# LifelongCrossNav: Persistent 3D Semantic Memory for Cross-Floor Multi-Object Navigation

arXiv: https://arxiv.org/abs/2608.07079 · HTML: https://mlsanity.com/paper/2608.07079/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [Faster Segment Anything: Towards Lightweight SAM for Mobile Applications](https://mlsanity.com/paper/2306.14289/) (2023)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation](https://mlsanity.com/paper/2312.03275/) (2023)
- [ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings](https://mlsanity.com/paper/2206.12403/) (2022)
- [InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment](https://mlsanity.com/paper/2406.04882/) (2024)
- [SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation](https://mlsanity.com/paper/2410.08189/) (2024)
- [MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation](https://mlsanity.com/paper/2012.03912/) (2020)
- [GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation](https://mlsanity.com/paper/2404.06609/) (2024)
- [OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models](https://mlsanity.com/paper/2402.10670/) (2024)
- [ApexNav: An Adaptive Exploration Strategy for Zero-Shot Object Navigation with Target-centric Semantic Fusion](https://mlsanity.com/paper/2504.14478/) (2025)
- [BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation](https://mlsanity.com/paper/2506.06487/) (2025)
- [One Map to Find Them All: Real-time Open-Vocabulary Mapping for Zero-shot Multi-Object Navigation](https://mlsanity.com/paper/2409.11764/) (2024)
- [Multi-Floor Zero-Shot Object Navigation Policy](https://mlsanity.com/paper/2409.10906/) (2024)
- [Stairway to Success: An Online Floor-Aware Zero-Shot Object-Goal Navigation Framework via LLM-Driven Coarse-to-Fine Exploration](https://mlsanity.com/paper/2505.23019/) (2025)
- [TravExplorer: Cross-Floor Embodied Exploration via Traversability-Aware 3-D Planning](https://mlsanity.com/paper/2605.19958/) (2026)

## Abstract (arXiv)

Object-goal navigation has made substantial progress in semantic perception and exploration, yet persistent memory for multi-object navigation and cross-floor navigation are still commonly addressed separately. We present LifelongCrossNav, a framework for sequential multi-object ObjectNav in unknown multi-floor indoor environments. Within each episode, the agent receives an ordered sequence of object-goal queries while continuously maintaining a shared sparse 3D semantic voxel memory. This memory incrementally accumulates geometric structure, traversability states, and vision-language features, allowing subsequent object-goal queries to retrieve previously acquired scene information without rebuilding the map. To support persistent search across floors, LifelongCrossNav combines support-aware 3D traversability mapping, stair-specific perception, and direction-aware stair traversal. A unified navigation policy coordinates same-floor frontier exploration, live and historical point-of-interest retrieval, stair navigation, and target-object search and approach. We further introduce HM3D-MFMON, a benchmark for sequential Multi-Floor Multi-Object Navigation built on HM3D scenes, including a dedicated subset in which completing the full sequence of object-goal subtasks requires at least one floor transition. Experimental results show that LifelongCrossNav consistently outperforms a representative planar persistent semantic-map baseline on HM3D-MFMON, demonstrating that persistent 3D semantic memory and cross-floor traversability modeling effectively support sequential multi-object navigation in multi-floor environments.