arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.12346cs.RO
收藏

Schur-MI:用于机器人信息收集的快速互信息

Schur-MI: Fast Mutual Information for Robotic Information Gathering

Texas A&M University(德克萨斯农工大学);University of North Carolina at Charlotte(北卡罗来纳大学夏洛特分校)

Kalvik Jakkala, Jason O'Kane, Srinivas Akella

AI总结:

提出Schur-MI,利用迭代结构和Schur补分解将互信息计算复杂度从O(|V|^3)降至O(|A|^3),在真实测深数据集上实现最高12.7倍加速,并成功用于自主水面车辆的在线路径规划。

摘要:

互信息(MI)是机器人信息收集(RIG)中一种原则性强且广泛使用的目标函数,为传感器放置(SP)和信息路径规划(IPP)提供了强大的理论保证。然而,其高计算成本——主要由重复的对数行列式计算主导——限制了其在实时规划中的应用。本文提出了Schur-MI,一种高斯过程(GP)MI公式,它(i)利用RIG的迭代结构,在规划步骤之间预计算并重用昂贵的中间量,以及(ii)使用Schur补分解避免大型行列式计算。这些方法共同将MI的每次评估成本从$\mathcal{O}(|\mathcal{V}|^3)$降低到$\mathcal{O}(|\mathcal{A}|^3)$,其中$\mathcal{V}$和$\mathcal{A}$分别表示候选和选定的感知位置。在真实测深数据集上的实验表明,Schur-MI相比标准MI公式实现了高达12.7倍的加速。使用自主水面车辆(ASV)执行自适应IPP的现场试验进一步证明了该方法的实用性。通过使MI计算适用于在线规划,Schur-MI有助于弥合信息论目标与实时机器人探索之间的差距。我们的代码可在以下网址获取:this http URL

英文摘要:

Mutual information (MI) is a principled and widely used objective for robotic information gathering (RIG), providing strong theoretical guarantees for sensor placement (SP) and informative path planning (IPP). However, its high computational cost - dominated by repeated log-determinant evaluations - has limited its use in real-time planning. This paper presents Schur-MI, a Gaussian process (GP) MI formulation that (i) leverages the iterative structure of RIG to precompute and reuse expensive intermediate quantities across planning steps, and (ii) uses a Schur-complement factorization to avoid large determinant computations. Together, these methods reduce the per-evaluation cost of MI from $\mathcal{O}(|\mathcal{V}|^3)$ to $\mathcal{O}(|\mathcal{A}|^3)$, where $\mathcal{V}$ and $\mathcal{A}$ denote the candidate and selected sensing locations, respectively. Experiments on real-world bathymetry datasets show that Schur-MI achieves up to a $12.7\times$ speedup over the standard MI formulation. Field trials with an autonomous surface vehicle (ASV) performing adaptive IPP further demonstrate the method's practicality. By making MI computation tractable for online planning, Schur-MI helps bridge the gap between information-theoretic objectives and real-time robotic exploration. Our code is available at: www.sgp-tools.com

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑