Informative Planning for Worst-Case Error Minimisation in Sparse Gaussian Process Regression
This work addresses error minimization in sparse Gaussian process regression for applications like robotics or sensor networks, but it is incremental as it builds on existing sparse GP and planning methods.
The authors tackled the problem of minimizing deterministic worst-case error in sparse Gaussian process regression by developing a planning framework that converts error minimization into a posterior entropy minimization problem, solved with a Gaussian belief space algorithm; their results showed this approach effectively reduces error and outperforms conventional methods when inducing points are fixed.
We present a planning framework for minimising the deterministic worst-case error in sparse Gaussian process (GP) regression. We first derive a universal worst-case error bound for sparse GP regression with bounded noise using interpolation theory on reproducing kernel Hilbert spaces (RKHSs). By exploiting the conditional independence (CI) assumption central to sparse GP regression, we show that the worst-case error minimisation can be achieved by solving a posterior entropy minimisation problem. In turn, the posterior entropy minimisation problem is solved using a Gaussian belief space planning algorithm. We corroborate the proposed worst-case error bound in a simple 1D example, and test the planning framework in simulation for a 2D vehicle in a complex flow field. Our results demonstrate that the proposed posterior entropy minimisation approach is effective in minimising deterministic error, and outperforms the conventional measurement entropy maximisation formulation when the inducing points are fixed.