From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning

• URL: http://arxiv.org/abs/2507.22028v1
• Date: Tue, 29 Jul 2025 17:26:10 GMT
• Title: From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning
• Authors: Honglin He, Yukai Ma, Wayne Wu, Bolei Zhou,
• Abstract summary: 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.
• Score: 59.88543114325153
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Navigation foundation models trained on massive webscale data enable agents to generalize across diverse environments and embodiments. However, these models trained solely on offline data, often lack the capacity to reason about the consequences of their actions or adapt through counterfactual understanding. They thus face significant limitations in the real-world urban navigation where interactive and safe behaviors, such as avoiding obstacles and moving pedestrians, are critical. To tackle these challenges, we introduce the Seeing-to-Experiencing framework to scale the capability of navigation foundation models with reinforcement learning. S2E combines the strengths of pre-training on videos and post-training through RL. It maintains the generalizability acquired from large-scale real-world videos while enhancing its interactivity through RL in simulation environments. Specifically, we introduce two innovations: an Anchor-Guided Distribution Matching strategy, which stabilizes learning and models diverse motion patterns through anchor-based supervision; and a Residual-Attention Module, which obtains reactive behaviors from simulation environments without erasing the model's pretrained knowledge. Moreover, we establish a comprehensive end-to-end evaluation benchmark, NavBench-GS, built on photorealistic 3DGS reconstructions of real-world scenes that incorporate physical interactions. It can systematically assess the generalizability and safety of navigation foundation models. Extensive experiments show that S2E mitigates the diminishing returns often seen when scaling with offline data alone. We perform a thorough analysis of the benefits of Reinforcement Learning compared to Supervised Fine-Tuning in the context of post-training for robot learning. Our findings emphasize the crucial role of integrating interactive online experiences to effectively scale foundation models in Robotics.

Related papers

• Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach [55.76249793590689]
  Video-Enhanced Offline RL (VeoRL) is a model-based method that constructs an interactive world model from diverse, unlabeled video data readily available online.<n>VeoRL achieves substantial performance gains across visual control tasks in robotic manipulation, autonomous driving, and open-world video games.
  arXiv  Detail & Related papers  (2025-05-10T00:54:12Z)
• Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning [93.58897637077001]
  This paper tries to learn and understand underlying semantic variations from distracting videos via offline-to-online latent distillation and flexible disentanglement constraints.<n>We pretrain the action-free video prediction model offline with disentanglement regularization to extract semantic knowledge from distracting videos.<n>For finetuning in the online environment, we exploit the knowledge from the pretrained model and introduce a disentanglement constraint to the world model.
  arXiv  Detail & Related papers  (2025-03-11T13:50:22Z)
• Sonar-based Deep Learning in Underwater Robotics: Overview, Robustness and Challenges [0.46873264197900916]
  The predominant use of sonar in underwater environments, characterized by limited training data and inherent noise, poses challenges to model robustness.<n>This paper studies sonar-based perception task models, such as classification, object detection, segmentation, and SLAM.<n>It systematizes sonar-based state-of-the-art datasets, simulators, and robustness methods such as neural network verification, out-of-distribution, and adversarial attacks.
  arXiv  Detail & Related papers  (2024-12-16T15:03:08Z)
• PLANRL: A Motion Planning and Imitation Learning Framework to Bootstrap Reinforcement Learning [13.564676246832544]
  We introduce PLANRL, a framework that chooses when the robot should use classical motion planning and when it should learn a policy. PLANRL switches between two modes of operation: reaching a waypoint using classical techniques when away from the objects and fine-grained manipulation control when about to interact with objects. We evaluate our approach across multiple challenging simulation environments and real-world tasks, demonstrating superior performance in terms of adaptability, efficiency, and generalization compared to existing methods.
  arXiv  Detail & Related papers  (2024-08-07T19:30:08Z)
• ReCoRe: Regularized Contrastive Representation Learning of World Model [21.29132219042405]
  We present a world model that learns invariant features using contrastive unsupervised learning and an intervention-invariant regularizer. Our method outperforms current state-of-the-art model-based and model-free RL methods and significantly improves on out-of-distribution point navigation tasks evaluated on the iGibson benchmark.
  arXiv  Detail & Related papers  (2023-12-14T15:53:07Z)
• Avoidance Navigation Based on Offline Pre-Training Reinforcement Learning [0.0]
  This paper presents a Pre-Training Deep Reinforcement Learning(DRL) for avoidance navigation without map for mobile robots. The efficient offline training strategy is proposed to speed up the inefficient random explorations in early stage. It was demonstrated that our DRL model have universal general capacity in different environment.
  arXiv  Detail & Related papers  (2023-08-03T06:19:46Z)
• Model-Based Reinforcement Learning with Multi-Task Offline Pretraining [59.82457030180094]
  We present a model-based RL method that learns to transfer potentially useful dynamics and action demonstrations from offline data to a novel task. The main idea is to use the world models not only as simulators for behavior learning but also as tools to measure the task relevance. We demonstrate the advantages of our approach compared with the state-of-the-art methods in Meta-World and DeepMind Control Suite.
  arXiv  Detail & Related papers  (2023-06-06T02:24:41Z)
• Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning [54.67880602409801]
  In this paper, we study the problem of pre-training world models with abundant in-the-wild videos for efficient learning of visual control tasks. We introduce Contextualized World Models (ContextWM) that explicitly separate context and dynamics modeling. Our experiments show that in-the-wild video pre-training equipped with ContextWM can significantly improve the sample efficiency of model-based reinforcement learning.
  arXiv  Detail & Related papers  (2023-05-29T14:29:12Z)
• Accelerating exploration and representation learning with offline pre-training [52.6912479800592]
  We show that exploration and representation learning can be improved by separately learning two different models from a single offline dataset. We show that learning a state representation using noise-contrastive estimation and a model of auxiliary reward can significantly improve the sample efficiency on the challenging NetHack benchmark.
  arXiv  Detail & Related papers  (2023-03-31T18:03:30Z)
• Continual Visual Reinforcement Learning with A Life-Long World Model [55.05017177980985]
  We present a new continual learning approach for visual dynamics modeling.<n>We first introduce the life-long world model, which learns task-specific latent dynamics.<n>Then, we address the value estimation challenge for previous tasks with the exploratory-conservative behavior learning approach.
  arXiv  Detail & Related papers  (2023-03-12T05:08:03Z)
• Towards Scale Consistent Monocular Visual Odometry by Learning from the Virtual World [83.36195426897768]
  We propose VRVO, a novel framework for retrieving the absolute scale from virtual data. We first train a scale-aware disparity network using both monocular real images and stereo virtual data. The resulting scale-consistent disparities are then integrated with a direct VO system.
  arXiv  Detail & Related papers  (2022-03-11T01:51:54Z)
• Counterfactual Vision-and-Language Navigation via Adversarial Path Sampling [65.99956848461915]
  Vision-and-Language Navigation (VLN) is a task where agents must decide how to move through a 3D environment to reach a goal.<n>One of the problems of the VLN task is data scarcity since it is difficult to collect enough navigation paths with human-annotated instructions for interactive environments.<n>We propose an adversarial-driven counterfactual reasoning model that can consider effective conditions instead of low-quality augmented data.
  arXiv  Detail & Related papers  (2019-11-17T18:02:51Z)

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.