TY - GEN
T1 - Learning local behavioral sequences to better infer non-local properties in real multi-robot systems
AU - Choi, Taeyeong
AU - Kang, Sehyeok
AU - Pavlic, Theodore P.
N1 - Funding Information:
*This work was supported in part by NSF grant #1735579.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/5
Y1 - 2020/5
N2 - When members of a multi-robot team follow regular motion rules sensitive to robots and other environmental factors within sensing range, the team itself may become an informational fabric for gaining situational awareness without explicit signalling among robots. In our previous work [1], we used machine learning to develop a scalable module, trained only on data from 3-robot teams, that could predict the positions of all robots in larger multi-robot teams based only on observations of the movement of a robot's nearest neighbor. Not only was this approach scalable from 3-to-many robots, but it did not require knowledge of the control laws of the robots under observation, as would a traditional observer-based approach. However, performance was only tested in simulation and could only be a substitute for explicit communication for short periods of time or in cases of very low sensing noise. In this work, we apply more sophisticated machine learning methods to data from a physically realized robotic team to develop Remote Teammate Localization (ReTLo) modules that can be used in realistic environments. To be specific, we adopt Long-Short-Term-Memory (LSTM) [2] to learn the evolution of behaviors in a modular team, which has the effect of greatly reducing errors from regression outcomes. In contrast with our previous work in simulation, all of the experiments conducted in this work were conducted on the Thymio physical, two-wheeled robotic platform.
AB - When members of a multi-robot team follow regular motion rules sensitive to robots and other environmental factors within sensing range, the team itself may become an informational fabric for gaining situational awareness without explicit signalling among robots. In our previous work [1], we used machine learning to develop a scalable module, trained only on data from 3-robot teams, that could predict the positions of all robots in larger multi-robot teams based only on observations of the movement of a robot's nearest neighbor. Not only was this approach scalable from 3-to-many robots, but it did not require knowledge of the control laws of the robots under observation, as would a traditional observer-based approach. However, performance was only tested in simulation and could only be a substitute for explicit communication for short periods of time or in cases of very low sensing noise. In this work, we apply more sophisticated machine learning methods to data from a physically realized robotic team to develop Remote Teammate Localization (ReTLo) modules that can be used in realistic environments. To be specific, we adopt Long-Short-Term-Memory (LSTM) [2] to learn the evolution of behaviors in a modular team, which has the effect of greatly reducing errors from regression outcomes. In contrast with our previous work in simulation, all of the experiments conducted in this work were conducted on the Thymio physical, two-wheeled robotic platform.
UR - http://www.scopus.com/inward/record.url?scp=85092737977&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85092737977&partnerID=8YFLogxK
U2 - 10.1109/ICRA40945.2020.9196728
DO - 10.1109/ICRA40945.2020.9196728
M3 - Conference contribution
AN - SCOPUS:85092737977
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 2138
EP - 2144
BT - 2020 IEEE International Conference on Robotics and Automation, ICRA 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Robotics and Automation, ICRA 2020
Y2 - 31 May 2020 through 31 August 2020
ER -