Active Next-Best-View Optimization for Risk-Averse Path Planning
This addresses the problem of risk-averse path planning for autonomous systems in uncertain environments, representing an incremental advance by coupling existing concepts with scalable implementations.
The paper tackles safe navigation in uncertain environments by developing a unified framework that refines coarse reference paths using tail-sensitive risk maps from Average Value-at-Risk statistics and optimizes Next-Best-View selection to reduce critical uncertainty, demonstrating effectiveness through extensive computational studies.
Safe navigation in uncertain environments requires planning methods that integrate risk aversion with active perception. In this work, we present a unified framework that refines a coarse reference path by constructing tail-sensitive risk maps from Average Value-at-Risk statistics on an online-updated 3D Gaussian-splat Radiance Field. These maps enable the generation of locally safe and feasible trajectories. In parallel, we formulate Next-Best-View (NBV) selection as an optimization problem on the SE(3) pose manifold, where Riemannian gradient descent maximizes an expected information gain objective to reduce uncertainty most critical for imminent motion. Our approach advances the state-of-the-art by coupling risk-averse path refinement with NBV planning, while introducing scalable gradient decompositions that support efficient online updates in complex environments. We demonstrate the effectiveness of the proposed framework through extensive computational studies.