From LLM Plans to Authorized Motion: Execution-Bound Authorization for Excavators
cs.RO
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/Mehdi-Heydari-Shahna/ExecutionBound
License: http://creativecommons.org/licenses/by/4.0/
The gist: An LLM-directed excavator can execute mechanically feasible motion whose destination or authority no longer matches the operator's approval.
Abstract
An LLM-directed excavator can execute mechanically feasible motion whose destination or authority no longer matches the operator's approval. We propose execution-bound authorization for the approval--dispatch--execution interval. A one-use lease binds the action, generated motion, mission contract and admission tolerance; atomic dispatch rechecks current authority and measured joint drift. Periodic supervision detects revocation and requests a quintic stop with a carry-pitch endpoint, selected through sampled joint, stroke, flow and reference-acceleration checks. The framework connects exact motion identity to dispatch integrity and load-aware interruption. Evaluation combines a 672-case interface suite, four loaded digging cases in synchronous simulation, unloaded MuJoCo/Pinocchio transfers and two command-level LLM planners. The gateway admitted all 120 benign interface cases and produced zero unauthorized dispatches in the attack suite. Loaded dispatch-window tests produced zero unauthorized deposition. During simulated dump-phase revocation, maximum closed-site deposition decreased from 1.23 to 0.33,m cubed; loaded-slew stops used less than 75% of nominal swing torque. These results demonstrate motion-bound authorization and quantify the retention and stopping behavior of supervised excavation skills.
Sources
- AuthGuard-R: Safety-Compliant Mission Hijacking and Dual-Gate Defense for LLM-Controlled Robots
- Defeating Prompt Injections by Design
- Progent: Securing AI Agents with Privilege Control
- RoboCompiler: Graph-Native Compilation of Closed-Chain Robots for Consistent Modeling, Control, and Simulation
- Qwen2.5 Technical Report
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies