Distributed Optimization with Consensus Constraint for Multi-Robot Semantic Octree Mapping

TL;DR

This paper presents a distributed optimization algorithm for multi-robot 3D semantic mapping that uses consensus constraints and octree data structures to efficiently build a shared environment map with minimal communication.

Contribution

It introduces a gradient-based distributed optimization method with a consensus constraint for multi-robot semantic mapping, utilizing adaptive octree compression for efficient communication.

Findings

Closed-form updates similar to Bayes rule with prior averaging

Efficient map sharing using adaptive octree compression

Effective multi-robot semantic mapping with limited communication

Abstract

This work develops a distributed optimization algorithm for multi-robot 3-D semantic mapping using streaming range and visual observations and single-hop communication. Our approach relies on gradient-based optimization of the observation log-likelihood of each robot subject to a map consensus constraint to build a common multi-class map of the environment. This formulation leads to closed-form updates which resemble Bayes rule with one-hop prior averaging. To reduce the amount of information exchanged among the robots, we utilize an octree data structure that compresses the multi-class map distribution using adaptive-resolution.