发表机构
Voryx Robotics LLC（Voryx机器人公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出物理人机交互的行为-实现分离框架，采用后退时域二次规划方法，在 Franka FR3 机器人实验中验证其可显著降低超调、提升力矩约束执行的可行性，证明了该分离策略的有效性。
AI 中文摘要
物理人机交互软件常将期望行为规范与受限实现耦合在一起，本文将二者视为分离的两层。行为层提供期望的接触端口加速度 $a_k^{\mathrm{id}}=f_\theta(e_k,\dot e_k,F_{h,k})$；实现层将其转换为受限机器人指令，并报告总期望与实际加速度的误差，而非将其隐藏在饱和处理中。针对相同目标的无约束反事实方法将正则化与约束干预分离，同时被控对象数据可揭示模型误差。本文实现了一种后退时域二次规划方法，用于实现无记忆仿射行为；修改行为时，通过 $(C_\theta,G_\theta)$ 调整目标系数，而机器人指令变量与可行集保持不变。平面研究实例化了阻抗与导纳，同一运行层可在现有速率限制下接受阻抗-导纳-阻抗的重新分配，无需重构。在 MuJoCo 中基于力矩控制的 7 自由度 Franka FR3 机器人上，该方法每次求解冻结任务空间动力学，并在整个时域内执行力矩可行性约束；在持续 20 N 的推力下，其将松弛的工作空间边界保持在约 0.1-0.2 mm 以内，而瞬时限幅的阻抗与导纳方法分别存在 4.4 cm 和 4.7 cm 的超调。随后，降低的执行器预算激活力矩约束：全时域执行使冻结模型计划的可行性达到 $2.1\times10^{-4}\\ \mathrm{N}\cdot\mathrm{m}$，而仅第一步的 ablation 计划超出预算达 11.329 N·m；在执行的非线性被控对象上，二者局部模型误差相同，可行性差距缩小，但全时域执行仍更优（0.161 对比 0.380 N·m）。这些结果是行为-实现分离的针对性验证。
英文摘要
Physical human--robot interaction software often couples desired-behavior specification with constrained realization; we treat these as separate layers. A \emph{behavior layer} supplies a desired contact-port acceleration $a_k^{\mathrm{id}}=f_θ(e_k,\dot e_k,F_{h,k})$. A \emph{realization layer} converts it into constrained robot commands and reports total desired-versus-realized acceleration error instead of hiding it in saturation. A same-objective unconstrained counterfactual separates regularization from constraint intervention, while plant data expose model error. This paper implements a receding-horizon quadratic program realizing memoryless affine behaviors. Changing the behavior modifies objective coefficients through $(C_θ,G_θ)$ while the robot-command variable and feasible set remain unchanged. A planar study instantiates impedance and admittance; the same running layer accepts an impedance--admittance--impedance reassignment without reconstruction, under its existing rate limit. On a torque-controlled 7-DOF Franka FR3 in MuJoCo, the runtime freezes task-space dynamics per solve and enforces torque feasibility across its horizon. Under a sustained 20~N push, it holds a slack-relaxed workspace boundary to within approximately 0.1--0.2~mm, versus 4.4~cm (impedance) and 4.7~cm (admittance) overshoot from instantaneous clipping. A derated actuator budget then activates the torque constraint: horizon-wide enforcement keeps its frozen-model plan feasible to $2.1\times10^{-4}$~N$\cdot$m, whereas a first-step-only ablation plans up to 11.329~N$\cdot$m beyond budget; on the executed nonlinear plant, where both share the same local-model error, the gap is smaller but still favors horizon-wide enforcement (0.161 vs.\ 0.380~N$\cdot$m). These results are a focused proof of behavior--realization separation.
