Skip to content

CPNav: Calibrated Vision-Language Navigation for Object-Goal Search in Unseen Environments

Nov 2026 · 0 citations · 49 references
Computer Science

TL;DR

CPNav is introduced, a navigation framework that combines collision-aware planning with statistically calibrated VLM action scoring for map-free object-goal navigation and provides finite-sample guarantees at a user-specified risk level.

Abstract

Directing a robot to locate a target object in unseen environments remains a central challenge in embodied AI. Vision-Language Model (VLM)-based methods provide rich semantic reasoning but often produce uncalibrated and overconfident action decisions. We introduce CPNav, a navigation framework that combines collision-aware planning with statistically calibrated VLM action scoring for map-free object-goal navigation. From RGB-D input, CPNav constructs a navigability map, generates collision-free motion primitives, and queries two VLMs for goal detection and action scoring. The resulting scores are calibrated offline via conformal prediction (CP) using oracle actions obtained through a tree-structured exploration procedure with backtracking, providing finite-sample guarantees at a user-specified risk level. The CP layer is model-agnostic and can wrap any VLM policy. Online, calibrated VLM scores guide action selection, while a tree-structured exploration history records alternative actions and allows backtracking. We evaluate CPNav in both simulation and real-world hardware settings. In AI Habitat simulation, compared with the uncalibrated baseline method, CPNav achieves relative SR and SPL improvements of 6.2% and 11.4% on HM3D v0.2, and 12.4% and 8.8% on MP3D, respectively. In real-world deployment on a modified Hiwonder MentorPi robot, the corresponding improvements in SR and SPL are 24.9% and 15.2%, respectively. Code is available at https://github.com/practice-lab-ucla/CPnav.

View source

Similar papers

Sep 2026

NaViRrator: Robot Navigation from Human-Readable Maps through a Learned Visual Route

NaViRRator, a framework that translates user-specified start and goal locations on such maps into navigation instructions for a pretrained vision-and-language navigation (VLN) policy, is presented, supporting route-grounded language as a modular interface between human-readable maps and pretrained navigation policies.

Ayun Lee, Jiseon Kim, Giseop Kim · 1 citation
Conference Open access Oct 2026

When Maps Are Incomplete: Evaluating Vision-Language-Guided Navigation Against Nav2

Real-world mobile robots may not always have access to complete or accurate prior maps. In such cases, vision-language models (VLMs), which combine visual perception with semantic reasoning, offer a promising way to interpret environmental changes and revise navigation decisions. This study develops and evaluates two V...

Brian Fitzpatrick, Noorbakhsh Amiri Golilarz, Soroush Korivand · 0 citations
Preprint Nov 2026

SCOUT: Planning under Occlusion via Object-Centric World Model Rollouts

Robots manipulating in cluttered spaces must often plan from partial views where foreground objects occlude the target, surrounding geometry, and usable free space. Reactive policies often miss these hidden constraints, while exhaustive search becomes computationally prohibitive in dense clutter. We present SCOUT, an o...

Amir Hossain Raj, Xue-Su Xiao · 0 citations
Preprint Oct 2026

$S^3$-Nav: Structured Spatial-Semantic Decision Making for Language-Guided Robot Navigation

Evaluations across multiple environments and object- and relation-goal tasks show improved closed-loop navigation reliability and reduced language-model token consumption with capacity-controlled evidence exposure under the evaluated inference configuration.

Chaemin Lee, H. Cho · 0 citations
Preprint Oct 2026

SuperNav: An Agentic Navigation System for Any Task in Any Scene

General-purpose service robots need navigation systems that can handle diverse human requests in unfamiliar environments, combining task generality with scene generality. Some existing methods fine-tune multimodal large language models (MLLMs) to predict navigation actions, making their behavior dependent on the covera...

Jin-Kai Zhang, Jing-Yi Xu, Yuan-Hong Yu et al. · 3 citations
Preprint Oct 2026

End-to-End Vision-Language-Action Policies for Autonomous Lunar Rover Docking

A vision-language-action policy for autonomous lunar rover docking and its performance relative to a modular navigation pipeline is designed and a scalable training framework is developed that generates safety-aware expert demonstrations in a high-fidelity lunar simulation environment.

Si-Tan Huang, G. Gao · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.