Back to search

Boston University

Enabling collaborative autonomy: from human-robot teams to multi-agent systems

Abstract

dc:description.abstract

As robots continue to become more sophisticated, we need robots capable of interacting and collaborating with other robots and human teammates. We envision robots designed to collaborate with other agents, whether robot or human. This vision presents a variety of challenges, and this dissertation specifically focuses on exploring various levels of inter-agent interaction and inferred teammate information. We first explore single-human–single robot teaming within the scope of collaborative navigation, which requires direct human-robot interaction and inferred teammate information. We consider the case where a human and robot must navigate through an environment to reach a shared goal. We propose two distinct haptic guidance systems, which provide collision avoidance and route suggestions to the human user via force feedback. Each approach provides different benefits in computation and optimality. Analytical and experimental results show our approach guarantees simultaneous collision avoidance and guidance to the goal. While this first work addresses two-agent collaboration, the remainder of this dissertation focuses on multi-agent collaboration, with little interaction between robots and humans and different levels of teammate information. We consider a heterogeneous multi-agent team, in that each robot has different capabilities such as sensing or resource capacity. We propose control policies to deploy robots to serve complex, dynamic tasks, enabling the team to adapt to changes in tasks and within the team. Our distributed approach allows for large-scale applications. Analyses show our approaches converge to optimal solutions while adapting to the dynamic environment, and simulations and hardware experiments demonstrate comparable performance to baseline algorithms.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy
Level thesis:degree_level
doctoral
Discipline thesis:degree_discipline
Mechanical Engineering
Grantor
Boston University
Year dc:date.issued
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Coffey, Mela
Advisor dc:contributor.advisor
  • Pierson, Alyssa
ORCID dc:identifier.orcid

Subjects

dc:subject × 1

Rights

dc:rights
Statement dc:rights
  • Attribution 4.0 International
Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/2144/50468

Chain of custody

source
Harvested from
Boston University
Base URL
open.bu.edu/oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
related terms
citation

Coffey, Mela. Enabling collaborative autonomy: from human-robot teams to multi-agent systems. doctoral thesis, Boston University, 2025. https://hdl.handle.net/2144/50468