让机器人通过反思经验持续进化，提升复杂任务成功率。
Evolvable Embodied Agent for Robotic Manipulation via Long Short-Term Reflection and Optimization
- 用大视觉语言模型理解环境并规划策略
- 动态优化提示词，实现长期经验积累
- 适合需要自适应能力的机器人研究者
实现通用机器人需赋予其根据环境与反馈自主适应和演化的能力。传统方法受限于训练成本高、跨任务泛化难及可解释性差。提示学习为无需大量训练的自我演化机器人带来新可能，但如何从成功与失败中提取有效洞见仍是挑战。为此，我们提出可演化的具身智能体（EEAgent）框架，利用大型视觉语言模型（VLMs）提升环境理解与策略规划能力。为增强对过往经验的反思，我们设计了长短期反思优化（LSTRO）机制，基于历史经验与新学知识动态优化提示词，实现持续自我进化，从而显著提升整体任务成功率。在六个VIMA-Bench任务上的评估表明，该方法达到新基准，尤其在复杂场景下显著优于基线模型。
原文摘要 · Abstract (English)
Achieving general-purpose robotics requires empowering robots to adapt and evolve based on their environment and feedback. Traditional methods face limitations such as extensive training requirements, difficulties in cross-task generalization, and lack of interpretability. Prompt learning offers new opportunities for self-evolving robots without extensive training, but simply reflecting on past experiences. However, extracting meaningful insights from task successes and failures remains a challenge. To this end, we propose the evolvable embodied agent (EEAgent) framework, which leverages large vision-language models (VLMs) for better environmental interpretation and policy planning. To enhance reflection on past experiences, we propose a long short-term reflective optimization (LSTRO) mechanism that dynamically refines prompts based on both past experiences and newly learned lessons, facilitating continuous self-evolution, thereby enhancing overall task success rates. Evaluations on six VIMA-Bench tasks reveal that our approach sets a new state-of-the-art, notably outperforming baselines in complex scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。