Learning from My Partner’s Actions: Roles in Decentralized Robot Teams

Dylan P. Losey, Mengxi Li, Jeannette Bohg, Dorsa Sadigh
Proceedings of the Conference on Robot Learning, PMLR 100:752-765, 2020.

Abstract

When teams of robots collaborate to complete a task, communication is often necessary. Like humans, robot teammates should implicitly communicate through their actions: but interpreting our partner’s actions is typically difficult, since a given action may have many different underlying reasons. Here we propose an alternate approach: instead of not being able to infer whether an action is due to exploration, exploitation, or communication, we define separate roles for each agent. Because each role defines a distinct reason for acting (e.g., only exploit, only communicate), teammates now correctly interpret the meaning behind their partner’s actions. Our results suggest that leveraging and alternating roles leads to performance comparable to teams that explicitly exchange messages.

Cite this Paper

BibTeX
@InProceedings{pmlr-v100-losey20a, title = {Learning from My Partner’s Actions: Roles in Decentralized Robot Teams}, author = {Losey, Dylan P. and Li, Mengxi and Bohg, Jeannette and Sadigh, Dorsa}, booktitle = {Proceedings of the Conference on Robot Learning}, pages = {752--765}, year = {2020}, editor = {Kaelbling, Leslie Pack and Kragic, Danica and Sugiura, Komei}, volume = {100}, series = {Proceedings of Machine Learning Research}, month = {30 Oct--01 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v100/losey20a/losey20a.pdf}, url = {https://proceedings.mlr.press/v100/losey20a.html}, abstract = {When teams of robots collaborate to complete a task, communication is often necessary. Like humans, robot teammates should implicitly communicate through their actions: but interpreting our partner’s actions is typically difficult, since a given action may have many different underlying reasons. Here we propose an alternate approach: instead of not being able to infer whether an action is due to exploration, exploitation, or communication, we define separate roles for each agent. Because each role defines a distinct reason for acting (e.g., only exploit, only communicate), teammates now correctly interpret the meaning behind their partner’s actions. Our results suggest that leveraging and alternating roles leads to performance comparable to teams that explicitly exchange messages.} }
Endnote
%0 Conference Paper %T Learning from My Partner’s Actions: Roles in Decentralized Robot Teams %A Dylan P. Losey %A Mengxi Li %A Jeannette Bohg %A Dorsa Sadigh %B Proceedings of the Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2020 %E Leslie Pack Kaelbling %E Danica Kragic %E Komei Sugiura %F pmlr-v100-losey20a %I PMLR %P 752--765 %U https://proceedings.mlr.press/v100/losey20a.html %V 100 %X When teams of robots collaborate to complete a task, communication is often necessary. Like humans, robot teammates should implicitly communicate through their actions: but interpreting our partner’s actions is typically difficult, since a given action may have many different underlying reasons. Here we propose an alternate approach: instead of not being able to infer whether an action is due to exploration, exploitation, or communication, we define separate roles for each agent. Because each role defines a distinct reason for acting (e.g., only exploit, only communicate), teammates now correctly interpret the meaning behind their partner’s actions. Our results suggest that leveraging and alternating roles leads to performance comparable to teams that explicitly exchange messages.
APA
Losey, D.P., Li, M., Bohg, J. & Sadigh, D.. (2020). Learning from My Partner’s Actions: Roles in Decentralized Robot Teams. Proceedings of the Conference on Robot Learning, in Proceedings of Machine Learning Research 100:752-765 Available from https://proceedings.mlr.press/v100/losey20a.html.

Related Material