CORTEXA
← Browse
arxivcs.RO2026-06-29

RoamFlow: Reinforcement-Aligned One-Step Action MeanFlow Policy for Image-Goal Navigation

Zixuan Zhang, Yuqi Chen, Junjie Gao, Siyuan Song, Yongzhou Pan, Beichen Wang, Mir Feroskhan

Image-goal navigation is a key challenge in embodied robotics, where an agent must reach a target specified solely by a goal image. While existing reinforcement learning approaches map perceptual observations directly to actions, they struggle to model long-horizon dependencies, often leading to suboptimal trajectories. To address this limitation, we propose RoamFlow, a generative navigation framework that leverages MeanFlow to predict the average velocity field for trajectory synthesis, enabling efficient few-step generation and reducing inference latency. We further adopt a two-stage training strategy that combines expert imitation for stable initialization with reinforcement learning for task-specific policy refinement. Extensive experiments in both Habitat simulation and real-world robotic platforms demonstrate that RoamFlow achieves efficient inference while maintaining strong navigation performance under real-time constraints.

View free PDFSource page

Related papers

arxivcs.ROcs.AI2026-07-04

High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matching

Yuran Chen, Xinye Cai, Zhonglin Gong, Yang Huang

Generative models such as diffusion and flow matching have advanced robotic visuomotor policies by modeling multimodal action distributions, but their multi-step sampling or ODE solving introduces inference latency. Existing one-step acceleration methods often compress the whole…

View free PDFSource page
arxivcs.RO2026-07-16

NavCMPO: Critic-Guided MeanFlow Policy Optimization for Adaptive Navigation

Junjie An, Yi Wu, Xiao Liu, Yiqun Zhou, Yuechen Wu, Xiaoqing Guan, et al.

End-to-end diffusion-based policies have demonstrated strong performance in mapless visual navigation, but their iterative denoising process introduces substantial inference latency, while behavior cloning limits performance to the quality of expert demonstrations. We present Nav…

View free PDFSource page
arxivcs.RO2026-07-21

Beyond Transformers: Linear Attention Policy for Open-Vocabulary Object Goal Navigation

Jiahong Zhang, Yifan Lin, Yandong Zhang, Sijun Shen, Kexin Wang, Yuqi Pan, et al.

Open-Vocabulary Object Goal Navigation (OVON) requires agents to operate under partial observability, making effective internal state updates critical for navigation performance. This update is implemented by the policy network, where recent approaches adopt Transformer-based bac…

View free PDFSource page
arxivcs.RO2026-07-06

SEAM: Smooth Execution of Action-Chunked Motion for Vision-Language-Action Policies

Dijia Zhan, Xuemiao Xu, Jinyi Li, Jie Tang

Vision-Language-Action (VLA) policies that execute fixed-length action chunks can exhibit multimodal bifurcation: a cross-chunk inconsistency in which adjacent chunks generated from independent Gaussian latents can converge to incompatible trajectory modes, producing abrupt disco…

View free PDFSource page
arxivcs.CVcs.RO2026-07-06

Green for Go, Red for No: Visual Grounding via Semantic Segmentation for VLA Navigation Policies

Adrian Szvoren, Dimitrios Kanoulas, Nilufer Tuptuk

Vision-language-action (VLA) models enable robot navigation from natural language and visual goals, but remain susceptible to perceptual distractions and ambiguous scene interpretations. This paper presents the first empirical evaluation of visual grounding for VLA navigation pol…

View free PDFSource page
arxivcs.CVcs.RO2026-07-16

SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment

Saad Ejaz, Miguel Fernandez-Cortizas, Javier Civera, Holger Voos, Jose Luis Sanchez-Lopez

CAD-to-image alignment aims to estimate an object's 9D pose (rotation, translation, and anisotropic scale) from a single RGB image, enabling applications in robotics and augmented reality. Recent zero-shot methods use visual foundation models to match image regions to CAD models,…

View free PDFSource page