Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigation

• URL: http://arxiv.org/abs/2406.09798v3
• Date: Mon, 14 Oct 2024 04:48:18 GMT
• Title: Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigation
• Authors: Zihan Wang, Xiangyang Li, Jiahao Yang, Yeqi Liu, Shuqiang Jiang,
• Abstract summary: Vision-and-language navigation (VLN) enables the agent to navigate to a remote location in 3D environments following the natural language instruction. In this work, we propose a sim-to-real transfer approach to endow the monocular robots with panoramic traversability perception and panoramic semantic understanding. Our VLN system outperforms previous SOTA monocular VLN methods in R2R-CE and RxR-CE benchmarks within the simulation environments and is also validated in real-world environments.
• Score: 38.04404612393027
• License:
• Abstract: Vision-and-language navigation (VLN) enables the agent to navigate to a remote location in 3D environments following the natural language instruction. In this field, the agent is usually trained and evaluated in the navigation simulators, lacking effective approaches for sim-to-real transfer. The VLN agents with only a monocular camera exhibit extremely limited performance, while the mainstream VLN models trained with panoramic observation, perform better but are difficult to deploy on most monocular robots. For this case, we propose a sim-to-real transfer approach to endow the monocular robots with panoramic traversability perception and panoramic semantic understanding, thus smoothly transferring the high-performance panoramic VLN models to the common monocular robots. In this work, the semantic traversable map is proposed to predict agent-centric navigable waypoints, and the novel view representations of these navigable waypoints are predicted through the 3D feature fields. These methods broaden the limited field of view of the monocular robots and significantly improve navigation performance in the real world. Our VLN system outperforms previous SOTA monocular VLN methods in R2R-CE and RxR-CE benchmarks within the simulation environments and is also validated in real-world environments, providing a practical and high-performance solution for real-world VLN.

Related papers

• Enhancing Autonomous Navigation by Imaging Hidden Objects using Single-Photon LiDAR [12.183773707869069]
  We present a novel approach that leverages Non-Line-of-Sight (NLOS) sensing using single-photon LiDAR to improve visibility and enhance autonomous navigation. Our method enables mobile robots to "see around corners" by utilizing multi-bounce light information.
  arXiv  Detail & Related papers  (2024-10-04T16:03:13Z)
• Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions [69.9980759344628]
  Vision-and-Language Navigation (VLN) aims to develop embodied agents that navigate based on human instructions. We introduce Human-Aware Vision-and-Language Navigation (HA-VLN), extending traditional VLN by incorporating dynamic human activities. We present the Expert-Supervised Cross-Modal (VLN-CM) and Non-Expert-Supervised Decision Transformer (VLN-DT) agents, utilizing cross-modal fusion and diverse training strategies.
  arXiv  Detail & Related papers  (2024-06-27T15:01:42Z)
• Gaussian Splatting to Real World Flight Navigation Transfer with Liquid Networks [93.38375271826202]
  We present a method to improve generalization and robustness to distribution shifts in sim-to-real visual quadrotor navigation tasks. We first build a simulator by integrating Gaussian splatting with quadrotor flight dynamics, and then, train robust navigation policies using Liquid neural networks. In this way, we obtain a full-stack imitation learning protocol that combines advances in 3D Gaussian splatting radiance field rendering, programming of expert demonstration training data, and the task understanding capabilities of Liquid networks.
  arXiv  Detail & Related papers  (2024-06-21T13:48:37Z)
• Volumetric Environment Representation for Vision-Language Navigation [66.04379819772764]
  Vision-language navigation (VLN) requires an agent to navigate through a 3D environment based on visual observations and natural language instructions. We introduce a Volumetric Environment Representation (VER), which voxelizes the physical world into structured 3D cells. VER predicts 3D occupancy, 3D room layout, and 3D bounding boxes jointly.
  arXiv  Detail & Related papers  (2024-03-21T06:14:46Z)
• NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning [101.56342075720588]
  Vision-and-Language Navigation (VLN), as a crucial research problem of Embodied AI, requires an embodied agent to navigate through complex 3D environments following natural language instructions. Recent research has highlighted the promising capacity of large language models (LLMs) in VLN by improving navigational reasoning accuracy and interpretability. This paper introduces a novel strategy called Navigational Chain-of-Thought (NavCoT), where we fulfill parameter-efficient in-domain training to enable self-guided navigational decision.
  arXiv  Detail & Related papers  (2024-03-12T07:27:02Z)
• Image-based Navigation in Real-World Environments via Multiple Mid-level Representations: Fusion Models, Benchmark and Efficient Evaluation [13.207579081178716]
  In recent learning-based navigation approaches, the scene understanding and navigation abilities of the agent are achieved simultaneously. Unfortunately, even if simulators represent an efficient tool to train navigation policies, the resulting models often fail when transferred into the real world. One possible solution is to provide the navigation model with mid-level visual representations containing important domain-invariant properties of the scene.
  arXiv  Detail & Related papers  (2022-02-02T15:00:44Z)
• On Embodied Visual Navigation in Real Environments Through Habitat [20.630139085937586]
  Visual navigation models based on deep learning can learn effective policies when trained on large amounts of visual observations. To deal with this limitation, several simulation platforms have been proposed in order to train visual navigation policies on virtual environments efficiently. We show that our tool can effectively help to train and evaluate navigation policies on real-world observations without running navigation pisodes in the real world.
  arXiv  Detail & Related papers  (2020-10-26T09:19:07Z)
• Transferable Active Grasping and Real Embodied Dataset [48.887567134129306]
  We show how to search for feasible viewpoints for grasping by the use of hand-mounted RGB-D cameras. A practical 3-stage transferable active grasping pipeline is developed, that is adaptive to unseen clutter scenes. In our pipeline, we propose a novel mask-guided reward to overcome the sparse reward issue in grasping and ensure category-irrelevant behavior.
  arXiv  Detail & Related papers  (2020-04-28T08:15:35Z)

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.