Human–Robot Collaboration in Industrial Production

Period: Oct 2015 – Sep 2017
Role: Doctoral Researcher
Principal Investigators: Prof. Martin Buss, PD Dr.-Ing. Dirk Wollherr, Dr.-Ing. Georg von Wichert
Affiliation: Technical University of Munich (TUM)
Funding: Siemens AD-Campus Project [ link ]
Industry Partner: Siemens AG

Overview

This project investigated human–robot collaboration (HRC) for industrial assembly scenarios in the context of emerging Industry 4.0 production paradigms.

Modern manufacturing increasingly requires flexible production systems capable of supporting mass customization and small-batch production. Traditional industrial robots are designed for rigid and repetitive tasks and therefore struggle to operate effectively in dynamic environments where humans and robots must cooperate.

The project explored how robotic systems can safely and efficiently collaborate with human workers in shared workspaces, focusing on task coordination, perception uncertainty, and execution monitoring in collaborative assembly processes.

Technical Focus

The project studied key challenges in deploying collaborative robots in industrial production, including:

• Modeling collaborative assembly processes: Representing human–robot tasks and coordination structures in assembly workflows.

• Task allocation and scheduling: Assigning subtasks between human operators and robotic manipulators.

• Perception uncertainty in collaborative environments: Handling incomplete or noisy information about object states and human actions.

• Execution monitoring and error detection: Supervising collaborative operations and identifying failures during assembly processes.

My Contribution

As an early-stage doctoral researcher, I worked on experimental and control-related aspects of the collaborative robotic platform.

My work focused on:

• Investigating robot sensing and control challenges in collaborative manipulation tasks

• Developing methods for collision torque diagnosis and system monitoring

• Exploring robust control strategies for safe robot operation under sensing uncertainty

• Gaining hands-on experience with industrial robot hardware and control systems

This work provided the practical foundation for my later research on signal reconstruction, observer design, and robust control in robotic systems.

Applications and Impact

The project contributed to early research on human–robot collaboration in industrial production, exploring how robots can support flexible manufacturing environments where humans and machines work closely together.

Beyond its immediate industrial context, the project exposed fundamental challenges related to uncertain sensing, safe interaction, and reliable robot control in real-world environments. These challenges later motivated my research on signal reconstruction and safety-critical control for autonomous systems.

Publications

• Z. Zhang*, M. Leibold, and D. Wollherr, "Integral Sliding-Mode Observer-Based Disturbance Estimation for Euler–Lagrangian Systems," in IEEE Transactions on Control Systems Technology, vol. 28, no. 6, pp. 2377-2389, Nov. 2020, doi: 10.1109/TCST.2019.2945904. [IEEEXplore]

• Y. Sun*, Z. Zhang, M. Leibold, R. Hayat, D. Wollherr, and M. Buss. "Protective Control For Robot Manipulator By Sliding Mode Based Disturbance Reconstruction Approach." 2017 IEEE International Conference on Advanced Intelligent Mechatronics (AIM). Munich, Germany, 03-07 July 2017.

Technology Transfer

• Zengjie Zhang, Sensor-less Collision Detector for Robot Manipulators, Technical University of Munich, Siemens AG, 2018-07E03 MR.