Guided Diffusion with Distilled Vision-Language Reliability for Aerial Navigation

• URL: http://arxiv.org/abs/2606.13883v1
• Date: Thu, 11 Jun 2026 20:18:34 GMT
• Title: Guided Diffusion with Distilled Vision-Language Reliability for Aerial Navigation
• Abstract summary: We present a reliability-aware diffusion planner for 3D UAV navigation.<n>It conditions trajectory generation on the observation together with a scene-level reliability heatmap.<n>To generalise to unseen environments without retraining, we steer the denoising process with a differentiable two-stage ESDF cost.
• Score: 2.186077977059593
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Autonomous UAV navigation is conventionally solved by pipelines that separate perception, mapping, and planning into distinct stages, which propagates errors, accumulates latency, and requires environment-specific retuning. End-to-end generative models remove these interfaces by mapping raw observations directly to trajectories, but inherit a subtle failure mode: trained on clean data, they cannot recognise when an observation is unreliable, and treat degraded regions such as glass, mirrors, and overexposed surfaces as valid evidence for planning. We present a reliability-aware diffusion planner for 3D UAV navigation. It conditions trajectory generation on the observation together with a scene-level reliability heatmap that marks where perception cannot be trusted, produced by a lightweight network that distils the open-vocabulary reasoning of a vision-language model within the real-time planning budget. To generalise to unseen environments without retraining, we steer the denoising process with a differentiable two-stage ESDF cost that treats physical obstacles from depth and virtual obstacles from highly unreliable regions on equal footing. In simulation and on a real quadrotor, our planner produces markedly safer trajectories than a state-of-the-art diffusion baseline, reducing the obstacle-violation rate from 40.3% to 9.6% and raising the mean reliability of traversed regions from 0.588 to 0.925. Ablating the reliability term alone drops mean reliability from 0.898 to 0.783, confirming it as the decisive component, while distillation runs the framework up to 2 times faster than the full vision-language model.

Related papers

• Map the Possibilities: Spatial Belief Fields for Language-Goal Aerial Navigation [49.03955946482723]
  We introduce SBFNav, a closed-loop navigation framework centered on a language- conditioned Spatial Belief Field.<n>Unlike ego-centric maps that primarily record what has been observed, SBF rep- resents a task-conditioned distribution over plausible target locations.<n>SBFNav selects the goal that best aligns with the instruction and observations as a met- ric waypoint for control.
  arXiv  Detail & Related papers  (2026-09-05T03:11:01Z)
• Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning [60.888463449435484]
  We present Shift & Drift, a novel dual-track benchmark designed to rigorously stress-test motion planners across two critical axes of distribution shift.<n>We show that imitation learning methods achieve high scores in ID benchmarks, but suffer from persistent drift when subjected to temporally correlated actuation noise.<n>Our findings reveal an empirical trade-off between imitation fidelity and closed-loop resilience, providing the community with a rigorous benchmark to evaluate progress toward reliable deployment.
  arXiv  Detail & Related papers  (2026-07-08T18:23:48Z)
• A Reliable Context-Aware and Temporal Planning Framework for Autonomous Driving [10.702734504331147]
  We present a Reliable Context-Aware and Temporal Planning framework for Autonomous Driving (RCT-AD)<n>A Reliable Context Awareness module scores per-frame reliability and selectively retains trustworthy features.<n>A Temporal Trajectory Planner captures long-term dependencies and multi-agent interactions to produce smoother, safety-aware trajectories.
  arXiv  Detail & Related papers  (2026-07-06T05:32:48Z)
• Rethinking Embodied Navigation via Relational Inductive Bias [53.72276435022479]
  We propose DB-Nav, a framework that reshapes the search space via dual relational biases.<n>It factorizes target-centric relations into an Activation Bias and an Inhibition Bias.<n>It significantly outperforms existing methods in success rate (SR) and Success weighted by Path Length (SPL)
  arXiv  Detail & Related papers  (2026-06-09T02:57:34Z)
• Uncertainty-Aware 3D Position Refinement for Multi-UAV Systems [0.3867363075280543]
  This paper presents a decentralized, lightweight 3D position-refinement layer that improves robustness by fusing each Unmanned Aerial Vehicle's local estimate with neighbor-shared state summaries and inter-UAV range or proximity constraints.<n>Results show that the proposed refinement substantially reduces mean localization error during cold start, remains competitive after local estimators stabilize, and maintains lower error as the fraction of malicious nodes increases compared with fusion without trust.
  arXiv  Detail & Related papers  (2026-05-13T13:22:14Z)
• Evidence-Based Landing Site Selection and Vison-Based Landing for UAVs in Unstructured Environments [0.9236074230806578]
  This paper presents an evidence-based probabilistic framework for autonomous UAV landing.<n>It explicitly separates decision-making under uncertainty from execution via visual servoing.<n>It is validated through both real-world laboratory experiments and high-fidelity simulations in Nvidia Isaac Sim.
  arXiv  Detail & Related papers  (2026-05-02T13:05:20Z)
• Task-Conditioned Uncertainty Costmaps for Legged Locomotion [8.377206870832945]
  Legged robots maintain dynamic feasibility through multicontact interactions with terrain.<n>We show that modeling uncertainty in predicted footholds, conditioned on terrain observations and commanded motion, distinguishes in-distribution from out-of-distribution operating regimes.<n>We use this learned uncertainty to detect OOD regions and incorporate them into a unified costmap-generation framework for uncertainty-aware path planning.
  arXiv  Detail & Related papers  (2026-04-30T21:54:43Z)
• Instance-level Visual Active Tracking with Occlusion-Aware Planning [61.982298426203165]
  Visual Active Tracking (VAT) aims to control cameras to follow a target in 3D space.<n>VAT faces two key bottlenecks in real-world deployment: confusion from visually similar distractors and severe failure under occlusions.<n>We propose OA-VAT, a unified pipeline with three complementary modules.
  arXiv  Detail & Related papers  (2026-04-23T09:11:50Z)
• LLM-Generated Fault Scenarios for Evaluating Perception-Driven Lane Following in Autonomous Edge Systems [0.5046831208137847]
  We introduce a decoupled offline-online fault injection framework for autonomous vision systems on edge devices.<n>This architecture separates the validation process into two distinct phases: a computationally intensive Offline Phase and a lightweight Online Phase.<n>We extensively validated this framework on a ResNet18 lane-following model across 460 fault scenarios.
  arXiv  Detail & Related papers  (2026-04-01T09:27:46Z)
• SAVANT: Semantic Analysis with Vision-Augmented Anomaly deTection [6.806105013817923]
  SAVANT is a structured reasoning framework that achieves high accuracy and recall in detecting anomalous driving scenarios.<n>By automatically labeling over 9,640 real-world images with high accuracy, SAVANT addresses the critical data scarcity problem in anomaly detection.
  arXiv  Detail & Related papers  (2025-10-20T19:14:29Z)
• Digging into contrastive learning for robust depth estimation with diffusion models [55.62276027922499]
  We propose a novel robust depth estimation method called D4RD. It features a custom contrastive learning mode tailored for diffusion models to mitigate performance degradation in complex environments. In experiments, D4RD surpasses existing state-of-the-art solutions on synthetic corruption datasets and real-world weather conditions.
  arXiv  Detail & Related papers  (2024-04-15T14:29:47Z)
• Robust Self-Supervised LiDAR Odometry via Representative Structure Discovery and 3D Inherent Error Modeling [67.75095378830694]
  We develop a two-stage odometry estimation network, where we obtain the ego-motion by estimating a set of sub-region transformations. In this paper, we aim to alleviate the influence of unreliable structures in training, inference and mapping phases. Our two-frame odometry outperforms the previous state of the arts by 16%/12% in terms of translational/rotational errors.
  arXiv  Detail & Related papers  (2022-02-27T12:52:27Z)

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.