外观
论文arXiv 2610.1788115 天前
通过生成、验证与修订的智能体式机器人创建
原文链接：Agentic Robot Creation through Generation, Verification, and Revision（arXiv 2610.17881 · 发布日期：2026-10-13）
Agentic Robot Creation through Generation, Verification, and Revision
研究将高层意图转为机器人及行为，提出设计评估指标与Roboforge，并在生成形体、多机器人行为和实体Gorilla上验证。
核心要点
- 问题聚焦AI智能体能否从高层用户意图创建机器人形体并教会其行为。
- 形体创建方面评估多模态模型对机械需求的把握，并提出制造前计算指标。
- Roboforge将任务规格转为可执行策略，并用执行反馈修订参考运动、奖励或二者。
- 实验显示计算指标暴露生成设计的机械故障，执行落地精炼改善任务行为和执行质量。
验证范围与局限：验证范围包括多个MLLM的生成形体、四种不同机器人行为，以及一个实体Gorilla直接部署。
英文摘要 (Abstract)
Can an AI agent turn high-level user intent into a functioning robot and teach it how to behave? We study this question from two complementary aspects: embodiment and behavior creation. For embodiment creation, we investigate how well current multimodal models capture mechanical requirements, and introduce computational metrics for evaluating generated designs before fabrication. For behavior creation, we present Roboforge, an agentic framework that turns task specifications into executable policies through motion generation, policy learning, and execution-grounded revision. Given a robot embodiment and task, the agent generates a reference motion, configures the learning objective, and trains a policy. Crucially, motion remains in the loop: rollout feedback can revise the reference motion, reward, or both. We evaluate a generated embodiment across multiple MLLMs and behavior creation across four diverse robots against reward-refinement and one-shot motion baselines. Our computational metrics expose recurring mechanical failures in generated designs, while behavior experiments show that execution-grounded refinement improves task-level behavior and execution quality. Finally, we fabricate an agent-generated Gorilla and directly deploy learned behaviors on the physical robot.
作者：Xuebing Li, Yibo He, Sitong Liu, Ran Ji, Jiayuan Gu
来源
本页事实对应的公开页面，以原文为准。