Collaborating for Success: Optimizing System Efficiency and Resilience Under Agile Industrial Settings

TL;DR

The paper tackles safe, ergonomic, and high-performance human-robot collaboration in agile manufacturing by integrating ISO-compliant safety zones with 2D laser sensing and 3D depth perception, and by a hierarchical velocity controller that combines a laser-driven primary loop with a depth-driven secondary loop. Stability is rigorously analyzed using LaSalle's invariance principle on a Lyapunov function $V = \frac{1}{2} e^T K_P e + \frac{1}{2} \dot{e}^T K_D \dot{e}$, with $\dot{V} \le 0$, ensuring global asymptotic convergence. The approach introduces dynamic MSD-based distance calculations and quadrant-based workspace segmentation to improve uptime and throughput, validated on a UR5 cobot cell performing medical-device assembly tasks. Empirical results show sizable improvements in cycle time, reaction delay, flexibility, and OEE compared to autonomous and traditional HRC setups, highlighting the method's potential for scalable, resilient operation in Industry 5.0 contexts. The work also lays out a clear path toward broader industrial testing and digital-twin deployment to ensure transferability across varied production environments.

Abstract

Designing an efficient and resilient human-robot collaboration strategy that not only upholds the safety and ergonomics of shared workspace but also enhances the performance and agility of collaborative setup presents significant challenges concerning environment perception and robot control. In this research, we introduce a novel approach for collaborative environment monitoring and robot motion regulation to address this multifaceted problem. Our study proposes novel computation and division of safety monitoring zones, adhering to ISO 13855 and TS 15066 standards, utilizing 2D lasers information. These zones are not only configured in the standard three-layer arrangement but are also expanded into two adjacent quadrants, thereby enhancing system uptime and preventing unnecessary deadlocks. Moreover, we also leverage 3D visual information to track dynamic human articulations and extended intrusions. Drawing upon the fused sensory data from 2D and 3D perceptual spaces, our proposed hierarchical controller stably regulates robot velocity, validated using Lasalle in-variance principle. Empirical evaluations demonstrate that our approach significantly reduces task execution time and system response delay, resulting in improved efficiency and resilience within collaborative settings.

Figures (7)

• Figure 1: Proposed configuration and parameterization of safety zones for SSM mode in accordance with ISO 13855 and TS 15066.
• Figure 2: Hierarchical velocity control architecture for fused perceptual monitoring and collaborative decision making.
• Figure 3: Collaborative workspace monitoring using 2D laser scanners and 3D depth sensor. (a-c) demonstrate configuration of safety zones for human activity tracking using strategically positioned scanners (white is normal, yellow is warning and red is dangerous), and (d-f) illustrate precise tracking of operator's skeleton to facilitate improved cooperation and resilience.
• Figure 4: Velocity profile of cobot under collaborative conditions using proposed hierarchical controller formulation.
• Figure 5: Experimental assessment of proposed solution within agile assembly settings. (a-d) represent human operator approaching shared workspace while cobot adapts it motion and configuration accordingly; (e-i) illustrate human operator performing assembly operation while cobot sorts parts into designated bins; (j-l) show how operator transit between subsequent zones for product batching while cobot arranges sorted bins into adjacent zone.