Multi-Agent Next-Best-View Optimization for Risk-Averse Planning

2026-06-02

AI Summary

This work addresses the challenge of multi-agent cooperative safe exploration in unknown environments, where agents must balance information gain, risk avoidance, and communication efficiency. Existing centralized approaches suffer from poor scalability and high communication overhead. To overcome these limitations, the authors propose a distributed risk-aware Next-Best-View (NBV) framework in which each agent maintains a private 3D Gaussian Splatting (3DGS) map. The method uniquely integrates Average Value-at-Risk (AV@R) into viewpoint selection and trajectory scoring, and employs consensus ADMM to collaboratively optimize Expected Information Gain (EIG) under trajectory mask constraints, exchanging only candidate viewpoints, trajectory descriptors, and scalar gains. Experiments in Gibson environments demonstrate that the approach achieves map quality and trajectory safety comparable to centralized baselines while reducing communication overhead by several orders of magnitude, substantially improving system scalability.

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.

Problem

• Multi-Agent
• Next-Best-View
• Risk-Averse Planning
• Safe Path Planning
• Scalability

Innovation

• distributed multi-agent planning
• risk-aware NBV
• 3D Gaussian Splatting
• Consensus ADMM
• Average Value-at-Risk