Learning Adaptive Safety Margins for Visual Navigation

• URL: http://arxiv.org/abs/2607.18200v1
• Date: Mon, 20 Jul 2026 17:40:25 GMT
• Title: Learning Adaptive Safety Margins for Visual Navigation
• Abstract summary: Diffusion-based planners propose diverse trajectory candidates from egocentric RGB-D, yet reliable selection remains the bottleneck.<n>We propose a context-conditioned safety critic that learns an adaptive clearance preference for ranking diffusion proposals.<n>We train the critic with privileged ESDF geometry in simulation and distill it into a perception-only selector via a two-stage teacher-student procedure.
• Score: 10.650323979444982
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Robots in cluttered indoor spaces often fail not because they cannot generate collision-free paths, but because a fixed safety margin is mis-calibrated: conservative margins cause detours and timeouts, while permissive margins lead to near-boundary shortcuts under perception bias. Diffusion-based planners propose diverse trajectory candidates from egocentric RGB-D, yet reliable selection remains the bottleneck. We propose a context-conditioned safety critic that learns an adaptive clearance preference for ranking diffusion proposals, decomposed into three complementary terms: (i) a safety term with a clearance-budget penalty and a control-barrier-function residual for waypoint- and transition-wise safety, (ii) an efficiency term combining a smoothness penalty with a safety-gated detour-ratio penalty that avoids detours without incentivizing risky shortcuts, and (iii) a distance-constraint matching term that anchors the learned budget to realized ESDF clearances to prevent margin collapse. We train the critic with privileged ESDF geometry in simulation and distill it into a perception-only selector via a two-stage teacher-student procedure. On PointGoal navigation in HM3D and MP3D, including cross-dataset transfer, our method achieves the highest success rate (SR) and success weighted by path length (SPL) among strong diffusion, optimization, and RL baselines. Trained purely in simulation, it transfers to a Unitree G1 humanoid and navigates cluttered indoor scenes without task-specific tuning.

Related papers

• Variance-Guided Spatial Attention Fusion for Robust End-to-End Driving under Asymmetric Sensor Degradation [14.393656149682068]
  We propose Variance-Guided Spatial Attention Fusion (VG-SAF) to improve end-to-end multimodal driving.<n>First, a physically grounded augmentor simulates representative camera and LiDAR failures and emits a continuous spatial mask.<n>Second, modality-specific experts predict per-pixel reliability scales through cross-branch dense distillation in log space.<n>Third, calibrated reliability maps drive a hybrid attention mechanism that suppresses unreliable cells with a local spatial gate.
  arXiv  Detail & Related papers  (2026-08-25T10:27:02Z)
• RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework [49.531001563853984]
  RAD-2 is a unified generator-discriminator framework for closed-loop planning.<n>It produces diverse trajectory candidates, while an RL-optimized discriminator reranks these candidates according to their long-term driving quality.<n>It reduces the collision rate by 56% compared with strong diffusion-based planners.
  arXiv  Detail & Related papers  (2026-04-16T17:59:44Z)
• PC-Diffuser: Path-Consistent Capsule CBF Safety Filtering for Diffusion-Based Trajectory Planner [15.914164951048614]
  PC-Diffuser is a safety augmentation framework that embeds a path-consistent barrier-function structure directly into the denoising loop of diffusion planning.<n>It evaluates collision risk using a capsule-distance barrier function that better reflects vehicle geometry.<n>It converts denoised waypoints into dynamically feasible motion under a kinematic bicycle model.
  arXiv  Detail & Related papers  (2026-03-11T01:52:56Z)
• BarrierSteer: LLM Safety via Learning Barrier Steering [83.12893815611052]
  BarrierSteer is a novel framework that formalizes safety by embedding learned non-linear safety constraints directly into the model's latent representation space.<n>We show that BarrierSteer substantially reduces adversarial success rates, decreases unsafe generations, and outperforms existing methods.
  arXiv  Detail & Related papers  (2026-02-23T18:19:46Z)
• Understanding and Preserving Safety in Fine-Tuned LLMs [20.821783178639063]
  Fine-tuning can substantially degrade safety alignment, even when the fine-tuning data is harmless.<n>We propose safety-preserving fine-tuning (SPF), a lightweight approach that explicitly removes gradient components conflicting with the low-rank safety subspace.<n> SPF consistently maintains downstream task performance and recovers nearly all pre-trained safety alignment, even under adversarial fine-tuning scenarios.
  arXiv  Detail & Related papers  (2026-01-15T07:33:13Z)
• SWIFT-Nav: Stability-Aware Waypoint-Level TD3 with Fuzzy Arbitration for UAV Navigation in Cluttered Environments [0.0]
  We propose a TD3-based navigation framework that achieves fast, stable convergence to obstacle-aware paths.<n>We show that combining TD3 with replay prioritisation, exploration, and fuzzy-safety rules yields a robust and deployable solution for UAV navigation in cluttered scenes.
  arXiv  Detail & Related papers  (2025-12-17T23:19:06Z)
• Building a Foundational Guardrail for General Agentic Systems via Synthetic Data [76.18834864749606]
  LLM agents can plan multi-step tasks, intervening at the planning stage-before any action is executed-is often the safest way to prevent harm.<n>Existing guardrails mostly operate post-execution, which is difficult to scale and leaves little room for controllable supervision at the plan level.<n>We introduce AuraGen, a controllable engine that synthesizes benign trajectories, injects category-labeled risks with difficulty, and filters outputs via an automated reward model.
  arXiv  Detail & Related papers  (2025-10-10T18:42:32Z)
• Boundary-to-Region Supervision for Offline Safe Reinforcement Learning [56.150983204962735]
  Boundary-to-Region (B2R) is a framework that enables asymmetric conditioning through cost signal realignment.<n>B2R redefines CTG as a boundary constraint under a fixed safety budget, unifying the cost distribution of all feasible trajectories.<n> Experimental results show that B2R satisfies safety constraints in 35 out of 38 safety-critical tasks.
  arXiv  Detail & Related papers  (2025-09-30T03:38:20Z)
• Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts [80.32933059529135]
  Test-Time Adaptation (TTA) methods have emerged to adapt to target distributions during inference.<n>We propose Dual Uncertainty Optimization (DUO), the first TTA framework designed to jointly minimize both uncertainties for robust M3OD.<n>In parallel, we design a semantic-aware normal field constraint that preserves geometric coherence in regions with clear semantic cues.
  arXiv  Detail & Related papers  (2025-08-28T07:09:21Z)
• Rethinking Safety in LLM Fine-tuning: An Optimization Perspective [56.31306558218838]
  We show that poor optimization choices, rather than inherent trade-offs, often cause safety problems, measured as harmful responses to adversarial prompts.<n>We propose a simple exponential moving average (EMA) momentum technique in parameter space that preserves safety performance.<n>Our experiments on the Llama families across multiple datasets demonstrate that safety problems can largely be avoided without specialized interventions.
  arXiv  Detail & Related papers  (2025-08-17T23:46:36Z)
• AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin [38.577959886489076]
  Large language models (LLMs) are vulnerable to safety risks during fine-tuning.<n>We propose a methodology for safety fine-tuning called AsFT (Anchoring Safety in Fine-Tuning)
  arXiv  Detail & Related papers  (2025-06-10T05:59:48Z)

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.