Multi-Agent Next-Best-View Optimization for Risk-Averse Planning
2026-06-02 • Robotics
Robotics
AI summaryⓘ
The authors created a way for multiple robots to safely explore unknown places by planning their viewing angles together without sharing all their sensor data. Each robot keeps its own local 3D map and they work as a team to choose the best new viewpoints that provide the most useful information while avoiding risky paths. They use a method called Consensus ADMM to agree on these plans by only sharing small bits of information like possible viewpoints and scores. Their tests show this method nearly matches centralized approaches in mapping and safety but needs much less communication between robots.
Multi-agent systemsNext-Best-View (NBV)Safe path planning3D Gaussian SplattingExpected Information Gain (EIG)Consensus ADMMAverage Value-at-Risk (AV@R)Distributed algorithmsGibson environment
Authors
Amirhossein Mollaei Khass, Vivek Pandey, Guangyi Liu, Athanasios Cosse, Emrah Bayrak, Nader Motee
Abstract
Multi-agent Next-Best-View (NBV) selection for safe path planning in uncertain and unknown environments requires informative, safety-aware, and efficient coordination. Centralized approaches rely on sharing raw sensor data or significant communication overhead, resulting in limited scalability. We propose a distributed, risk-aware multi-agent NBV framework in which each robot maintains a private local 3D Gaussian Splatting map and the team jointly maximizes expected information gain (EIG) restricted to masked zones along planned trajectories. The resulting distributed objective is solved by Consensus ADMM (C-ADMM) over a communication graph, with each robot exchanging only candidate viewpoints, planned trajectory descriptors, and scalar EIG contributions. Collision risk along each trajectory is modeled via Average Value-at-Risk (AV@R) over the local 3DGS map and used both to shape the masking radius and to score planned paths. Experiments in Gibson environments at multiple team sizes show that the distributed formulation approaches the centralized baseline in mapping quality and trajectory safety while reducing communication by orders of magnitude.