大模型
arxiv.org ·
ADM-Planner：面向移动操作器的 LLM 引导长时程规划与注意力增强动态记忆
该论文针对 LLM 长时程规划中固定场景描述易过时、全量保留观察又导致历史冗余冲突的问题，提出 ADM-Planner 框架：把持久工作区知识与对象级状态分离，由异步观察和动作结果更新状态，并用有界检索器仅暴露影响下一步决策的条目，当更新使剩余计划失效时触发 LLM 重规划。在 1500 个任务仿真回合的 14 容器噪声动态场景中，ADM 全任务成功率达 100%，静态记忆为 62%、未过滤动态记忆为 97%，上下文规模代理指标较后者降低 95.8%；6 回合 GPT-5 Mini 实测中动态记忆变体均完成任务，ADM 减少 14.4% 输入 token，平均规划调用从 7.0 降至 6.0；60 次 PyBullet 试验中 ADM 成功率 100%，静态记忆为 50%，并在室内外真机实验中纳入执行开始后才出现的目标。
AI推荐理由 arXiv 机器人方向新论文，提出 ADM-Planner：将持久工作区知识与对象级状态分离，用有界检索器只暴露影响下一步决策的条目，并在更新使剩余计划失效时触发 LLM 重规划。摘要给出具体量化结果：1500 个任务仿真回合中，14 容器噪声动态场景下 ADM 全任务成功率 100%，静态记忆 62%、未过滤动态记忆 97%，同时上下文规模代理指标较后者降低 95.8%；6 回合 GPT-5 Mini 实测中 ADM 减少 14.4% 输入 token、平均规划调用从 7.0 降至 6.0；另有 60 次 PyBullet 试验 ADM 成功率 100% 对静态记忆 50%，并完成室内外真机实验。局限在于均为作者自报结果，尚无第三方复现，且仿真与真机规模有限。
78
正文
Computer Science > Robotics
arXiv:2609.29212 (cs)
[Submitted on 24 Sep 2026]
Title:ADM-Planner: LLM-Guided Long-Horizon Planning for Mobile Manipulators with Attention-Enhanced Dynamic Memory
Authors:Jiaping Xiao, Pingyuan Ji, Mir Feroskhan
View a PDF of the paper titled ADM-Planner: LLM-Guided Long-Horizon Planning for Mobile Manipulators with Attention-Enhanced Dynamic Memory, by Jiaping Xiao and 2 other authors
View PDF
HTML (experimental)
Abstract:Large language models can decompose mobile-manipulation goals into long action sequences, but the resulting plans remain reliable only while their world context is current. A fixed scene description becomes stale when objects are discovered, moved, or completed while retaining every observation instead produces a growing history with redundant and conflicting state. To resolve this tension, we present an LLM-guided planning framework ADM-Planner with attention-enhanced dynamic memory (ADM). Persistent workspace knowledge is separated from object-centric state, asynchronous observations and action outcomes update that state, and a bounded retriever exposes only the entries that can affect the next decision. The LLM replans when an update invalidates the remaining plan. Across 1,500 task-simulator episodes, the proposed ADM achieved 100% full-task success in the 14-container noisy dynamic setting, compared with 62% for static memory and 97% for unfiltered dynamic memory, while reducing the context-size proxy by 95.8% relative to the latter. In a six-episode live GPT-5 Mini planner, both dynamic memory variants completed every mission, while ADM reduced provider-reported input tokens by 14.4% and mean planner calls from 7.0 to 6.0. A separate 60-trial PyBullet study retained 100% success for ADM, compared with 50% for static memory. Finally, the mobile manipulator with ADM-Planner completed various missions in indoor and outdoor physical experiments while incorporating targets revealed after execution began. The results show that selective state maintenance with ADM, rather than prompt history alone, is a practical basis for long-horizon planning in changing environments. Project page: this https URL
Comments:
Subjects:
Robotics (cs.RO)
Cite as:
arXiv:2609.29212 [cs.RO]
(or
arXiv:2609.29212v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.29212
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Jiaping Xiao [view email]
[v1]
Thu, 24 Sep 2026 08:19:12 UTC (9,353 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled ADM-Planner: LLM-Guided Long-Horizon Planning for Mobile Manipulators with Attention-Enhanced Dynamic Memory, by Jiaping Xiao and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.RO
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)