Award Abstract # 2026611
FW-HTF-RM: Collaborative Research: Supervise It! Optimizing Intelligent Robot Integration Through Feedback to Workers and Supervisors

NSF Org: CMMI
Division of Civil, Mechanical, and Manufacturing Innovation
Recipient: GEORGIA TECH RESEARCH CORP
Initial Amendment Date: August 3, 2020
Latest Amendment Date: August 3, 2020
Award Number: 2026611
Award Instrument: Standard Grant
Program Manager: Alexandra Medina-Borja
amedinab@nsf.gov
 (703)292-7557
CMMI
 Division of Civil, Mechanical, and Manufacturing Innovation
ENG
 Directorate for Engineering
Start Date: October 1, 2020
End Date: September 30, 2025 (Estimated)
Total Intended Award Amount: $457,240.00
Total Awarded Amount to Date: $457,240.00
Funds Obligated to Date: FY 2020 = $457,240.00
History of Investigator:
  • Patricio Vela (Principal Investigator)
    pvela@ece.gatech.edu
Recipient Sponsored Research Office: Georgia Tech Research Corporation
926 DALNEY ST NW
ATLANTA
GA  US  30318-6395
(404)894-4819
Sponsor Congressional District: 05
Primary Place of Performance: Georgia Institute of Technology
225 North Ave NW
Atlanta
GA  US  30332-0002
Primary Place of Performance
Congressional District:
05
Unique Entity Identifier (UEI): EMW9FC8J3HN4
Parent UEI: EMW9FC8J3HN4
NSF Program(s): FW-HTF Futr Wrk Hum-Tech Frntr
Primary Program Source: 01002021DB NSF RESEARCH & RELATED ACTIVIT
Program Reference Code(s): 063Z
Program Element Code(s): 103Y00
Award Agency Code: 4900
Fund Agency Code: 4900
Assistance Listing Number(s): 47.041

ABSTRACT

Limitations in achievable performance and programmability are obstacles to realizing productivity gains from the full automation of manufacturing operations requiring a large variety of low-volume tasks. The use of collaborative robots to assist human workers is a promising approach to overcoming these obstacles, without displacing human jobs. Current efforts in this area focus on the worker-robot partnership and overlook the critical role of the supervisor in managing workloads and allocating tasks. By considering the larger context of supervised work teams, this Future of Work at the Human-Technology Frontier (FW-HTF) research aims to enhance productivity and improve worker quality of life by increasing the effectiveness of workers operating in partnership with robots. It provides a framework for analyzing readiness, assessing adoption, and evaluating performance of collaborative robotics in industrial settings. Partnerships and interactions with companies in the Southeastern USA will promote realistic research efforts that translate to practice, benefitting small-to-medium manufacturing companies in the USA. Efforts and findings will be promoted to the public to attract the next generation of workers and researchers to science and engineering fields.

This project explores two hypotheses. The first working hypothesis is that, when workers view robots as partners, imperfection will be tolerated if the worker can successfully manage the robot to complete the task faster than their self-conceived rate. The determining factor regarding the value of a worker-robot collaborative partnership is hypothesized to be the worker?s ability to allocate the task workload between the robot and themselves towards an optimal partnership. The second working hypothesis is that the introduction of a supervisor to guide and promote task allocation will further contribute to enhanced worker-robot performance. This hypothesis builds on the observation that line supervisors interact with multiple workers, and thus are a repository of holistic institutional knowledge regarding good practice. To confirm these hypotheses and arrive at the anticipated framework, called the Worker-Robot Supervisor Effectiveness Model, requires a mixed-methods research design. First, a grounded theory study will establish assessment criteria related to worker, robot, and supervisor technology adoption and performance to develop an instrument for measuring both. Second, within a simulated manufacturing work cell environment, a set of experiments will investigate factors linked to successful technology adoption and work cell performance. Third, the findings from these studies will inform the creation of the model, which will provide guidance for effective integration, adoption, and supervision of worker-robot partnerships. Fourth, to confirm the applicability of the derived model, it will be used to field and integrate a robot within the existing processes of a real-world company. Field deployment will provide empirical evidence to validate and refine the model.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH

Note:  When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

Chen, Yiye and Lin, Yunzhi and Xu, Ruinian and Vela, Patricio A "WDiscOOD: Out-of-Distribution Detection via Whitened Linear Discriminant Analysis" , 2023 https://doi.org/10.1109/ICCV51070.2023.00488 Citation Details
Chen, Yiye and Lin, Yunzhi and Xu, Ruinian and Vela, Patricio A. "Keypoint-GraspNet: Keypoint-based 6-DoF Grasp Generation from the Monocular RGB-D input" International Conference on Robotics and Automation , 2023 https://doi.org/10.1109/ICRA48891.2023.10161284 Citation Details
Chen, Yiye and Xu, Ruinian and Lin, Yunzhi and Chen, Hongyi and Vela, Patricio A "KGNv2: Separating Scale and Pose Prediction for Keypoint-Based 6-DoF Grasp Synthesis on RGB-D Input" , 2023 https://doi.org/10.1109/IROS55552.2023.10342514 Citation Details
Lin, Yunzhi and Müller, Thomas and Tremblay, Jonathan and Wen, Bowen and Tyree, Stephen and Evans, Alex and Vela, Patricio A. and Birchfield, Stan "Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation" International Conference on Robotics and Automation , 2023 https://doi.org/10.1109/ICRA48891.2023.10161117 Citation Details
Lin, Yunzhi and Tremblay, Jonathan and Tyree, Stephen and Vela, Patricio A. and Birchfield, Stan "Keypoint-Based Category-Level Object Pose Tracking from an RGB Sequence with Uncertainty Estimation" International Conference on Robotics and Automation , 2022 https://doi.org/10.1109/ICRA46639.2022.9811720 Citation Details
Lin, Yunzhi and Tremblay, Jonathan and Tyree, Stephen and Vela, Patricio A. and Birchfield, Stan "Single-Stage Keypoint- Based Category-Level Object Pose Estimation from an RGB Image" International Conference on Robotics and Automation , 2022 https://doi.org/10.1109/ICRA46639.2022.9812299 Citation Details
Xu, Ruinian and Chen, Hongyi and Lin, Yunzhi and Vela, Patricio A. "SGL: Symbolic Goal Learning in a Hybrid, Modular Framework for Human Instruction Following" IEEE Robotics and Automation Letters , v.7 , 2022 https://doi.org/10.1109/LRA.2022.3190076 Citation Details

Please report errors in award information by writing to: awardsearch@nsf.gov.

Print this page

Back to Top of page