VTInstructor: Visual Trajectory Prompting for Navigation Instruction Generation in Continuous Environments

• URL: http://arxiv.org/abs/2608.15284v1
• Date: Sat, 15 Aug 2026 15:31:27 GMT
• Title: VTInstructor: Visual Trajectory Prompting for Navigation Instruction Generation in Continuous Environments
• Abstract summary: We propose VTInstructor, the first VLN instruction generation framework for continuous environments.<n> EDTC condenses long RGB trajectories into navigation-criticals, VTP overlays path, turn, and goal cues onto these anchors, and VTMod injects the resulting trajectory signals into the visual encoder.<n>On the challenging R2R-CE and RxR-CE Val Unseen benchmarks, VTInstructor sets a new state of the art across all standard NLG metrics.
• Score: 14.629408091049982
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Navigation instruction generation from ego-centric RGB video in continuous environments is an important yet challenging task for human-robot interaction and scalable dataset construction. Prior instruction generators assume discrete viewpoint graphs with panoramic observations, where trajectory structure is explicit; in continuous environments, however, the agent receives only a dense RGB stream, making trajectory cues difficult to recover. We propose VTInstructor, the first VLN instruction generation framework for continuous environments. Our key idea is to convert implicit trajectory geometry into explicit visual trajectory prompts: EDTC condenses long RGB trajectories into navigation-critical keyframes, VTP overlays path, turn, and goal cues onto these anchors, VTMod injects the resulting trajectory signals into the visual encoder, and VT-GRPO further calibrates this spatial injection during training, all without requiring a navigation graph, pre-built map, or scene reconstruction. On the challenging R2R-CE and RxR-CE Val Unseen benchmarks, VTInstructor sets a new state of the art across all standard NLG metrics, surpassing the strongest baseline by +0.357 CIDEr and +0.109 CIDEr, respectively. Beyond automatic metrics, VTInstructor-generated instructions raise a frozen follower's success rate to 63.3%, a +14.7 percentage-point gain over the best competing instruction source, and provide consistent data augmentation gains of +3 SR points on downstream navigation tasks.

Related papers

• LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation [52.91080323083409]
  Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embodiments.<n>Here we present LightNav-0, a compact generalist embodied navigation model that elicits the spatial intelligence of a pretrained VLM and aligns it with navigation, without task-specific prediction heads.
  arXiv  Detail & Related papers  (2026-08-31T15:08:53Z)
• Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation [68.02899606570223]
  We propose TAMP-Nav, a unified framework for efficient embodied navigation.<n>First, we introduce a Pixel-to-3D Action Formulation (Point) that reformulates navigation into 2D visual coordinates.<n>Second, we propose an integrated Selective Reasoning and Anchor-Trajectory Memory mechanism (Think and Memorize)
  arXiv  Detail & Related papers  (2026-08-18T08:37:08Z)
• DynFly: Dynamic-Aware Continuous Trajectory Generation for UAV Vision-Language Navigation in Urban Environments [55.73595346639892]
  We propose DynFly to bridge high-level navigation reasoning and executable UAV motion.<n>DynFly represents expert trajectories in B-spline control-point space and employs a Spline-DiT generator to learn conditional trajectory generation.<n>Experiments on the OpenUAV UAV-VLN benchmark show that DynFly improves both navigation performance and trajectory quality.
  arXiv  Detail & Related papers  (2026-06-30T13:33:48Z)
• AutoFly: Vision-Language-Action Model for UAV Autonomous Navigation in the Wild [62.47761809929869]
  Vision-language navigation (VLN) requires intelligent agents to navigate environments by interpreting linguistic instructions alongside visual observations.<n>Current VLN research for unmanned aerial vehicles (UAVs) relies on detailed, pre-specified instructions to guide the UAV along predetermined routes.<n>We propose AutoFly, an end-to-end Vision-Language-Action model for autonomous UAV navigation.
  arXiv  Detail & Related papers  (2026-02-10T11:08:07Z)
• SwiTrack: Tri-State Switch for Cross-Modal Object Tracking [74.15663758681849]
  Cross-modal object tracking (CMOT) is an emerging task that maintains target consistency while the video stream switches between different modalities.<n>We propose SwiTrack, a novel state-switching framework that redefines CMOT through the deployment of three specialized streams.
  arXiv  Detail & Related papers  (2025-11-20T10:52:54Z)
• VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning [77.34267241692706]
  Vision-Language Navigation (VLN) is a core challenge in embodied AI, requiring agents to navigate real-world environments using natural language instructions.<n>We propose VLN-R1, an end-to-end framework that leverages Large Vision-Language Models (LVLM) to directly translate egocentric video streams into continuous navigation actions.
  arXiv  Detail & Related papers  (2025-06-20T17:59:59Z)
• ST-Booster: An Iterative SpatioTemporal Perception Booster for Vision-and-Language Navigation in Continuous Environments [1.9566515100805284]
  VLN-CE requires agents to navigate continuous spaces based on natural language instructions.<n>This paper introduces ST-Booster, a navigation booster that enhances performance through multi-granularity perception and instruction-aware reasoning.<n>Extensive experiments and performance analyses are conducted, demonstrating that ST-Booster outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-04-14T03:29:08Z)
• Reinforced Structured State-Evolution for Vision-Language Navigation [42.46176089721314]
  Vision-and-language Navigation (VLN) task requires an embodied agent to navigate to a remote location following a natural language instruction. Previous methods usually adopt a sequence model (e.g., Transformer and LSTM) as the navigator. We propose a novel Structured state-Evolution (SEvol) model to effectively maintain the environment layout clues for VLN.
  arXiv  Detail & Related papers  (2022-04-20T07:51:20Z)
• Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation [41.334731014665316]
  Most existing works in vision-and-language navigation (VLN) focus on either discrete or continuous environments. We propose a predictor to generate a set of candidate waypoints during navigation. We show that agents navigating in continuous environments with predicted waypoints perform significantly better than agents using low-level actions.
  arXiv  Detail & Related papers  (2022-03-05T14:56:14Z)

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.