Back to search

Boston University

Programming by demonstration for dual-arm manipulation

Abstract

dc:description.abstract

Motivated by challenges operators face with manual control tasks, including fatigue and workload management, this research explores the adoption of a semi-autonomous control method to improve work environment quality and task metrics in controlled situations. Building upon the success of Programming by Demonstration (PbD) for single-arm industrial robotic applications, we extend these techniques to dual-arm robotic control. We present a semi-autonomous approach allowing users to supervise tasks while delegating control to the system, alleviating stress and fatigue associated with manual control operations. This research compares manual and semi-autonomous control in a human-robot team, focusing quantitatively on user performance and qualitatively on trust in the system. Participants controlled a dual-arm robotic system from a remote cockpit, monitoring progress through a graphical user interface (GUI) and camera views. Semi-autonomous control employs PbD with selectable ’motion primitives’. Trials involved a modified pick-and-place task and results demonstrate a significantly higher success rate across all metrics with semi-autonomous control. This study highlights the applicability of PbD as a semi-autonomous control method in human-robot teams, reducing workload stress and enhancing task performance. Integrating sensors for dynamic environment analysis to create motion feedback mechanisms could further enhance user trust and system adaptability. Ultimately, this research suggests implementing semi-autonomous control for dual-arm robotic systems, offering faster onboarding for new operators and increased operational flexibility while minimizing user stress and fatigue.

Degree

thesis:*
Name thesis:degree_name
Master of Science
Level thesis:degree_level
masters
Discipline thesis:degree_discipline
Mechanical Engineering
Grantor
Boston University
Year dc:date.issued
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Mudgal, Karan Chaitanya
Advisor dc:contributor.advisor
  • Ranzani, Tommaso
ORCID dc:identifier.orcid

Subjects

dc:subject × 5

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/2144/48897

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
citation

Mudgal, Karan Chaitanya. Programming by demonstration for dual-arm manipulation. masters thesis, Boston University, 2024. https://hdl.handle.net/2144/48897