HCSG: Human-Centric Semantic-Geometric Reasoning for Vision-Language Navigation

• URL: http://arxiv.org/abs/2605.13321v1
• Date: Wed, 13 May 2026 10:34:47 GMT
• Title: HCSG: Human-Centric Semantic-Geometric Reasoning for Vision-Language Navigation
• Abstract summary: VLN has achieved remarkable progress by scaling data and model capacity.<n>We propose HCSG, the first human-centric framework for VLN.<n>This framework provides a robust foundation for safe, socially intelligent navigation in dynamic human-robot environments.
• Score: 26.790598190282136
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: VLN has achieved remarkable progress by scaling data and model capacity. However, the assumption of a static environment breaks down in real-world indoor scenarios, where robots inevitably encounter dynamic pedestrians. Existing human-aware approaches typically treat humans merely as moving obstacles based on implicit visual cues, lacking the explicit reasoning required to interpret human intentions or maintain social norms. To address this, we propose HCSG, the first human-centric framework for VLN. This framework provides a robust foundation for safe, socially intelligent navigation in dynamic human-robot environments that shifts the paradigm from passive collision avoidance to active human behavior understanding. Specifically, HCSG introduces a unified Human Understanding Module that synergizes two key capabilities: (i) geometric forecasting, which predicts human pose and trajectory to anticipate future motion dynamics; and (ii) semantic interpretation, which leverages a Vision-Language Model (VLM) to generate natural language descriptions of human actions and intentions. These semantic-geometric representations are fused into the agent's topological map for instruction-conditioned planning. Furthermore, a social distance loss is introduced to enforce socially compliant interaction distances. Extensive experiments on the HA-VLNCE benchmark demonstrate that HCSG significantly outperforms state-of-the-art methods, achieving a 14% improvement in Success Rate and a 34% reduction in Collision Rate. Our project can be seen at https://haoxuanxu1024.github.io/HCSG/.

Related papers

• DeSeG: Decoupling Semantic Intent and Geometric Constraints for Physically Plausible Human-Scene Interaction [50.06148080975928]
  We propose DeSeG, a hierarchical framework that explicitly decouples semantic intent from geometric constraints.<n>DeSeG achieves state-of-the-art performance, reducing mean scene penetration by 47% and improving semantic alignment by 29% over the SOTA baselines.
  arXiv  Detail & Related papers  (2026-07-07T03:21:08Z)
• Scene-aware Prediction of Diverse Human Movement Goals [0.0]
  We propose a novel multi-goal prediction method using the generative model to address the semanticity of human movement.<n>Our results demonstrate that our approach is capable of generating multiple movement goals in the scene via samplings in latent space of the Conditional Variational Autoencoder.
  arXiv  Detail & Related papers  (2026-06-29T08:20:19Z)
• EscherVerse: An Open World Benchmark and Dataset for Teleo-Spatial Intelligence with Physical-Dynamic and Intent-Driven Understanding [56.89359230139883]
  We introduce Teleo-Spatial Intelligence (TSI), a new paradigm that unifies two critical pillars: Physical-Dynamic Reasoning and Intent-Driven Reasoning.<n>We present EscherVerse, consisting of a large-scale, open-world benchmark (Escher-Bench), a dataset (Escher-35k), and models (Escher series)<n>It is the first benchmark to systematically assess Intent-Driven Reasoning, challenging models to connect physical events to their underlying human purposes.
  arXiv  Detail & Related papers  (2026-01-04T14:42:39Z)
• Seeing is Believing (and Predicting): Context-Aware Multi-Human Behavior Prediction with Vision Language Models [8.568706722040421]
  We present CAMP-VLM (Context-Aware Multi-human behavior Prediction): a Vision Language Model (VLM)-based framework.<n> CAMP-VLM incorporates contextual features from visual input and spatial awareness from scene graphs to enhance prediction of humans-scene interactions.<n>It outperforms the best-performing baseline by up to 66.9% in prediction accuracy.
  arXiv  Detail & Related papers  (2025-12-17T20:44:32Z)
• HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions [64.69468932145234]
  We present HA-VLN 2.0, a unified benchmark introducing explicit social-awareness constraints.<n>Results show that explicit social modeling improves navigation robustness and reduces collisions.
  arXiv  Detail & Related papers  (2025-03-18T13:05:55Z)
• 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)
• CoNav: A Benchmark for Human-Centered Collaborative Navigation [66.6268966718022]
  We propose a collaborative navigation (CoNav) benchmark. Our CoNav tackles the critical challenge of constructing a 3D navigation environment with realistic and diverse human activities. We propose an intention-aware agent for reasoning both long-term and short-term human intention.
  arXiv  Detail & Related papers  (2024-06-04T15:44:25Z)
• Predicting Human Mobility via Self-supervised Disentanglement Learning [21.61423193132924]
  We propose a novel disentangled solution called SSDL for tackling the next POI prediction problem. We present two realistic trajectory augmentation approaches to enhance the understanding of both the human intrinsic periodicity and constantly-changing intents. Extensive experiments conducted on four real-world datasets demonstrate that our proposed SSDL significantly outperforms the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-11-17T16:17:22Z)
• GIMO: Gaze-Informed Human Motion Prediction in Context [75.52839760700833]
  We propose a large-scale human motion dataset that delivers high-quality body pose sequences, scene scans, and ego-centric views with eye gaze. Our data collection is not tied to specific scenes, which further boosts the motion dynamics observed from our subjects. To realize the full potential of gaze, we propose a novel network architecture that enables bidirectional communication between the gaze and motion branches.
  arXiv  Detail & Related papers  (2022-04-20T13:17:39Z)

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.