跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.11580 · v1

Qubit-to-Motion: Traceable Action Provenance in Hybrid QRL for Robotic Bin-Packing Sequencing

首次提交 2026-11-09 03:52
版本更新 2026-11-09 03:52
雷达观测 2026-11-10 13:19
arXiv ↗PDF ↗

摘要

Hybrid quantum reinforcement learning has been explored for robotic decision-making, but evaluations often emphasize task success, return, or convergence, leaving unresolved whether quantum circuit outputs influence constrained actions and remain traceable through robot execution. We present \texttt{Qubit-to-Motion}, an evidence-centered framework for support-constrained sequencing and simulated robotic placement. Four Pauli-ZZ readouts provide the sole learned input to the actor and critic, while a support mask enforces admissible object selection. Each decision is recorded and linked via step indices and SHA-256 fingerprints to a sealed route, deterministic Cartesian and inverse-kinematics waypoints, prescribed joint motion, and MuJoCo contact replay. A frozen checkpoint is evaluated across five deterministic 30-object scene variants. All 150 placements satisfy support, containment, and settling criteria. A fixed-state zero-readout intervention changes 90.0±0.0%90.0\pm0.0\% of decisions, demonstrating dependence on the joint circuit representation. Mean macro travel is 34.537±0.20634.537\pm0.206~m, inference requires 8.60±1.278.60\pm1.27~ms per route, and replay achieves 8.764±0.220 μ8.764\pm0.220~μm mean final position error with 0.356~mm maximum interpenetration. These results establish reproducible decision-to-contact traceability. The implementation is available at \href{https://anonymous.4open.science/r/Qubit-to-Motion-Quantum-Reinforcement-Learning-F7DC}{\textcolor{linkpink}{the anonymous repository}}.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-09 03:52 · 最新观测版本

Qubit-to-Motion: Traceable Action Provenance in Hybrid QRL for Robotic Bin-Packing Sequencing

Hybrid quantum reinforcement learning has been explored for robotic decision-making, but evaluations often emphasize task success, return, or convergence, leaving unresolved whether quantum circuit outputs influence constrained actions and remain traceable through robot execution. We present \texttt{Qubit-to-Motion}, an evidence-centered framework for support-constrained sequencing and simulated robotic placement. Four Pauli-ZZ readouts provide the sole learned input to the actor and critic, while a support mask enforces admissible object selection. Each decision is recorded and linked via step indices and SHA-256 fingerprints to a sealed route, deterministic Cartesian and inverse-kinematics waypoints, prescribed joint motion, and MuJoCo contact replay. A frozen checkpoint is evaluated across five deterministic 30-object scene variants. All 150 placements satisfy support, containment, and settling criteria. A fixed-state zero-readout intervention changes 90.0±0.0%90.0\pm0.0\% of decisions, demonstrating dependence on the joint circuit representation. Mean macro travel is 34.537±0.20634.537\pm0.206~m, inference requires 8.60±1.278.60\pm1.27~ms per route, and replay achieves 8.764±0.220 μ8.764\pm0.220~μm mean final position error with 0.356~mm maximum interpenetration. These results establish reproducible decision-to-contact traceability. The implementation is available at \href{https://anonymous.4open.science/r/Qubit-to-Motion-Quantum-Reinforcement-Learning-F7DC}{\textcolor{linkpink}{the anonymous repository}}.

查看此版本解读 →查看此版本原文 ↗