VANP: Learning Where to See for Navigation with Self-Supervised Vision-Action Pre-Training

• URL: http://arxiv.org/abs/2403.08109v3
• Date: Wed, 4 Sep 2024 20:54:13 GMT
• Title: VANP: Learning Where to See for Navigation with Self-Supervised Vision-Action Pre-Training
• Authors: Mohammad Nazeri, Junzhe Wang, Amirreza Payandeh, Xuesu Xiao,
• Abstract summary: Humans excel at efficiently navigating through crowds without collision by focusing on specific visual regions relevant to navigation. Most robotic visual navigation methods rely on deep learning models pre-trained on vision tasks, which prioritize salient objects. We propose a Self-Supervised Vision-Action Model for Visual Navigation Pre-Training (VANP)
• Score: 8.479135285935113
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Humans excel at efficiently navigating through crowds without collision by focusing on specific visual regions relevant to navigation. However, most robotic visual navigation methods rely on deep learning models pre-trained on vision tasks, which prioritize salient objects -- not necessarily relevant to navigation and potentially misleading. Alternative approaches train specialized navigation models from scratch, requiring significant computation. On the other hand, self-supervised learning has revolutionized computer vision and natural language processing, but its application to robotic navigation remains underexplored due to the difficulty of defining effective self-supervision signals. Motivated by these observations, in this work, we propose a Self-Supervised Vision-Action Model for Visual Navigation Pre-Training (VANP). Instead of detecting salient objects that are beneficial for tasks such as classification or detection, VANP learns to focus only on specific visual regions that are relevant to the navigation task. To achieve this, VANP uses a history of visual observations, future actions, and a goal image for self-supervision, and embeds them using two small Transformer Encoders. Then, VANP maximizes the information between the embeddings by using a mutual information maximization objective function. We demonstrate that most VANP-extracted features match with human navigation intuition. VANP achieves comparable performance as models learned end-to-end with half the training time and models trained on a large-scale, fully supervised dataset, i.e., ImageNet, with only 0.08% data.

Related papers

• UnitedVLN: Generalizable Gaussian Splatting for Continuous Vision-Language Navigation [71.97405667493477]
  We introduce a novel, generalizable 3DGS-based pre-training paradigm, called UnitedVLN. It enables agents to better explore future environments by unitedly rendering high-fidelity 360 visual images and semantic features. UnitedVLN outperforms state-of-the-art methods on existing VLN-CE benchmarks.
  arXiv  Detail & Related papers  (2024-11-25T02:44:59Z)
• Narrowing the Gap between Vision and Action in Navigation [28.753809306008996]
  We introduce a low-level action decoder jointly trained with high-level action prediction. Our agent can improve navigation performance metrics compared to the strong baselines on both high-level and low-level actions.
  arXiv  Detail & Related papers  (2024-08-19T20:09:56Z)
• Aligning Knowledge Graph with Visual Perception for Object-goal Navigation [16.32780793344835]
  We propose the Aligning Knowledge Graph with Visual Perception (AKGVP) method for object-goal navigation. Our approach introduces continuous modeling of the hierarchical scene architecture and leverages visual-language pre-training to align natural language description with visual perception. The integration of a continuous knowledge graph architecture and multimodal feature alignment empowers the navigator with a remarkable zero-shot navigation capability.
  arXiv  Detail & Related papers  (2024-02-29T06:31:18Z)
• What Makes Pre-Trained Visual Representations Successful for Robust Manipulation? [57.92924256181857]
  We find that visual representations designed for manipulation and control tasks do not necessarily generalize under subtle changes in lighting and scene texture. We find that emergent segmentation ability is a strong predictor of out-of-distribution generalization among ViT models.
  arXiv  Detail & Related papers  (2023-11-03T18:09:08Z)
• Learning Navigational Visual Representations with Semantic Map Supervision [85.91625020847358]
  We propose a navigational-specific visual representation learning method by contrasting the agent's egocentric views and semantic maps. Ego$2$-Map learning transfers the compact and rich information from a map, such as objects, structure and transition, to the agent's egocentric representations for navigation.
  arXiv  Detail & Related papers  (2023-07-23T14:01:05Z)
• ViNT: A Foundation Model for Visual Navigation [52.2571739391896]
  Visual Navigation Transformer (ViNT) is a foundation model for vision-based robotic navigation. ViNT is trained with a general goal-reaching objective that can be used with any navigation dataset. It exhibits positive transfer, outperforming specialist models trained on singular datasets.
  arXiv  Detail & Related papers  (2023-06-26T16:57:03Z)
• KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation [61.08389704326803]
  Vision-and-language navigation (VLN) is the task to enable an embodied agent to navigate to a remote location following the natural language instruction in real scenes. Most of the previous approaches utilize the entire features or object-centric features to represent navigable candidates. We propose a Knowledge Enhanced Reasoning Model (KERM) to leverage knowledge to improve agent navigation ability.
  arXiv  Detail & Related papers  (2023-03-28T08:00:46Z)
• Towards self-attention based visual navigation in the real world [0.0]
  Vision guided navigation requires processing complex visual information to inform task-orientated decisions. Deep Reinforcement Learning agents trained in simulation often exhibit unsatisfactory results when deployed in the real-world. This is the first demonstration of a self-attention based agent successfully trained in navigating a 3D action space, using less than 4000 parameters.
  arXiv  Detail & Related papers  (2022-09-15T04:51:42Z)
• PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning [125.22462763376993]
  We propose Potential functions for ObjectGoal Navigation with Interaction-free learning (PONI) PONI disentangles the skills of where to look?' for an object and how to navigate to (x, y)?'
  arXiv  Detail & Related papers  (2022-01-25T01:07:32Z)
• MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigation [4.127128889779478]
  This work focuses on performing better or comparable to the existing learning-based solutions for visual navigation for autonomous agents. We propose a method to encode vital scene semantics into a semantically informed, top-down egocentric map representation. We conduct experiments on 3-D reconstructed indoor PointGoal visual navigation and demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2021-03-21T12:01:23Z)

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.