Vi-LAD: Vision-Language Attention Distillation for Socially-Aware Robot Navigation in Dynamic Environments

• URL: http://arxiv.org/abs/2503.09820v1
• Date: Wed, 12 Mar 2025 20:38:23 GMT
• Title: Vi-LAD: Vision-Language Attention Distillation for Socially-Aware Robot Navigation in Dynamic Environments
• Authors: Mohamed Elnoor, Kasun Weerakoon, Gershom Seneviratne, Jing Liang, Vignesh Rajagopal, Dinesh Manocha,
• Abstract summary: We introduce Vision-Language Attention Distillation (Vi-LAD), a novel approach for distilling socially compliant navigation knowledge.<n>Vi-LAD fine-tunes a transformer-based model using intermediate attention maps extracted from a pre-trained vision-action model.<n>We validate our approach through real-world experiments on a Husky wheeled robot, demonstrating significant improvements over state-of-the-art navigation methods.
• Score: 41.75629159747654
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce Vision-Language Attention Distillation (Vi-LAD), a novel approach for distilling socially compliant navigation knowledge from a large Vision-Language Model (VLM) into a lightweight transformer model for real-time robotic navigation. Unlike traditional methods that rely on expert demonstrations or human-annotated datasets, Vi-LAD performs knowledge distillation and fine-tuning at the intermediate layer representation level (i.e., attention maps) by leveraging the backbone of a pre-trained vision-action model. These attention maps highlight key navigational regions in a given scene, which serve as implicit guidance for socially aware motion planning. Vi-LAD fine-tunes a transformer-based model using intermediate attention maps extracted from the pre-trained vision-action model, combined with attention-like semantic maps constructed from a large VLM. To achieve this, we introduce a novel attention-level distillation loss that fuses knowledge from both sources, generating augmented attention maps with enhanced social awareness. These refined attention maps are then utilized as a traversability costmap within a socially aware model predictive controller (MPC) for navigation. We validate our approach through real-world experiments on a Husky wheeled robot, demonstrating significant improvements over state-of-the-art (SOTA) navigation methods. Our results show up to 14.2% - 50% improvement in success rate, which highlights the effectiveness of Vi-LAD in enabling socially compliant and efficient robot navigation.

Related papers

• CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models [89.44024245194315]
  We introduce a method that incorporates explicit visual chain-of-thought (CoT) reasoning into vision-language-action models (VLAs) We introduce CoT-VLA, a state-of-the-art 7B VLA that can understand and generate visual and action tokens. Our experimental results demonstrate that CoT-VLA achieves strong performance, outperforming the state-of-the-art VLA model by 17% in real-world manipulation tasks and 6% in simulation benchmarks.
  arXiv  Detail & Related papers  (2025-03-27T22:23:04Z)
• NavigateDiff: Visual Predictors are Zero-Shot Navigation Assistants [24.689242976554482]
  Navigating unfamiliar environments presents significant challenges for household robots.<n>Existing reinforcement learning methods cannot be directly transferred to new environments.<n>We try to transfer the logical knowledge and the generalization ability of pre-trained foundation models to zero-shot navigation.
  arXiv  Detail & Related papers  (2025-02-19T17:27:47Z)
• Mobile Robot Navigation Using Hand-Drawn Maps: A Vision Language Model Approach [5.009635912655658]
  This paper introduces a novel Hand-drawn Map Navigation (HAM-Nav) architecture.<n>HAM-Nav integrates a unique Selective Visual Association Prompting approach for topological map-based position estimation.<n>Experiments were conducted in simulated environments, using both wheeled and legged robots.
  arXiv  Detail & Related papers  (2025-01-31T19:03:33Z)
• VANP: Learning Where to See for Navigation with Self-Supervised Vision-Action Pre-Training [8.479135285935113]
  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)
  arXiv  Detail & Related papers  (2024-03-12T22:33:08Z)
• Voila-A: Aligning Vision-Language Models with User's Gaze Attention [56.755993500556734]
  We introduce gaze information as a proxy for human attention to guide Vision-Language Models (VLMs) We propose a novel approach, Voila-A, for gaze alignment to enhance the interpretability and effectiveness of these models in real-world applications.
  arXiv  Detail & Related papers  (2023-12-22T17:34:01Z)
• Interactive Semantic Map Representation for Skill-based Visual Object Navigation [43.71312386938849]
  This paper introduces a new representation of a scene semantic map formed during the embodied agent interaction with the indoor environment. We have implemented this representation into a full-fledged navigation approach called SkillTron. The proposed approach makes it possible to form both intermediate goals for robot exploration and the final goal for object navigation.
  arXiv  Detail & Related papers  (2023-11-07T16:30:12Z)
• 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)
• Rapid Exploration for Open-World Navigation with Latent Goal Models [78.45339342966196]
  We describe a robotic learning system for autonomous exploration and navigation in diverse, open-world environments. At the core of our method is a learned latent variable model of distances and actions, along with a non-parametric topological memory of images. We use an information bottleneck to regularize the learned policy, giving us (i) a compact visual representation of goals, (ii) improved generalization capabilities, and (iii) a mechanism for sampling feasible goals for exploration.
  arXiv  Detail & Related papers  (2021-04-12T23:14:41Z)
• Occupancy Anticipation for Efficient Exploration and Navigation [97.17517060585875]
  We propose occupancy anticipation, where the agent uses its egocentric RGB-D observations to infer the occupancy state beyond the visible regions. By exploiting context in both the egocentric views and top-down maps our model successfully anticipates a broader map of the environment. Our approach is the winning entry in the 2020 Habitat PointNav Challenge.
  arXiv  Detail & Related papers  (2020-08-21T03:16:51Z)
• 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. 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. 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.