CORTEXA
← Browse
arxivcs.RO2026-07-16

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation

Yi Wu, Junjie An, Xiao Liu, Yiqun Zhou, Yuechen Wu, Xiaoqing Guan, Shuyang Yu, You Wang, Guang Li

In goal-directed embodied navigation, where an agent must locate a specified target in an unseen environment, 3D scene understanding and navigation reasoning must work in concert. Current approaches transmit 3D scene information to vision-language models (VLMs) through text, suggesting a representation gap in our tested configurations; a controlled ablation confirms that direct embedding-level transfer significantly outperforms the evaluated text serialization formats. We introduce SoftNav, which injects entity-level 3D continuous representations -- one token per detected object or frontier -- into a VLM's hidden space as soft tokens through a lightweight projector. With the 3D encoder and VLM frozen, only ~1,200 samples and ~17M trainable parameters are needed. On HM3D-OVON, SoftNav achieves 74.2%/68.3%/66.7% SR across three splits, surpassing all prior methods in both SR and SPL; the same navigation policy transfers zero-shot to GOAT-Bench (67.2% SR), SG3D (47.2% s-SR), and real-world robot deployment without retraining or architectural modification. Injecting 3D scene tokens directly into VLMs bridges the representation gap, enabling transferable navigation with minimal training.

View free PDFSource page

Related papers

arxivcs.ROcs.CV2026-07-22

EA-Nav: Learning Safe Visual Navigation Policies with Embodiment Awareness

Jialu Zhang, Yong Du, Xianda Guo, Shunwang Sun, Xinqi Liu, Yue Sun, et al.

Cross-embodiment navigation is a key challenge in embodied intelligence. Due to differences in embodiment, the same visual observation may imply different actions for different agents, making prediction ambiguous when relying solely on vision. Existing studies mainly rely on rein…

View free PDFSource page
arxivcs.ROcs.CV2026-07-22

NavVerse: Benchmarking Indoor-to-Outdoor Embodied Navigation in Continuous Robot Simulation

Junzhe Wu, Yue Hu, Zeyu Han, Po-Hsun Chang, Yinan Dong, Behrad Rabiei, et al.

Robots deployed in delivery, campus, and emergency-response settings often need to navigate from buildings to streets within a single continuous episode. Existing benchmarks usually evaluate indoor and outdoor navigation separately, and many abstract away robot execution, leaving…

View free PDFSource page
arxivcs.RO2026-07-22

SeededGrasp: Language-Guided Grasping in Complex Scenes with Multiple Embodiments

Yang Xu, Gurpreet Singh Mukker, Raymond Wang, Jasper Gerigk, Maria Attarian, Igor Gilitschenski

Practical robotic grasping in complex scenes requires both 3D spatial reasoning and alignment with task-specific requirements. Vision-language models (VLMs) offer a natural way to specify these requirements using language, but existing approaches either use a VLM to predict the g…

View free PDFSource page
arxivcs.RO2026-07-17

Vision-Language-Motion Maps: An Open-Vocabulary, Uncertainty-Aware, Queryable Motion Attribute for 3D Scene Maps

Dibyendu Ghosh, Ayushi Shakya

Open-vocabulary 3D maps let robots answer language queries about what and where, but they assume a static world and cannot answer queries about how scene elements behave. We introduce Vision-Language-Motion Maps (VLMM), an open-vocabulary, natural-language-queryable 3D map in whi…

View free PDFSource page
arxivcs.ROcs.AI2026-07-24

ACME: A Multi-Cultural, Multi-Embodiment Social-Navigation Dataset

Shashank Rao Marpally, Allan Wang, Atharva Ghotavadekar, Renato Alexandre Ribeiro, Nhat Le, Pilar Bachiller-Burgos, et al.

Understanding how robots and humans move in shared spaces is essential for designing effective social robot navigation policies and predicting human behavior. However, existing datasets often lack the diversity needed to capture differences in culture, geography, and human-robot…

View free PDFSource page
arxivcs.RO2026-07-20

Closing the Loop in Humanoid VLA: Persistent 3D Object Tokens for Verifiable Loco-Manipulation

Peng Ren, Haoyang Ge, Jiang Zhao, Cong Huang, Yukun Shi, Pei Chi, et al.

Vision-language-action policies are a promising foundation for general robot control, but long-horizon humanoid loco-manipulation requires the robot to treat task objects as persistent physical entities across movement, contact, occlusion, and recovery. We study this problem as o…

View free PDFSource page