MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning

• URL: http://arxiv.org/abs/2510.03142v1
• Date: Fri, 03 Oct 2025 16:15:09 GMT
• Title: MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning
• Authors: Tianyu Xu, Jiawei Chen, Jiazhao Zhang, Wenyao Zhang, Zekun Qi, Minghan Li, Zhizheng Zhang, He Wang,
• Abstract summary: We propose to leverage the intelligence of the Vision-Language-Action model to learn diverse navigation capabilities from synthetic expert data.<n>For large-scale navigation data, we collect expert data from three reinforcement learning (RL) experts trained with privileged depth information.<n>We iteratively train our VLA model using data collected online from RL experts, where the training ratio is dynamically balanced.
• Score: 19.308491194903556
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual navigation policy is widely regarded as a promising direction, as it mimics humans by using egocentric visual observations for navigation. However, optical information of visual observations is difficult to be explicitly modeled like LiDAR point clouds or depth maps, which subsequently requires intelligent models and large-scale data. To this end, we propose to leverage the intelligence of the Vision-Language-Action (VLA) model to learn diverse navigation capabilities from synthetic expert data in a teacher-student manner. Specifically, we implement the VLA model, MM-Nav, as a multi-view VLA (with 360 observations) based on pretrained large language models and visual foundation models. For large-scale navigation data, we collect expert data from three reinforcement learning (RL) experts trained with privileged depth information in three challenging tailor-made environments for different navigation capabilities: reaching, squeezing, and avoiding. We iteratively train our VLA model using data collected online from RL experts, where the training ratio is dynamically balanced based on performance on individual capabilities. Through extensive experiments in synthetic environments, we demonstrate that our model achieves strong generalization capability. Moreover, we find that our student VLA model outperforms the RL teachers, demonstrating the synergistic effect of integrating multiple capabilities. Extensive real-world experiments further confirm the effectiveness of our method.

Related papers

• DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning [21.055712962530716]
  Reinforcement Learning with Verifiable Rewards (RLVR) has been shown effective in enhancing the visual reflection and reasoning capabilities of Large Multimodal Models (LMMs)<n>We introduce textbfDeepVision-103K, a comprehensive dataset for RLVR training that covers diverse K12 mathematical topics, extensive knowledge points, and rich visual elements.<n>Models trained on DeepVision achieve strong performance on multimodal mathematical benchmarks, and generalize effectively to general multimodal reasoning tasks.
  arXiv  Detail & Related papers  (2026-02-18T01:51:21Z)
• DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving [52.63591791507895]
  We propose textbfDriveVLA-W0, a training paradigm that employs world modeling to predict future images.<n>This task generates a dense, self-supervised signal that compels the model to learn the underlying dynamics of the driving environment.<n>Experiments on the NAVSIM v1/v2 benchmark and a 680x larger in-house dataset demonstrate that DriveVLA-W0 significantly outperforms BEV and VLA baselines.
  arXiv  Detail & Related papers  (2025-10-14T17:59:47Z)
• From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning [59.88543114325153]
  We introduce the Seeing-to-Experiencing framework to scale the capability of navigation foundation models with reinforcement learning.<n>S2E combines the strengths of pre-training on videos and post-training through RL.<n>We establish a comprehensive end-to-end evaluation benchmark, NavBench-GS, built on photorealistic 3DGS reconstructions of real-world scenes.
  arXiv  Detail & Related papers  (2025-07-29T17:26:10Z)
• Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends [11.678954304546988]
  Vision-language-action (VLA) models extend vision-language models (VLM)<n>This paper reviews post-training strategies for VLA models through the lens of human motor learning.
  arXiv  Detail & Related papers  (2025-06-26T03:06:57Z)
• One RL to See Them All: Visual Triple Unified Reinforcement Learning [92.90120580989839]
  We propose V-Triune, a Visual Triple Unified Reinforcement Learning system that enables visual reasoning and perception tasks within a single training pipeline.<n>V-Triune comprises triple complementary components: Sample-Level Datashelf (to unify diverse task inputs), Verifier-Level Reward (to deliver custom rewards via specialized verifiers).<n>We introduce a novel Dynamic IoU reward, which provides adaptive, progressive, and definite feedback for perception tasks handled by V-Triune.
  arXiv  Detail & Related papers  (2025-05-23T17:41:14Z)
• LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving [88.85002707211777]
  LargeAD is a versatile and scalable framework designed for large-scale 3D pretraining across diverse real-world driving datasets.<n>Our framework leverages VFMs to extract semantically rich superpixels from 2D images, which are aligned with LiDAR point clouds.<n>This alignment facilitates cross-modal representation learning, enhancing the semantic consistency between 2D and 3D data.
  arXiv  Detail & Related papers  (2025-01-07T18:59:59Z)
• Towards Learning a Generalist Model for Embodied Navigation [24.816490551945435]
  We propose the first generalist model for embodied navigation, NaviLLM. It adapts LLMs to embodied navigation by introducing schema-based instruction. We conduct extensive experiments to evaluate the performance and generalizability of our model.
  arXiv  Detail & Related papers  (2023-12-04T16:32:51Z)
• StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data [129.92449761766025]
  We propose a novel data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning. This approach harnesses the power of generative models, marrying the abilities of ChatGPT and text-to-image generative models. Our research includes comprehensive experiments conducted on various datasets.
  arXiv  Detail & Related papers  (2023-08-20T12:43:52Z)
• Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation [97.17517060585875]
  We present a unified approach to visual navigation using a novel modular transfer learning model. Our model can effectively leverage its experience from one source task and apply it to multiple target tasks. Our approach learns faster, generalizes better, and outperforms SoTA models by a significant margin.
  arXiv  Detail & Related papers  (2022-02-05T00:07:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.