ForesightSafety-VLA creates a diagnostic benchmark for VLA safety with taxonomy across physical, language, and visual risks, showing perception and structure variations cause more safety degradation than language changes in tested models.
Generating robot constitutions & benchmarks for semantic safety
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
LLM planners for robots often produce dangerous plans even when planning succeeds, with safety awareness staying flat as model scale improves planning ability.
SafeDec uses constrained decoding to ensure autoregressive robot navigation foundation models generate actions that provably satisfy STL safety specifications under assumed dynamics.
SafetyALFRED shows multimodal LLMs recognize kitchen hazards accurately in QA tests but achieve low success rates when required to mitigate those hazards through embodied planning.
Control-theoretic guardrails enable proactive correction of risky LLM agent actions in latent space, preventing catastrophes like collisions or bankruptcy while preserving task performance in simulated environments.
REBAR is a new test framework that turns ethical scenario difficulty into computable Autonomy Readiness Level scores using LLM-based analysis and simulation for autonomous systems.
Embodied reward models systematically over-reward unsafe, suboptimal, and shortcut robot behaviors due to training on successful data only, and modest inclusion of bad behavior data improves alignment with human preferences.
A literature survey that unifies fragmented work on attacks, defenses, evaluations, and deployment challenges for Vision-Language-Action models in robotics.
The paper proposes a paradigm of provable probabilistic safety to enable scalable, safe deployment of embodied AI in critical applications.
citing papers explorer
-
ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models
ForesightSafety-VLA creates a diagnostic benchmark for VLA safety with taxonomy across physical, language, and visual risks, showing perception and structure variations cause more safety degradation than language changes in tested models.
-
Using large language models for embodied planning introduces systematic safety risks
LLM planners for robots often produce dangerous plans even when planning succeeds, with safety awareness staying flat as model scale improves planning ability.
-
Constrained Decoding for Safe Robot Navigation Foundation Models
SafeDec uses constrained decoding to ensure autoregressive robot navigation foundation models generate actions that provably satisfy STL safety specifications under assumed dynamics.
-
SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
SafetyALFRED shows multimodal LLMs recognize kitchen hazards accurately in QA tests but achieve low success rates when required to mitigate those hazards through embodied planning.
-
From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails
Control-theoretic guardrails enable proactive correction of risky LLM agent actions in latent space, preventing catastrophes like collisions or bankruptcy while preserving task performance in simulated environments.
-
REBAR: Reference Ethical Benchmark for Autonomy Readiness
REBAR is a new test framework that turns ethical scenario difficulty into computable Autonomy Readiness Level scores using LLM-based analysis and simulation for autonomous systems.
-
Position: Good Embodied Reward Models Need Bad Behavior Data
Embodied reward models systematically over-reward unsafe, suboptimal, and shortcut robot behaviors due to training on successful data only, and modest inclusion of bad behavior data improves alignment with human preferences.
-
Towards provable probabilistic safety for scalable embodied AI systems
The paper proposes a paradigm of provable probabilistic safety to enable scalable, safe deployment of embodied AI in critical applications.