analiza aiqbench
This paper addresses a real safety gap: an LLM-driven excavator can produce motion that is physically feasible but no longer matches what the operator approved. The proposed fix is a one-use authorization lease checked at dispatch, plus supervised stopping when authority is revoked. Its evaluation is mostly simulation-based, with only two LLM planners, so readers should treat the safety numbers as preliminary until tested on hardware.
From LLM Plans to Authorized Motion: Execution-Bound Authorization for Excavators
arXiv:2610.14245v1 Announce Type: new 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$^3$; 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.
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$^3$; 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.
Robotics (cs.RO)
arXiv:2610.14245 [cs.RO]
(or arXiv:2610.14245v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.14245 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 258 cuvinte
Subiecte conexe

Agent identity architectures: Delegated, bounded, and autonomous
1Password · 26 iun. 2026

[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · 13 oct. 2026

Generate Trajectories, Reasoning Traces, and Auto-Labels with NVIDIA Alpamayo 2 Super
NVIDIA · 4 aug. 2026
Constant-Time Planning for Chaining Collision-free Motion to Manipulation Behaviors
arXiv · 2 oct. 2026