Communication- and Computation-Efficient Distributed Submodular Optimization in Robot Mesh Networks
Zirui Xu, Sandilya Sai Garimella, Vasileios Tzoumas
TL;DR
This work tackles scalable, near-optimal distributed submodular optimization in robot mesh networks under realistic communication constraints. It introduces Resource-Aware distributed Greedy (RAG), which limits coordination to neighbor information and achieves $O(|\mathcal{N}|)$ decision-time scaling, a major improvement over cubically scaling baselines. The authors provide a priori and a posteriori guarantees that connect neighborhood topology and decentralization metrics (coin_f,i and $\kappa_f$) to performance, with bounds that tighten as networks become more centralized. They extend AirSim to simulate realistic r2r delays and demonstrate real-time planning with up to 45 robots and up to 3 orders of magnitude speedups while achieving superior mean road-coverage, validating both theory and practical impact. The work includes an open-source AirSim-based simulator and establishes a general framework for resource-aware distributed optimization applicable across robotics, control, and ML tasks.
Abstract
We provide a communication- and computation-efficient method for distributed submodular optimization in robot mesh networks. Submodularity is a property of diminishing returns that arises in active information gathering such as mapping, surveillance, and target tracking. Our method, Resource-Aware distributed Greedy (RAG), introduces a new distributed optimization paradigm that enables scalable and near-optimal action coordination. To this end, RAG requires each robot to make decisions based only on information received from and about their neighbors. In contrast, the current paradigms allow the relay of information about all robots across the network. As a result, RAG's decision-time scales linearly with the network size, while state-of-the-art near-optimal submodular optimization algorithms scale cubically. We also characterize how the designed mesh-network topology affects RAG's approximation performance. Our analysis implies that sparser networks favor scalability without proportionally compromising approximation performance: while RAG's decision time scales linearly with network size, the gain in approximation performance scales sublinearly. We demonstrate RAG's performance in simulated scenarios of area detection with up to 45 robots, simulating realistic robot-to-robot (r2r) communication speeds such as the 0.25 Mbps speed of the Digi XBee 3 Zigbee 3.0. In the simulations, RAG enables real-time planning, up to three orders of magnitude faster than competitive near-optimal algorithms, while also achieving superior mean coverage performance. To enable the simulations, we extend the high-fidelity and photo-realistic simulator AirSim by integrating a scalable collaborative autonomy pipeline to tens of robots and simulating r2r communication delays. Our code is available at https://github.com/UM-iRaL/Resource-Aware-Coordination-AirSim.