TY - JOUR
T1 - Point-wise Fusion of Distributed Gaussian Process Experts (FuDGE) using a fully decentralized robot team operating in communication-devoid environment
AU - Tiwari, Kshitij
AU - Jeong, Sungmoon
AU - Chong, Nak Young
N1 - Publisher Copyright:
© 2004-2012 IEEE.
PY - 2018/6
Y1 - 2018/6
N2 - In this paper, we focus on large-scale environment monitoring by utilizing a fully decentralized team of mobile robots. The robots utilize the resource constrained-decentralized active sensing scheme to select the most informative (uncertain) locations to observe while conserving allocated resources (battery, travel distance, etc.). We utilize a distributed Gaussian process (GP) framework to split the computational load over our fleet of robots. Since each robot is individually generating a model of the environment, there may be conflicting predictions for test locations. Thus, in this paper, we propose an algorithm for aggregating individual prediction models into a single globally consistent model that can be used to infer the overall spatial dynamics of the environment. To make a prediction at a previously unobserved location, we propose a novel gating network for a mixture-of-experts model wherein the weight of an expert is determined by the responsibility of the expert over the unvisited location. The benefit of posing our problem as a centralized fusion with a distributed GP computation approach is that the robots never communicate with each other, individually optimize their own GP models based on their respective observations, and off-load all their learnt models on the base station only at the end of their respective mission times. We demonstrate the effectiveness of our approach using publicly available datasets.
AB - In this paper, we focus on large-scale environment monitoring by utilizing a fully decentralized team of mobile robots. The robots utilize the resource constrained-decentralized active sensing scheme to select the most informative (uncertain) locations to observe while conserving allocated resources (battery, travel distance, etc.). We utilize a distributed Gaussian process (GP) framework to split the computational load over our fleet of robots. Since each robot is individually generating a model of the environment, there may be conflicting predictions for test locations. Thus, in this paper, we propose an algorithm for aggregating individual prediction models into a single globally consistent model that can be used to infer the overall spatial dynamics of the environment. To make a prediction at a previously unobserved location, we propose a novel gating network for a mixture-of-experts model wherein the weight of an expert is determined by the responsibility of the expert over the unvisited location. The benefit of posing our problem as a centralized fusion with a distributed GP computation approach is that the robots never communicate with each other, individually optimize their own GP models based on their respective observations, and off-load all their learnt models on the base station only at the end of their respective mission times. We demonstrate the effectiveness of our approach using publicly available datasets.
KW - Distributed robot systems
KW - field robots
KW - model fusion
KW - path planning for multiple mobile robot systems
KW - surveillance systems
UR - http://www.scopus.com/inward/record.url?scp=85042861550&partnerID=8YFLogxK
U2 - 10.1109/TRO.2018.2794535
DO - 10.1109/TRO.2018.2794535
M3 - Article
AN - SCOPUS:85042861550
SN - 1552-3098
VL - 34
SP - 820
EP - 828
JO - IEEE Transactions on Robotics
JF - IEEE Transactions on Robotics
IS - 3
ER -