Maintaining Communication in Multi-Robot Tree Coverage

Authors: Mor Sinay, Noa Agmon, Oleg Maksimov, Sarit Kraus, David Peleg

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We enhance the theoretically-proven solution with a dripping heuristic algorithm, and show in extensive simulations that it significantly decreases the coverage time. The algorithm is then adjusted to general (not necessarily perfect) N-ary trees and additional experiments prove its efficiency. Furthermore, we show the use of our solution in a simulated officebuilding scenario. Finally, we deploy our algorithm on real robots in a real office building setting, showing efficient coverage time in practice.
Researcher Affiliation Academia 1Bar-Ilan University, Israel 2 The Weizmann Institute, Israel
Pseudocode Yes Algorithm 1 NCOCTA; Algorithm 2 COCTA
Open Source Code No The paper mentions implementing solutions on ROS/Gazebo, but does not provide a link or statement about releasing their specific implementation code.
Open Datasets No The paper uses simulations and real-world deployments in custom environments (N-ary trees, simulated office building) rather than named public datasets with concrete access information.
Dataset Splits No The paper describes experiments on simulated and real-world environments but does not specify training, validation, or test dataset splits.
Hardware Specification No The paper mentions using 'Hamster robots' for real-world deployment but does not provide specific hardware specifications like GPU/CPU models or memory details for these robots or for the simulation environment.
Software Dependencies Yes We have implemented our solutions on ROS/Gazebo 1.
Experiment Setup Yes Simulation of NCOCTA algorithm on a perfect 2-ary tree when k = 11, H = 3 and h = {3, 2}. ... SF vs number of robots on a perfect 2-ary tree (H=15), 3-ary tree (H=8), 4-ary tree (H=8). ... SF on a perfect 2-ary tree using 60 robots with different tree heights. ... In order to create these imperfect trees, we defined a number of nodes to remove from the tree, and removed them from a predefined height (and all its subtrees) at random.