MARS (Multiple Autonomous Robot Systems) Research Lab
A Resilient and Adaptable Cooperative Heterogeneous Foraging Robot Swarm
Javier Becerril, Arturo Gonzalez
We plan to develop a heterogeneous foraging robot swarm. It is relatively difficult for unmanned ground vehicles/robots (UGVs) to search for resources in a large environment. UAVs have better sensing and further vision that complement the ground robot swarms. Therefore, the collaboration between the UGVs and UAVs has the potential to improve the foraging performance significantly. We will demonstrate the efficient collaboration between UGVs and UAVs for completing the foraging task.
Epidemiology-Based Models for Self-Propagating Cyber Attacks and Defenses in Foraging Swarm Robotics
Ryan Luna
We will investigate the potential security problems and threats in the swarm robotic systems. We will apply the compartmental (epidemiology-based) models to study malware self-propagation in robotic swarms. The compartmental models have been widely used to analyze and forecast the Ebola virus and the spread of the Coronavirus (COVID-19) recently. There has been extensive research in customizing compartmental models to study the behavior of malware propagation in general computer networks. We believe this to be one of the first ongoing research efforts on its application towards swarm robotics. We will disclose the dynamics of malware self-propagation in swarm robotic systems and how it impacts the foraging performance of robot swarms. It will instruct administrators to take suitable security and quarantine strategies or design efficient intrusion detection systems to suppress malware propagation in swarm robotic systems.
Nanoscale Foraging and Self-Assembly Swarms
This project will explore fundamental theoretical questions in the intersection of two critical areas of swarm robotics: foraging swarms and nanoscale self-assembly robots. We propose to explore the new direction of designing foraging algorithms for nanoscale robot swarms -- an area that we have not studied yet and has important implications. We will model the concrete mathematical and computational foraging problems in nanoscale self-assembly robots. One of the challenges is the limitation of the robot size in the nanoscale. We will find the solution to the delivery of resources based on some graph theories in computational geometry.
Dynamic Robot Chain Networks
Dohee Lee, Qi Lu and Tsz-Chiu Au
We propose a novel extension to the multiple-place foraging in which multiple robot chains are deployed dynamically. Each robot chain connects a foraging location to the central collection zone. Instead of delivering resources by a single robot, resources are passed on robot chains from foraging locations to the center directly such that congestion near the central collection zone can be avoided. Dynamic robot chains can also relocate themselves to get closer to the resources while avoiding obstacles. We simulate our robot swarms in the robot simulator ARGoS. Our experiments show that robots with dynamic chains outperform our previous work in robots with dynamic depots and have less congestion.
Foraging Robot Swarms
Qi Lu, Antonio D. Griego, Takaya Tsuno, Joshua P. Hecker, G. Matthew Fricke, and Melanie E. Moses
We design algorithms for coordinating multiple robots to accomplish a task collectively. For example, foraging is the behavior of social insects (e.g., ant colonies, and honey bees) of searching for foods and transporting them to their nests. We design robots to mimic the foraging behavior for searching for certain resources (e.g., minerals, hazardous waste, and survivors) in a largely unknown area and transporting them to specific locations (e.g., warehouses, hospitals, or military bases). The foraging task is a useful abstraction of many complex, real-world applications such as humanitarian de-mining, search and rescue operations, intrusion tracking, agricultural harvesting, infrastructure inspection, and planetary exploration.
Current students:
Master's Students
Eric Rodriguez -- CS, Fall 2022
Ryan Luna -- CS, Fall 2022
Javier Becerril -- ME (Mechanical Engineering), Summer 2023
Undergraduate Students
Daniel Masamba -- CS, Summer 2023
Arturo Gonzalez -- Fall 2023
Cesia Guzman -- ME, Spring 2024
Past students:
Ph.D. students
Dohee Lee, UNIST (Ulsan National Institute of Science and Technology in Ulsan, South Korea), co-advice with Dr. Tsz-Chiu Au, 2019 - 2022.
Master's Students
Alberto Velazquez, Edgar Torres, Rodrigo Gonzalez, Mechanical Engineering, Fall 2022 - Spring 2023
Dylan Markovic, CS UTSA, Summer 2022
William Hinson, CS UTSA, Fall 2021 - Spring 2022.
Undergraduate Students
- Tristan Hernandez, Computer Engineering, Spring 2023 - Summer 2023
Diego Cantu, Mechanical Engineering, Fall 2022 - Spring 2023.
Recent Publications
Conferences:
Dohee Lee, Qi Lu, and Tsz-Chiu Au. Dynamic Robot Chain Networks for Swarm Foraging. IEEE/RSJ International Conference on Robotics and Automation (ICRA 2022), May 2022. [link].
Ning Yang, Qi Lu, Kele Xu, Zijian Gao, and Bo Ding. Multi-Actor-Attention-Critic Reinforcement Learning for Central Place Foraging Swarms. The International Joint Conference on Neural Networks (IJCNN 2021), April 2021. [link].
Dohee Lee, Qi Lu, and Tsz-Chiu Au. Multiple-Place Swarm Foraging with Dynamic Robot Chains. IEEE International Conference on Robotics and Automation (ICRA 2021), May 2021 [link]
Qi Lu, G. Matthew Fricke, Takaya Tsuno, and Melanie Moses. A Bio-Inspired Transportation Network for Scalable Swarm Foraging. IEEE International Conference on Robotics and Automation (ICRA), May 2020. [link][PDF][video]
Qi Lu and Melanie E. Moses. A Bio-Inspired Transporation Network for Scalable Swarm Foraging. IEEE International Sym. on Multiple-Robot and Multi-Agent Systems (MRS), 2019.[Extended abstract][link]
Qi Lu, G. Matthew Fricke, and Melanie E. Moses. Comparing Physical and Simulated Performance of a Deterministic and a Bio-inspired Stochastic Foraging Strategy for Robot Swarms. IEEE International Conference on Robotics and Automation (ICRA), 2019.[link][PDF][video]
Journals:
Qi Lu, G. Matthew Fricke, John Ericksen, and Melanie Moses. Swarm Foraging Review: Closing the Gap Between Proof and Practice. Journal of Current Robotics Reports, Springer, June 2020.[link][PDF]
Qi Lu, Joshua P. Hecker, and Melanie E. Moses. Multiple-Place Swarm Foraging with Dynamic Depots. The Journal of Autonomous Robots, Jan. 2018.[link][PDF] [video]
Yuming Zhang, Cong Chen, Qiong Wu, Qi Lu, Su Zhang, Guohui Zhang, Yin Yang. A Kinect-Based Approach for 3D Pavement Surface Reconstruction and Cracking Recognition. IEEE Transactions on Intelligent Transportation Systems. 2018.
Patent
Melanie E. Moses, Joshua P. Hecker, and Qi Lu. System and Methods for Multiple-Place Swarm Foraging with Dynamic Depots. Supporting Technology Transfer and Catalyzing, University of New Mexico, 2020.