladder under a ceiling or wall fixture, climbs it, exchanges a spent bulb in a socket for a fresh one, and leaves the spent one in a disposal crate. We decompose the episode into twelve subtask environments scored on difficulty-weighted gates. The goal is a successful replacement, with the fresh bulb seated, the spent one disposed of, neither dropped, and a fragility bound not crossed. Runs that fall short can earn partial credit. Observations are split into a standard mode (signals a physical robot could sense or estimate) and a privileged mode (exact simulator state). We specify the evaluation protocol and provide reference baseline implementations spanning RSL-RL PPO, zero-shot NVIDIA GR00T N1.7 Vision-Language-Action (VLA) models, and whole-body controllers. Additionally, we provide the teleoperated recordings used to specify and check the success gates. The benchmark code and the teleoperated recordings are available at fiatlux-bench.github.io.
