REVIEW 7 cited by
SafePlan: Leveraging Formal Logic and Chain-of-Thought Reasoning for Enhanced Safety in LLM-based Robotic Task Planning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
SafePlan: Leveraging Formal Logic and Chain-of-Thought Reasoning for Enhanced Safety in LLM-based Robotic Task Planning
read the original abstract
Robotics researchers increasingly leverage large language models (LLM) in robotics systems, using them as interfaces to receive task commands, generate task plans, form team coalitions, and allocate tasks among multi-robot and human agents. However, despite their benefits, the growing adoption of LLM in robotics has raised several safety concerns, particularly regarding executing malicious or unsafe natural language prompts. In addition, ensuring that task plans, team formation, and task allocation outputs from LLMs are adequately examined, refined, or rejected is crucial for maintaining system integrity. In this paper, we introduce SafePlan, a multi-component framework that combines formal logic and chain-of-thought reasoners for enhancing the safety of LLM-based robotics systems. Using the components of SafePlan, including Prompt Sanity COT Reasoner and Invariant, Precondition, and Postcondition COT reasoners, we examined the safety of natural language task prompts, task plans, and task allocation outputs generated by LLM-based robotic systems as means of investigating and enhancing system safety profile. Our results show that SafePlan outperforms baseline models by leading to 90.5% reduction in harmful task prompt acceptance while still maintaining reasonable acceptance of safe tasks.
Forward citations
Cited by 7 Pith papers
-
When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space
Content danger and physical danger form separable hidden-state signals in LLMs, and a single-layer logistic probe (PRISM) detects both at lower false-positive rates than LLM judges or text guardrails.
-
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
The survey organizes over 400 papers on embodied AI safety into a multi-level taxonomy and flags overlooked issues such as fragile multimodal fusion and unstable planning under jailbreaks.
-
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
A multi-level taxonomy of risks, attacks, and defenses across the full embodied AI pipeline, synthesizing 500+ papers and flagging overlooked failure modes.
-
Pre-Execution Safety Gate & Task Safety Contracts for LLM-Controlled Robot Systems
SafeGate adds a deterministic pre-execution gate and runtime contracts with Z3 SMT solving to block unsafe LLM commands for robots while passing safe ones.
-
A Hierarchical Error-Corrective Graph Framework for Autonomous Agents with LLM-Based Action Generation
HECG combines multi-dimensional metrics for strategy choice, ten-type error classification with recoverability details, and causal-context graphs to improve LLM agent reliability in complex tasks.
-
ConceptBot: Enhancing Robot's Autonomy through Task Decomposition with Large Language Models and Knowledge Graph
Using ConceptNet-augmented prompts, ConceptBot reports 87% vs 31% success on implicit tasks and 76% vs 15% on risk-aware tasks over a re-implemented SayCan baseline, with an 80% SafeAgentBench score.
-
LLM-Assisted Tool for Joint Generation of Formulas and Functions in Rule-Based Verification of Map Transformations
LLM-assisted pipeline jointly generates logical formulas and executable predicates for rule-based verification of HD map transformations in CommonRoad, evaluated on synthetic bridge and slope scenarios.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.