LangMap introduces a human‑verified benchmark for language‑conditioned goal navigation (LGN) that spans four hierarchical semantic levels—scene, room, region, and instance—within real‑world indoor 3D scans. The dataset, built on HM3D, contains 18K tasks with concise and detailed descriptions for 414 object categories, and its contrastive annotation protocol ensures high‑quality, discriminative region and instance labels. Evaluation shows that LangMap’s descriptions improve text‑to‑view matching accuracy by 23 points over GOAT‑Bench and achieve a 92.5% unique‑and‑correct match rate in an independent human audit, while a proposed RGB‑only baseline, PlaNaVid, attains top‑tier success rates without depth or 3D scene representations.
By Bo Miao, Weijia Liu, Jun Luo, Lachlan Shinnick, Jian Liu, Thomas Hamilton-Smith, Yuhe Yang, Zijie Wu, Vanja Videnovic, Feras Dayoub, Anton van den Hengel
arXiv:2607. 06882v1 Announce Type: cross Abstract: Visual navigation policies built on large pretrained models have so far followed a common recipe: a dedicated visual encoder, a bespoke action head, and training on thousands of hours of cross-embodiment datasets.
By Peter Bohm, Saimunur Rahman, Abdelwahed Khamis, Sagun Man Singh Shrestha, Chris McCool, Peyman Moghadam
VoxelFix is a graph‑based post‑hoc semantic correction method that refines voxel labels in completed 3D voxel maps while preserving their geometry and occupancy. It learns to correct errors by exploiting local geometry and neighboring semantic information, using training pairs generated by corrupting annotated maps with class confusions from upstream perception pipelines. Experiments on OccuFly maps show consistent improvements of 4.23–5.00 percentage points in mIoU, especially for tree, roof, and wall classes, and the method generalizes to out‑of‑distribution aerial scenes.
By Sunesh Praveen Raja Sundarasami, Taehyoung Kim, Johannes Scherer, Toma\v{z} Coti\v{c}, Sivasubiramaniam Subbiah, Andreas Greiner, Paul Spannaus, Sebastian Houben
VEOcc++ is a voxel‑centric framework that unifies online incremental semantic occupancy mapping with offline global map refinement by maintaining a persistent sparse voxel feature map. During exploration the map expands and integrates local features with reliability‑guided updates, while a context‑aware decoder produces the current semantic occupancy map. After exploration, cached local features are consolidated and combined with the online representation for multi‑scale spatial refinement, achieving state‑of‑the‑art IoU and mIoU scores on EmbodiedOcc‑ScanNet and demonstrating zero‑shot transfer to unseen environments on a mobile robot.
By Ruoyu Wang, Jiahan Li, Yong Liu, Kexin Zhang
arXiv:2606. 00095v1 Announce Type: cross Abstract: Vision-Language Navigation (VLN) enables embodied agents to reach target locations in unseen environments by following language instructions.
By Kailing Li, Tianwen Qian, Lijin Yang, Yuqian Fu, Jingyu Gong, Xiaoling Wang, Liang He
arXiv:2603.26788v3 Announce Type: replace-cross
Abstract: Zero-shot object navigation requires agents to locate unseen targets in unfamiliar environments without prior maps or task-specific training....
By Feng Wu, Wei Zuo, Wenliang Yang, Jun Xiao, Yang Liu, Xinhua Zeng
AOV-GS is an active 3D Gaussian mapping system that uses frozen foundation models (SAM and CLIP) to guide exploration toward semantically informative regions. During coarse exploration, it re‑ranks geometrically promising views based on CLIP mask‑embedding novelty from SAM instance segmentation, biasing the robot’s trajectory. The system fits a lightweight scene‑specific language field offline to the collected CLIP embeddings, enabling open‑vocabulary text‑query segmentation on novel views and improving language‑field mIoU by 1.3–1.8 percentage points over geometry‑only planning on Replica and Matterport3D.
By Rodion Shkokov, Tatiana Zemskova, Dmitry Yudin
Visual navigation policies built on large pretrained models have so far followed a common recipe: a dedicated visual encoder, a bespoke action head, and training on thousands of hours of cross-embodiment datasets. We ask whether this recipe is necessary.
RoboAtlas is a contextual Active SLAM framework that balances geometric exploration with semantic reasoning through a scalable 3D semantic mapping system called OpenRoboVox. It uses frontier exploration, global semantic‑map reasoning, and egocentric VLM‑based reasoning guided by a contextual multi‑armed bandit to shift from exploration to semantically guided navigation as scene understanding improves. In simulation and on a Unitree Go2 robot, RoboAtlas achieved a 100% task success rate in environments over 1800 m² with ~30k semantic instances, and outperformed prior baselines on the GOAT‑Bench "Val Unseen" benchmark, reaching 90.6% SR with GPT‑4o and 88.8% SR with Qwen2.5‑VL‑7B.
By Alexander Schperberg, Shivam K. Panda, Abraham P. Vinod, Bhagawan Rokaha, M. K. Jawed, Stefano Di Cairano
arXiv:2608. 07079v1 Announce Type: cross Abstract: 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.
By Zehui Li, Zihao Sun, Jiawei Xu, Zheqi He, Xiaoqiang Zhang, Jing-Shu Zheng, Lu Liu, Dahui Gao, Xiuwan Chen
arXiv:2606.01621v3 Announce Type: replace
Abstract: Vision-language models (VLMs) have become a common foundation for vision-and-language navigation in continuous environments (VLN-CE). Yet most VLM-...
By Muyi Bao, Yuxin Cai, Hang Xu, Zongtai Li, Jinxi He, Jingfan Tang, Chen Lv, Ji Zhang, Yaqi Xie, Wenshan Wang
CatchUp is a training‑free framework that improves efficiency in large vision‑language models by depth‑aware re‑admission of visual tokens. It repeatedly evaluates query‑conditioned relevance, processes only selected tokens per decoder interval, and preserves deferred tokens for later re‑admission, using reference‑to‑current transition signals to approximate missed representation evolution. Experiments on three referring‑expression grounding datasets and six multimodal benchmarks show that CatchUp retains over 92% of full‑model performance with 88.9% fewer active tokens and reduces end‑to‑end latency by 8.0% at a 64‑token budget.
By Eunju Park, Uiwon Hwang