# RAVEN: Long-Horizon Reasoning & Navigation with a Visuo-Spatio-Temporal Memory

arXiv: https://arxiv.org/abs/2606.25206 · HTML: https://mlsanity.com/paper/2606.25206/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 49 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots](https://mlsanity.com/paper/2310.13724/) (2023)
- [PaliGemma 2: A Family of Versatile VLMs for Transfer](https://mlsanity.com/paper/2412.03555/) (2024)
- [VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation](https://mlsanity.com/paper/2312.03275/) (2023)
- [CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory](https://mlsanity.com/paper/2210.05663/) (2022)
- [GOAT: GO to Any Thing](https://mlsanity.com/paper/2311.06430/) (2023)
- [3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning](https://mlsanity.com/paper/2411.17735/) (2024)
- [ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation](https://mlsanity.com/paper/2409.13682/) (2024)
- [MemER: Scaling Up Memory for Robot Control via Experience Retrieval](https://mlsanity.com/paper/2510.20328/) (2025)
- [CLIP-Nav: Using CLIP for Zero-Shot Vision-and-Language Navigation](https://mlsanity.com/paper/2211.16649/) (2022)
- [Temporal Memory Attention for Video Semantic Segmentation](https://mlsanity.com/paper/2102.08643/) (2021)
- [Towards Robust Robot 3D Perception in Urban Environments: The UT Campus Object Dataset](https://mlsanity.com/paper/2309.13549/) (2023)
- [3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model](https://mlsanity.com/paper/2505.22657/) (2025)
- [Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying](https://mlsanity.com/paper/2506.02020/) (2025)
- [NavFormer: A Transformer Architecture for Robot Target-Driven Navigation in Unknown and Dynamic Environments](https://mlsanity.com/paper/2402.06838/) (2024)
- [Recurrent-OctoMap: Learning State-based Map Refinement for Long-Term Semantic Mapping with 3D-Lidar Data](https://mlsanity.com/paper/1807.00925/) (2018)
- [Probabilistic Semantic Mapping for Urban Autonomous Driving Applications](https://mlsanity.com/paper/2006.04894/) (2020)
- [Place Categorization and Semantic Mapping on a Mobile Robot](https://mlsanity.com/paper/1507.02428/) (2015)
- [FindingDory: A Benchmark to Evaluate Memory in Embodied Agents](https://mlsanity.com/paper/2506.15635/) (2025)

## Built on by (most cited first, 2 of 2)

- [Visual Navigation Transformer with Pose Attention](https://mlsanity.com/paper/2609.21212/) (2026)
- [Retrospective Open-Vocabulary Memory for Long-Term Object Search](https://mlsanity.com/paper/2610.00330/) (2026)

## Abstract (arXiv)

Long-term robot deployment requires a compact and scalable memory that preserves fine-grained visual semantics, grounds observations in space and time, and enables efficient storage and retrieval. In this paper, we propose RAVEN, an agentic memory system for long-horizon robotic question answering and navigation. RAVEN stores visual embeddings with pose and time in a vector database, and grounds retrieval in a spatial map to answer queries and navigate to goals. By operating directly on visual embeddings, RAVEN avoids lossy image-to-text captioning and enables accurate semantic, spatial, and temporal retrieval at scale. Across several simulated and real-world video question-answering benchmarks, RAVEN consistently surpasses caption-based memory systems and matches frontier VLMs on long-horizon tasks at 10× lower retrieval cost. Finally, we instantiate RAVEN on a Unitree Go1 robot for the task of long-horizon navigation for natural language goal-reaching, and show successful deployment over several large indoor environments.