Enter the Mind Palace: Reasoning and Planning for Long-term Active Embodied Question Answering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908557787529216 |
|---|---|
| author | Ginting, Muhammad Fadhil Kim, Dong-Ki Meng, Xiangyun Reinke, Andrzej Krishna, Bandi Jai Kayhani, Navid Peltzer, Oriana Fan, David D. Shaban, Amirreza Kim, Sung-Kyun Kochenderfer, Mykel J. Agha-mohammadi, Ali-akbar Omidshafiei, Shayegan |
| author_facet | Ginting, Muhammad Fadhil Kim, Dong-Ki Meng, Xiangyun Reinke, Andrzej Krishna, Bandi Jai Kayhani, Navid Peltzer, Oriana Fan, David D. Shaban, Amirreza Kim, Sung-Kyun Kochenderfer, Mykel J. Agha-mohammadi, Ali-akbar Omidshafiei, Shayegan |
| contents | As robots become increasingly capable of operating over extended periods -- spanning days, weeks, and even months -- they are expected to accumulate knowledge of their environments and leverage this experience to assist humans more effectively. This paper studies the problem of Long-term Active Embodied Question Answering (LA-EQA), a new task in which a robot must both recall past experiences and actively explore its environment to answer complex, temporally-grounded questions. Unlike traditional EQA settings, which typically focus either on understanding the present environment alone or on recalling a single past observation, LA-EQA challenges an agent to reason over past, present, and possible future states, deciding when to explore, when to consult its memory, and when to stop gathering observations and provide a final answer. Standard EQA approaches based on large models struggle in this setting due to limited context windows, absence of persistent memory, and an inability to combine memory recall with active exploration. To address this, we propose a structured memory system for robots, inspired by the mind palace method from cognitive science. Our method encodes episodic experiences as scene-graph-based world instances, forming a reasoning and planning algorithm that enables targeted memory retrieval and guided navigation. To balance the exploration-recall trade-off, we introduce value-of-information-based stopping criteria that determines when the agent has gathered sufficient information. We evaluate our method on real-world experiments and introduce a new benchmark that spans popular simulation environments and actual industrial sites. Our approach significantly outperforms state-of-the-art baselines, yielding substantial gains in both answer accuracy and exploration efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_12846 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enter the Mind Palace: Reasoning and Planning for Long-term Active Embodied Question Answering Ginting, Muhammad Fadhil Kim, Dong-Ki Meng, Xiangyun Reinke, Andrzej Krishna, Bandi Jai Kayhani, Navid Peltzer, Oriana Fan, David D. Shaban, Amirreza Kim, Sung-Kyun Kochenderfer, Mykel J. Agha-mohammadi, Ali-akbar Omidshafiei, Shayegan Robotics Artificial Intelligence As robots become increasingly capable of operating over extended periods -- spanning days, weeks, and even months -- they are expected to accumulate knowledge of their environments and leverage this experience to assist humans more effectively. This paper studies the problem of Long-term Active Embodied Question Answering (LA-EQA), a new task in which a robot must both recall past experiences and actively explore its environment to answer complex, temporally-grounded questions. Unlike traditional EQA settings, which typically focus either on understanding the present environment alone or on recalling a single past observation, LA-EQA challenges an agent to reason over past, present, and possible future states, deciding when to explore, when to consult its memory, and when to stop gathering observations and provide a final answer. Standard EQA approaches based on large models struggle in this setting due to limited context windows, absence of persistent memory, and an inability to combine memory recall with active exploration. To address this, we propose a structured memory system for robots, inspired by the mind palace method from cognitive science. Our method encodes episodic experiences as scene-graph-based world instances, forming a reasoning and planning algorithm that enables targeted memory retrieval and guided navigation. To balance the exploration-recall trade-off, we introduce value-of-information-based stopping criteria that determines when the agent has gathered sufficient information. We evaluate our method on real-world experiments and introduce a new benchmark that spans popular simulation environments and actual industrial sites. Our approach significantly outperforms state-of-the-art baselines, yielding substantial gains in both answer accuracy and exploration efficiency. |
| title | Enter the Mind Palace: Reasoning and Planning for Long-term Active Embodied Question Answering |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2507.12846 |