LH-AVLN: A Benchmark for Long-Horizon Audio-Visual-Language Navigation

• URL: http://arxiv.org/abs/2607.03920v1
• Date: Sat, 04 Jul 2026 15:25:25 GMT
• Title: LH-AVLN: A Benchmark for Long-Horizon Audio-Visual-Language Navigation
• Abstract summary: We introduce LH-AVLN, a benchmark for Long-Horizon Audio-Visual-Language Navigation.<n>In LH-AVLN, an agent receives a global mission of two to four goals specified by category, language description, or reference image.<n>We further develop PAG-Nav, a training-free reference agent that maintains a temporal uniform semantic map and performs progressive goal-state planning.
• Score: 30.160935888235727
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Embodied navigation is moving toward long-horizon missions, yet existing long-horizon benchmarks are largely acoustically silent, and audio-visual navigation tasks typically focus on a single goal. We introduce LH-AVLN, a benchmark for Long-Horizon Audio-Visual-Language Navigation that combines multi-goal mission execution, heterogeneous goal specifications, and persistent spatialized acoustic cues. In LH-AVLN, an agent receives a global mission of two to four goals specified by category, language description, or reference image, and navigates with RGB-D observations, pose, and binaural audio in indoor 3D environments. The benchmark supports both ordered and unordered missions, where alternating goal-associated sounds can guide non-line-of-sight search but may also become distractors as mission progress changes. We further develop PAG-Nav, a training-free reference agent that maintains a temporal uniform semantic map and performs progressive goal-state planning, using sound for search while reserving completion for visual-semantic verification. Experiments show that existing vision-language, memory-based, and audio-visual agents struggle to complete full LH-AVLN missions, and that PAG-Nav provides a stronger diagnostic baseline while leaving substantial room for future progress.

Related papers

• VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method [14.658802504108833]
  Vision-and-Language Navigation (VLN) enables embodied agents to follow natural-language instructions.<n>We propose Vision-Only Long-Horizon Navigation (VoLN), which shifts route-relevant information from externally supplied instructions and global guidance to locally observable in-scene cues.<n>We instantiate VoLN for aerial navigation through VoLN-UAV, a 7,210-episode benchmark that combines long-horizon goal-directed flight, continuous 3D motion, large viewpoint changes, and context-dependent beacon selection.
  arXiv  Detail & Related papers  (2026-07-23T15:02:01Z)
• SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning [59.64305326980364]
  SpaceVLN is a navigation agent built around Spatial Cognitive Memory and Task-Guided Spatial Reasoning.<n>Built on this memory, Spatial-CoT integrates task-progress reasoning with spatial perception, analysis, and prediction.<n>Across R2R-CE, RxR-CE, GN-Bench, and HM3D-OVON, SpaceVLN achieves state-of-the-art zero-shot performance.
  arXiv  Detail & Related papers  (2026-06-08T03:42:08Z)
• Semantic Audio-Visual Navigation in Continuous Environments [20.046962371381763]
  Audio-visual navigation enables embodied agents to navigate toward sound-emitting targets by leveraging both auditory and visual cues.<n>We introduce Audio-Visual Navigation in Continuous Environments (SAVNCE), where agents can move freely in 3D spaces and perceive temporally and spatially coherent audio-visual streams.<n>We propose MAGNet, a multimodal transformer-based model that jointly encodes spatial and semantic goal representations and integrates historical context with self-motion cues to enable memoryaugmented goal reasoning.
  arXiv  Detail & Related papers  (2026-03-20T05:49:50Z)
• OpenFrontier: General Navigation with Visual-Language Grounded Frontiers [54.661157616245966]
  Open-world navigation requires robots to make decisions in complex everyday environments.<n>Recent advances in vision--language navigation (VLN) and vision--language--action (VLA) models enable end-to-end policies conditioned on natural language.<n>We propose OpenFrontier, a training-free navigation framework that seamlessly integrates diverse vision--language prior models.
  arXiv  Detail & Related papers  (2026-03-05T17:02:22Z)
• VL-LN Bench: Towards Long-horizon Goal-oriented Navigation with Active Dialogs [51.18508300818979]
  Vision Language-Language Navigation (VL-LN) benchmark provides a large-scale, automatically generated dataset for training and assessing dialog-enabled navigation models.<n>VL-LN comprises over 41k long-horizon dialog-augmented trajectories for training and an automatic evaluation protocol with an oracle capable of responding to agent queries.
  arXiv  Detail & Related papers  (2025-12-26T19:00:12Z)
• CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory [39.76840258489023]
  Aerial vision-and-language navigation (VLN) requires drones to interpret natural language instructions and navigate complex urban environments.<n>We propose textbfCityNavAgent, a large language model (LLM)-empowered agent that significantly reduces the navigation complexity for urban aerial VLN.
  arXiv  Detail & Related papers  (2025-05-08T20:01:35Z)
• Navigation with VLM framework: Towards Going to Any Language [4.368039454973151]
  Vision Language Models (VLMs) have demonstrated remarkable capabilities to reason with both language and visual data.<n>We introduce Navigation with VLM (NavVLM), a training-free framework that harnesses open-source VLMs to enable robots to navigate effectively.
  arXiv  Detail & Related papers  (2024-09-18T02:29:00Z)
• GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation [65.71524410114797]
  GOAT-Bench is a benchmark for the universal navigation task GO to AnyThing (GOAT) In GOAT, the agent is directed to navigate to a sequence of targets specified by the category name, language description, or image. We benchmark monolithic RL and modular methods on the GOAT task, analyzing their performance across modalities.
  arXiv  Detail & Related papers  (2024-04-09T20:40:00Z)
• ESceme: Vision-and-Language Navigation with Episodic Scene Memory [72.69189330588539]
  Vision-and-language navigation (VLN) simulates a visual agent that follows natural-language navigation instructions in real-world scenes. We introduce a mechanism of Episodic Scene memory (ESceme) for VLN that wakes an agent's memories of past visits when it enters the current scene.
  arXiv  Detail & Related papers  (2023-03-02T07:42:07Z)
• AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments [60.98664330268192]
  We present AVLEN -- an interactive agent for Audio-Visual-Language Embodied Navigation. The goal of AVLEN is to localize an audio event via navigating the 3D visual world. To realize these abilities, AVLEN uses a multimodal hierarchical reinforcement learning backbone.
  arXiv  Detail & Related papers  (2022-10-14T16:35:06Z)
• Semantic Audio-Visual Navigation [93.12180578267186]
  We introduce semantic audio-visual navigation, where objects in the environment make sounds consistent with their semantic meaning. We propose a transformer-based model to tackle this new semantic AudioGoal task. Our method strongly outperforms existing audio-visual navigation methods by learning to associate semantic, acoustic, and visual cues.
  arXiv  Detail & Related papers  (2020-12-21T18:59:04Z)

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.