Cover Image

What You Don't Know Can Hurt You: How Well do Latent Safety Filters Understand Partially Observable Safety Constraints?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Matthew, Nakamura, Kensuke, Bajcsy, Andrea
Format:	Preprint
Published:	2025
Subjects:	Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AnySafe: Adapting Latent Safety Filters at Runtime via Safety Constraint Parameterization in the Latent Space
by: Agrawal, Sankalp, et al.
Published: (2025)

Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures
by: Seo, Junwon, et al.
Published: (2025)

How to Train Your Latent Control Barrier Function: Smooth Safety Filtering Under Hard-to-Model Constraints
by: Nakamura, Kensuke, et al.
Published: (2025)

Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis
by: Nakamura, Kensuke, et al.
Published: (2025)

Common-Sense Ergonomics (Or, What You Don't Do Can Hurt You!).
by: Butler, Sharon J.
Published: (1997)

First, Learn What You Don't Know: Active Information Gathering for Driving at the Limits of Handling
by: Davydov, Alexander, et al.
Published: (2024)

SPOC: Safety-Aware Planning Under Partial Observability And Physical Constraints
by: Kim, Hyungmin, et al.
Published: (2026)

Not All Errors Are Made Equal: A Regret Metric for Detecting System-level Trajectory Prediction Failures
by: Nakamura, Kensuke, et al.
Published: (2024)

What You Don't Know Won't Hurt You: Self-Consistent Hierarchical Inference with Unknown Follow-up Selection Strategies
by: Essick, Reed, et al.
Published: (2026)

What Matters to You? Towards Visual Representation Alignment for Robot Learning
by: Tian, Ran, et al.
Published: (2023)

Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs
by: Johnson, Daniel D., et al.
Published: (2024)

Visually Dehallucinative Instruction Generation: Know What You Don't Know
by: Cha, Sungguk, et al.
Published: (2024)

Parameter-Conditioned Reachable Sets for Updating Safety Assurances Online
by: Borquez, Javier, et al.
Published: (2022)

If You Don't Understand It, Don't Use It: Eliminating Trojans with Filters Between Layers
by: Hernandez, Adriano
Published: (2024)

Updating Robot Safety Representations Online from Natural Language Feedback
by: Santos, Leonardo, et al.
Published: (2024)

Know What You Don't Know: Uncertainty Calibration of Process Reward Models
by: Park, Young-Jin, et al.
Published: (2025)

Know What You Don't Know: Selective Prediction for Early Exit DNNs
by: Bajpai, Divya Jyoti, et al.
Published: (2025)

EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs
by: Yeom, Jewon, et al.
Published: (2026)

Deep QP Safety Filter: Model-free Learning for Reachability-based Safety Filter
by: Kim, Byeongjun, et al.
Published: (2026)

Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification
by: Wu, Yilin, et al.
Published: (2025)

I Know You Can't See Me: Dynamic Occlusion-Aware Safety Validation of Strategic Planners for Autonomous Vehicles Using Hypergames
by: Kahn, Maximilian, et al.
Published: (2021)

How to Computerize Your Serials and Periodicals When You Don't Know How
by: Matthews, Mary, et al.
Published: (1970)

RMP-YOLO: A Robust Motion Predictor for Partially Observable Scenarios even if You Only Look Once
by: Sun, Jiawei, et al.
Published: (2024)

Do You Know the Way? Human-in-the-Loop Understanding for Fast Traversability Estimation in Mobile Robotics
by: Schreiber, Andre, et al.
Published: (2025)

Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy
by: Ni, Minheng, et al.
Published: (2024)

Prosody for Intuitive Robotic Interface Design: It's Not What You Said, It's How You Said It
by: Sanoubari, Elaheh, et al.
Published: (2024)

Knowing What You Know Is Not Enough: Large Language Model Confidences Don't Align With Their Actions
by: Pal, Arka, et al.
Published: (2025)

When You Don't Know the Answer, Say So
Published: (2024)

The Hurts Don't Hurt Anymore
by: Miller, Betty Davis
Published: (1976)

Can AI Assistants Know What They Don't Know?
by: Cheng, Qinyuan, et al.
Published: (2024)

World Models That Know When They Don't Know - Controllable Video Generation with Calibrated Uncertainty
by: Mei, Zhiting, et al.
Published: (2025)

Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be Recovered
by: Jabbour, Jason, et al.
Published: (2025)

Safety-critical Control Under Partial Observability: Reach-Avoid POMDP meets Belief Space Control
by: Vahs, Matti, et al.
Published: (2026)

Distributionally Robust Safety Under Arbitrary Uncertainties: A Safety Filtering Approach
by: Cherenson, Daniel M., et al.
Published: (2026)

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment
by: Wu, Yilin, et al.
Published: (2025)

NeIn: Telling What You Don't Want
by: Bui, Nhat-Tan, et al.
Published: (2024)

"What Is It That You Don't Understand?" Language Games and Black Box Algorithms
by: Demichelis, Remy
Published: (2026)

Four Librarians of the Apocalypse; Or, What Part of the Paradigm Don't You Understand?
by: Schneider, Karen G.
Published: (1994)

From Words to Safety: Language-Conditioned Safety Filtering for Robot Navigation
by: Feng, Zeyuan, et al.
Published: (2025)

What Models Know, How Well They Know It: Knowledge-Weighted Fine-Tuning for Learning When to Say "I Don't Know"
by: Lee, Joosung, et al.
Published: (2026)