Active Next-Best-View Optimization for Risk-Averse Path Planning
By: Amirhossein Mollaei Khass , Guangyi Liu , Vivek Pandey and more
Potential Business Impact:
Helps robots safely navigate unknown places.
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.
Similar Papers
Near-optimal Active Reconstruction
Machine Learning (CS)
Helps robots see objects better and safer.
PB-NBV: Efficient Projection-Based Next-Best-View Planning Framework for Reconstruction of Unknown Objects
Robotics
Builds 3D models of things faster.
Quality-guided UAV Surface Exploration for 3D Reconstruction
Robotics
Drones build better 3D maps of new places.