Distributed Multi-robot Online Sampling with Budget Constraints
Azin Shamshirgaran, Sandeep Manjanna, Stefano Carpin
TL;DR
The paper tackles budget-constrained, multi-robot informative path planning (IPP) for reconstructing a spatial field using Gaussian Process regression. It introduces RMCTS, an online, distributed Monte Carlo Tree Search framework where robots share visited locations, use GP-based uncertainty to guide resampling, and optimize next sampling actions within per-robot budgets. A reward $r_g^{R_i} = \frac{\sigma_g^2}{d(s_g, s_s^{R_i})}$ and a stochastic energy cost $c_s^g = \alpha d(s_s^{R_i}, s_g) + U(\Lambda)$ drive planning, while an online resampling step updates the candidate location set. Empirical results on synthetic and vineyard datasets show RMCTS achieves lower reconstruction error than baselines when budgets are tight, and does so with substantially lower planning times, highlighting its practical utility for precision agriculture and similar domains.
Abstract
In multi-robot informative path planning the problem is to find a route for each robot in a team to visit a set of locations that can provide the most useful data to reconstruct an unknown scalar field. In the budgeted version, each robot is subject to a travel budget limiting the distance it can travel. Our interest in this problem is motivated by applications in precision agriculture, where robots are used to collect measurements to estimate domain-relevant scalar parameters such as soil moisture or nitrates concentrations. In this paper, we propose an online, distributed multi-robot sampling algorithm based on Monte Carlo Tree Search (MCTS) where each robot iteratively selects the next sampling location through communication with other robots and considering its remaining budget. We evaluate our proposed method for varying team sizes and in different environments, and we compare our solution with four different baseline methods. Our experiments show that our solution outperforms the baselines when the budget is tight by collecting measurements leading to smaller reconstruction errors.