ReMEmbR：ロボットナビゲーションのための長期時空間記憶の構築と推論
ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation
ロボットが長期間のナビゲーション履歴を記憶し、時空間的な質問に答えるための検索拡張記憶システムReMEmbRを提案。NaVQAデータセットを構築し、低遅延で効果的な長期推論を実現した。
著者: Abrar Anwar, John Welsh, Joydeep Biswas, Soha Pouya, Yan Chang
分類: cs.RO, cs.AI, cs.CL
原文アブストラクト
Navigating and understanding complex environments over extended periods of time is a significant challenge for robots. People interacting with the robot may want to ask questions like where something happened, when it occurred, or how long ago it took place, which would require the robot to reason over a long history of their deployment. To address this problem, we introduce a Retrieval-augmented Memory for Embodied Robots, or ReMEmbR, a system designed for long-horizon video question answering for robot navigation. To evaluate ReMEmbR, we introduce the NaVQA dataset where we annotate spatial, temporal, and descriptive questions to long-horizon robot navigation videos. ReMEmbR employs a structured approach involving a memory building and a querying phase, leveraging temporal information, spatial information, and images to efficiently handle continuously growing robot histories. Our experiments demonstrate that ReMEmbR outperforms LLM and VLM baselines, allowing ReMEmbR to achieve effective long-horizon reasoning with low latency. Additionally, we deploy ReMEmbR on a robot and show that our approach can handle diverse queries. The dataset, code, videos, and other material can be found at the following link: https://nvidia-ai-iot.github.io/remembr
