Sufficient Statistics for Optimal Decentralized Control in System of Systems

Nigam, Nikhil; Lall, Sanjay; Hovareshti, Pedram; Ezra, Kristopher L.; Mockus, Linas; Tolani, Devendra; Sloan, Shawn

doi:10.1109/ai4i.2018.8665711

Search citation statements

Order By: Relevance

Paper Sections

Select...

Related Work1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2019

Publication Types

Select...

Other1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Teams of robots have performed tasks such as localization [1], navigation [2], and manipulation [3,4]. While many works rely on centralized coordination [5], decentralized multiagent teams are receiving increasing attention [6,2,7,8]. Within decentralized control, the problem is reformulated as a decentralized partially-observable Markov decision process (Dec-POMDP) [9,10] or coordinator-POMDP [11].…”

Section: Related Workmentioning

confidence: 99%

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

Losey,

Li,

Bohg

et al. 2019

Preprint

View full text Add to dashboard Cite

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 exploitation, information giving, or information gathering, we define separate roles for each agent. Because each role defines a distinct reason for acting (e.g., only exploit), teammates can 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.

show abstract