Collaborative Industrial Robots
Related Projects:  Robot Task and Motion Planning    Our Algorithms At Work    Integrated Task and Motion Planning    Multi-Robot Motion Planning    Navigation & Localization  

Robots are widely used in industry as they improve productivity and reduce operating costs and time. They ease several tasks, such as assembly, object management, and quality control. Robots can even work in a team with humans to perform collaborative tasks.



Our research group is currently involved in two large research projects with the aim of leveraging robots in industrial settings. One project consists of enabling human-robot cooperation in the manufacturing industry. The second project involves leveraging hybrid cloud computing when using robots in the industry to maximize robots' performance by improving/reducing robots' local computation.

Human-Robot Collaboration: Interactive Manipulation for Industrial Robotics


Project overview

This project aims to enable high-speed, high-precision assembly of small parts with off-the-shelf industrial robots in high-mix, low-volume production lines. We look to develop new planning algorithms and human-robot collaboration strategies so that humans and industrial robots can safely interact and collaborate when manipulating and assembling industrial components and other objects.


Support info
This is large, multi-year, interactive manipulation project for an industrial robotics application and is part of the $100M Center for Networked Intelligent Components and Environments (C-NICE) within the Grainger College of Engineering at Illinois. Our team comes from the Illinois Robotics Group which spans seven departments at Illinois and is supported by the Center for Autonomy in the Coordinated Science Laboratory. While all team members are involved in all aspects of the project, the Parasol group is focusing on multi-robot motion planning and task allocation in mobile manipulation tasks.

Robots on the (Mobile) Edge and in the Hybrid Cloud


Project overview

This project aims to develop adaptive cyber-physical systems in which robot teams collaborate with humans and other robots to perform complex tasks in structured and instrumented industrial settings, such as factories and fulfillment centers. This is the first step on the path to the deployment of robotic assistants in office, commercial, and home environments.


A distinguishing feature of this project is the complex computational environment, as it aims to leverage hybrid (edge/cloud) computing procedures. First, it integrates robots (and their environment) edge computing to allow communication and passage of data from different sensors and other computational devices. Finally, it will incorporate cloud computing for larger computational capacity and provide access to proprietary and shareable resources.


Support info
This project is one of the Hybrid Cloud and Artificial Intelligence technological innovations of the new IBM-Illinois Discovery Accelerator Institute, which aims to expand the potential of edge computing and cloud security capabilities across public and private clouds. In this project, eight Illinois faculty and seven IBM researchers are collaborating. As well several students are playing an active role in developing this research.




Related Publications

Insights from an Industrial Collaborative Assembly Project: Lessons in Research and Collaboration, Tan Chen, Zhe Huang, James Motes, Junyi Geng, Quang Minh Ta, Holly Dinkel, Hameed Abdul-Rashid, Jessica Myers, Ye-Ji Mun, Wei-che Lin, Yuan-yung Huang, Sizhe Liu, Marco Morales, Nancy M Amato, Katherine Driggs-Campbell, Timothy Bretl, ICRA 2022 WORKSHOP ON COLLABORATIVE ROBOTS AND THE WORK OF THE FUTURE, Philadelphia, PA, USA, May 2022.
Keywords: Assembly, Industrial Applications, Interaction
Links : [ArXiv]

BibTex

@article{chen2022insights,
title={Insights from an Industrial Collaborative Assembly Project: Lessons in Research and Collaboration},
author={Chen, Tan and Huang, Zhe and Motes, James and Geng, Junyi and Ta, Quang Minh and Dinkel, Holly and Abdul-Rashid, Hameed and Myers, Jessica and Mun, Ye-Ji and Lin, Wei-che and others},
journal={arXiv preprint arXiv:2205.14340},
year={2022}
}


Abstract

Significant progress in robotics reveals new opportunities to advance manufacturing. Next-generation industrial automation will require both integration of distinct robotic technologies and their application to challenging industrial environments. This paper presents lessons from a collaborative assembly project between three academic research groups and an industry partner. The goal of the project is to develop a flexible, safe, and productive manufacturing cell for sub-centimeter precision assembly. Solving this problem in a high-mix, low-volume production line motivates multiple research thrusts in robotics. This work identifies new directions in collaborative robotics for industrial applications and offers insight toward strengthening collaborations between institutions in academia and industry on the development of new technologies.


Representation-Optimal Multi-Robot Motion Planning using Conflict-Based Search, Irving Solis, James Motes, Read Sandström, Nancy M. Amato, IEEE Robotics and Automation Letters, Mar 2021. DOI: https://doi.org/10.1109/LRA.2021.3068910
Keywords: Industrial Applications, Motion Planning, Multi-Agent
Links : [Published] [Manuscript]

BibTex

@article{solis2019representation,
title={Representation-optimal multi-robot motion planning using conflict-based search},
author={Solis, Irving and Sandstr{\"o}m, Read and Motes, James and Amato, Nancy M},
journal={arXiv preprint arXiv:1909.13352},
year={2019}
}


Abstract

Multi-Agent Motion Planning (MAMP) is the problem of computing feasible paths for a set of agents each with individual start and goal states within a continuous state space. Existing approaches can be split into coupled methods which provide optimal solutions but struggle with scalability or decoupled methods which provide scalable solutions but offer no optimality guarantees. Recent work has explored hybrid approaches that leverage the advantages of both coupled and decoupled approaches in an easier discrete subproblem, Multi-Agent Pathfinding (MAPF). In this work, we adapt recent developments in hybrid MAPF to the continuous domain of MAMP. We demonstrate the scalability of our method to manage groups of up to 32 agents, demonstrate the ability to handle up to 8 high-DOF manipulators, and plan for heterogeneous teams. In all scenarios, our approach plans significantly faster while providing higher quality solutions.