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

• URL: http://arxiv.org/abs/2606.25206v1
• Date: Tue, 23 Jun 2026 21:56:41 GMT
• Title: RAVEN: Long-Horizon Reasoning & Navigation with a Visuo-Spatio-Temporal Memory
• Abstract summary: RAVEN is an agentic memory system for long-horizon robotic question answering and navigation.<n>RAVEN stores visual embeddings with pose and time in a vector database, and grounds retrieval in a spatial map to answer queries.<n>We instantiate RAVEN on a Unitree Go1 robot for the task of long-horizon navigation for natural language goal-reaching.
• Score: 10.92726806758712
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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$\times$ 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.

Related papers

• Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents [24.05637675858576]
  Embodied agents performing long-horizon tasks require a memory representation in which the state transitions of dynamic objects remain queryable in natural language.<n>Our key contribution is textbfLinguistic Trajectory Linguistic Trajectory (LTE)<n>LTE compresses dynamic object motion histories via a hybrid representation combining natural language descriptions, sparse spatial anchors, and visual anchors.<n>LTE achieves trajectory compression by factors of $8.7times to $26.1times with sub-second query latency on $24,h video.
  arXiv  Detail & Related papers  (2026-09-04T07:00:48Z)
• Remember Smarter: Visual History Compressor and Hyperbolic Experience Space for Robotic Memory [54.400138177707504]
  Remember Smarter (RS) is a plug-and-play module with complementary visual-history and hyperbolic experience-memory branches.<n>When adapted to pi0, RS increases total success on LIBERO-Plus from 53.6% to 70.6% and achieves substantial performance gains in real-robot experiments.
  arXiv  Detail & Related papers  (2026-08-15T15:13:33Z)
• LongSpace: Exploring Long-Horizon Spatial Memory from Perception to Recall in Video [20.1389583507481]
  Long-horizon tasks such as autonomous driving and robotic navigation require more than recognizing the current view.<n>We introduce LongSpace, a room-tour video benchmark for long-horizon spatial memory.<n>LongSpace models long videos as sequential chunks, incorporates 3D structural cues into early decoder layers, and constructs layer-aware memory for question-guided retrieval.
  arXiv  Detail & Related papers  (2026-06-04T04:00:12Z)
• EvoMemNav: Efficient Self-Evolving Fine-Grained Memory for Zero-Shot Embodied Navigation [81.54723508469617]
  EvoMemNav is an efficient, self-evolving, fine-grained memory framework for zero-shot embodied navigation.<n>VSMGraph organizes views with semantic cues and topological relations into a room-view-object hierarchy.<n>Experiments on GOAT-Bench and HM3D across object, text-description, and image-goal modalities show consistent gains in SR/SPL.
  arXiv  Detail & Related papers  (2026-06-02T11:27:44Z)
• RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies [54.23445842621374]
  Memory is critical for long-horizon and history-dependent robotic manipulation.<n>Recent vision-language-action (VLA) models have begun to incorporate memory mechanisms.<n>We introduce RoboMME: a large-scale standardized benchmark for evaluating and advancing VLA models.
  arXiv  Detail & Related papers  (2026-03-04T21:59:32Z)
• STaR: Scalable Task-Conditioned Retrieval for Long-Horizon Multimodal Robot Memory [16.76678779219906]
  Mobile robots are often deployed over long durations in diverse open, dynamic scenes.<n>A core challenge is to build a scalable long-horizon memory that supports an agentic workflow for planning, retrieval, and reasoning.<n>We present STaR, a task-agnostic, multimodal long-term memory that generalizes to unseen queries.
  arXiv  Detail & Related papers  (2026-02-09T22:38:53Z)
• ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination [36.489349671649045]
  Vision-Language Models (VLMs) can achieve mapless visual navigation using only onboard RGB/RGB-D streams, unlocking their potential for spatial perception and planning.<n>We achieve this through an imagination-powered navigation framework, ImagineNav++, which imagines future observation images from candidate robot views.<n>To maintain spatial consistency, we develop a selective foveation memory mechanism, which hierarchically integrates observations via a sparse-to-dense framework.
  arXiv  Detail & Related papers  (2025-12-19T10:40:16Z)
• 3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model [83.70640091897947]
  Humans excel at performing complex tasks by leveraging long-term memory across temporal and spatial experiences.<n>Current Large Language Models (LLMs) struggle to effectively plan and act in dynamic, multi-room 3D environments.<n>We propose 3DLLM-Mem, a novel dynamic memory management and fusion model for embodied spatial-temporal reasoning and actions.
  arXiv  Detail & Related papers  (2025-05-28T17:59:13Z)
• 3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning [65.40458559619303]
  We propose 3D-Mem, a novel 3D scene memory framework for embodied agents.<n>3D-Mem employs informative multi-view images, termed Memory Snapshots, to represent the scene.<n>It further integrates frontier-based exploration by introducing Frontier Snapshots-glimpses of unexplored areas-enabling agents to make informed decisions.
  arXiv  Detail & Related papers  (2024-11-23T09:57:43Z)
• ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation [9.468486766002625]
  People interacting with robots may want to ask questions like where something happened when it occurred, or how long ago. We introduce ReMEmbR, a system designed for long-horizon video question answering for robot navigation. Our experiments demonstrate that ReMEmbR outperforms LLM and VLM baselines, allowing ReMEmbR to achieve effective long-horizon reasoning with low latency.
  arXiv  Detail & Related papers  (2024-09-20T17:50:07Z)
• Structured Scene Memory for Vision-Language Navigation [155.63025602722712]
  We propose a crucial architecture for vision-language navigation (VLN) It is compartmentalized enough to accurately memorize the percepts during navigation. It also serves as a structured scene representation, which captures and disentangles visual and geometric cues in the environment.
  arXiv  Detail & Related papers  (2021-03-05T03:41:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.