Follow a multi-step verbal instruction to complete a household task.
Plan and execute long-horizon tasks autonomously in novel environments without human correction.
Short-horizon tasks in structured settings; SayCan-style grounded planning with LLMs.
Long-horizon tasks beyond ~10 steps; recovery when early steps fail or environment changes.
| Technology | Quality | Source | Score vs. baseline | Score |
|---|---|---|---|---|
| Figure 03 | vendor reported | figure.ai/news | 38% |