SparseMax-dSTL: Sound Robustness with Horizon-Independent Gradient Allocation for Temporal Logic Trajectory Optimization
作者: Sai Sandeep Damera, Ryan Matheu, John S. Baras, Calin Belta
分类: eess.SY, cs.LO, cs.RO
发布日期: 2026-10-16
备注: 8 pages, 5 figures. This work has been submitted to the IEEE for possible publication
💡 一句话要点
提出SparseMax-dSTL以解决STL轨迹优化中的鲁棒性问题
🎯 匹配领域: 支柱一:机器人控制 (Robot Control)
关键词: 信号时序逻辑 轨迹优化 稀疏最大投影 鲁棒性 安全关键系统
📋 核心要点
- 现有的STL轨迹优化方法在鲁棒性和梯度分配上存在不足,无法同时满足健全性和长时间地平线的要求。
- 本文提出了一种新的鲁棒性近似方法,利用稀疏最大投影来确保在违反样本上的梯度权重保持正下界。
- 实验表明,稀疏最大方法在长时间地平线下仍能保持较高的梯度权重,优于传统的log-sum-exp近似。
📝 摘要(中文)
本文提出了一种基于梯度的求解器,利用平滑的量化语义近似来强制执行信号时序逻辑(STL)规范。在安全关键的轨迹优化中,该近似必须具备两个特性:一是健全性,即仅在满足规范的轨迹上非负;二是在每个时态运算符上,违反样本的梯度权重必须保持正下界。现有的近似方法如log-sum-exp及其健全变体未能同时满足这两个条件。我们引入了最小值和最大值的下界近似,其梯度为稀疏最大投影,并证明基于这些近似构建的鲁棒性同时具备健全性和独立于样本数量的误差界限。实验结果表明,稀疏最大方法在违反样本上的权重始终保持正下界,优于现有方法。
🔬 方法详解
问题定义:本文旨在解决在信号时序逻辑(STL)轨迹优化中,现有方法在鲁棒性和梯度分配上的不足,特别是在长时间地平线下的表现不佳。
核心思路:提出了一种基于稀疏最大投影的鲁棒性近似方法,确保在违反样本上的梯度权重保持正下界,从而提高轨迹优化的健全性和有效性。
技术框架:整体架构包括鲁棒性近似的构建、梯度计算和优化过程。主要模块包括信号时序逻辑规范的解析、稀疏最大投影的实现以及优化算法的设计。
关键创新:最重要的技术创新在于引入了基于稀疏最大投影的下界近似,确保了鲁棒性近似的健全性,并且在长时间地平线下保持了梯度权重的正下界。
关键设计:在参数设置上,设计了适应性阈值以决定梯度为零的样本,损失函数采用了鲁棒性近似的形式,确保优化过程中的稳定性和收敛性。实验中使用了平面单轮车和七关节机械臂的仿真环境进行验证。
🖼️ 关键图片
📊 实验亮点
实验结果显示,在长时间地平线下,稀疏最大方法在违反样本上的梯度权重保持在1,而log-sum-exp方法的权重从0.22降至0.04。通过约束稀疏最大鲁棒性,成功返回满足规范的轨迹,显示出显著的性能提升。
🎯 应用场景
该研究的潜在应用领域包括自动驾驶、机器人路径规划和其他安全关键的控制系统。通过提高轨迹优化的鲁棒性和健全性,能够更好地满足复杂环境下的安全性要求,具有重要的实际价值和未来影响。
📄 摘要(原文)
A gradient-based solver that enforces a Signal Temporal Logic (STL) specification uses a smooth approximation of its quantitative semantics, the robustness. In safety-critical trajectory optimization, this approximation must have two properties. First, it must be sound, that is, nonnegative only on trajectories that satisfy the specification. Second, at each temporal operator, the weight of its gradient on the violating samples must stay bounded away from zero, however long the horizon. The approximations in use, including the log-sum-exp, its sound variant, and the generalized-mean robustness, do not have both. We introduce lower approximations of the minimum and the maximum whose gradients are sparsemax projections, and we prove that the robustness built from them has both. It lies below the exact robustness and is therefore sound, and its error has a bound that is independent of the number of samples and known before optimization. The gradient of each approximation is exactly zero on every sample beyond a data-dependent threshold, so the weight on violating samples a gap beyond the others has a positive lower bound at every horizon. On a planar unicycle and on a seven-joint manipulator beside a person in simulation, the log-sum-exp approximation is positive on a violating trajectory. As the horizon of the manipulator's task grows from 10 to 80 s, the gradient weight of the sound variant on the violating samples falls from 0.22 to 0.04, while that of sparsemax stays at 1. In a constrained trajectory optimization of the unicycle, the constraint on the log-sum-exp robustness returns a violating trajectory, whereas the constraint on the sparsemax robustness returns a trajectory that satisfies the specification with the required margin.