← Back to all news
arXiv Computer Vision By Xinhao Liu, Yunsheng Tian, Yuheng Qiu, Pieter Abbeel, Xi Chen, Guanya Shi, Chen Feng

StopWatch: Goal Grounding for Object-goal Navigation

Read the original on arXiv Computer Vision →

The paper introduces StopWatch, a method that explicitly grounds the goal in object-goal navigation tasks. By addressing the dominant failure of goal grounding in fine‑tuned vision‑language models, StopWatch achieves state‑of‑the‑art success rates on six benchmarks across three scene collections and corrects annotation defects in these datasets. The authors demonstrate that with accurate goal grounding, their policy nearly matches the expert demonstrations, highlighting perception as the remaining bottleneck.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Oct 2

LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation

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
llmsagentsroboticsmultimodalbenchmarks
More like this →
arXiv AI
Jul 14

ABot-N1: Toward a General Visual Language Navigation Foundation Model

arXiv:2607. 10383v1 Announce Type: cross Abstract: Visual Language Navigation foundation models aim to unify deep reasoning for grounded spatial decisions with broad versatility for diverse embodied tasks.

By Ruiyan Gong, Yingnan Guo, Junjun Hu, Jintao Kong, Xiaoxu Leng, Tianlun Li, Weize Li, Fei Liu, Zhicheng Liu, Jia Lu, Minghua Luo, Chenlin Ming, Yanfen Shen, Jiyue Tao, Zhengbo Wang, Mingyang Yin, Minqi Gu, Zihao Guan, Wei Guo, Guoqing Liu, Huachong Pang, Menglin Yang, Zeqian Ye, Xiaoxiao Geng, Zhining Gu, Honglin Han, Di Jing, Hongyu Pan, Mingchao Sun, Kuan Yang, Jianfang Zhang, Yanghong Chen, Ye He, Wei Mei, Jiahao Shi, Xiangpo Yang, Yanqing Zhu, Zedong Chu, Xiaolong Wu, Mu Xu
roboticsmultimodalbenchmarkssafety
More like this →
arXiv Computer Vision
Oct 12

GuidedNav: Shaping Vision-Language Navigation Representations through Pre-action Attention and Spatial Guidance

GuidedNav is a new framework for vision‑and‑language navigation that explicitly shapes the representations linking instructions to actions. It uses subtask and landmark guidance to focus pre‑action attention on the relevant instruction segment and visual regions, and spatial guidance to align internal representations with geometric features of the environment. The method achieves state‑of‑the‑art success rates on R2R‑CE and RxR‑CE val‑unseen, improving by 8.1% and 13.1% respectively, while also providing faster inference and introducing two new annotation‑enriched datasets, Guided‑R2R and Guided‑RxR.

By Jingyu Guo, Jiaxin Huang, Chengxing Lin, Xiaoyu Luo, Cheng Wen, Shanshan Ye, Tingjin Chu, Shaoli Huang, Mingming Gong
agentsmultimodalbenchmarks
More like this →