Motion Priority Optimization Framework towards Automated and Teleoperated Robot Cooperation in Industrial Recovery Scenarios

TL;DR

The paper tackles maintaining production during industrial recovery by introducing Cooperative Tele-Recovery, a framework that optimizes motion priority between autonomous manufacturing robots and teleoperated recovery robots under a configurable risk limit $t_{lim}$. It combines an HRC simulator, flexible motion generators, and a data-driven priority-function optimizer to maximize productivity while bounding recovery risk, implemented atop an IK-based collision-avoidance controller and ProMP-based recovery trajectories. Key contributions include a modular framework with independent components (human knowledge, motion generators, simulator, optimizer), a QP-based collision-avoidance scheme controlled by a tractable priority function, and validated feasibility through a two-robot hardware experiment and a four-robot simulation demonstrating adaptive priority switching. The results suggest that the method can reduce productivity loss and safety risk in industrial recovery scenarios, with future work focusing on online optimization, photorealistic simulation, and human-operator impact analysis.

Abstract

In this study, we introduce an optimization framework aimed at enhancing the efficiency of motion priority design in scenarios involving automated and teleoperated robots within an industrial recovery context. The escalating utilization of industrial robots at manufacturing sites has been instrumental in mitigating human workload. Nevertheless, the challenge persists in achieving effective human-robot collaboration/cooperation where human workers and robots share a workspace for collaborative tasks. In the event of an industrial robot encountering a failure, it necessitates the suspension of the corresponding factory cell for safe recovery. Given the limited capacity of pre-programmed robots to rectify such failures, human intervention becomes imperative, requiring entry into the robot workspace to address the dropped object while the robot system is halted. This non-continuous manufacturing process results in productivity loss. Robotic teleoperation has emerged as a promising technology enabling human workers to undertake high-risk tasks remotely and safely. Our study advocates for the incorporation of robotic teleoperation in the recovery process during manufacturing failure scenarios, which is referred to as "Cooperative Tele-Recovery". Our proposed approach involves the formulation of priority rules designed to facilitate collision avoidance between manufacturing and recovery robots. This, in turn, ensures a continuous manufacturing process with minimal production loss within a configurable risk limitation. We present a comprehensive motion priority optimization framework, encompassing an HRC simulator-based priority optimization and a cooperative multi-robot controller, to identify optimal parameters for the priority function. The framework dynamically adjusts the allocation of motion priorities for manufacturing and recovery robots while adhering to predefined risk limitations.

Figures (29)

• Figure 1: Our proposed concept of cooperative teleoperation recovery for industrial failure. The left snapshots are quoted from a video of World Robot Summit 2020, Assembly Challenge DAY2 (September 10, 2021) VonDrigalski2022. The proposed approach "Cooperative Tele-Recovery" addresses eliminating the orange-colored processes, including stopping/restarting manufacturing robots and entering/leaving the shared workspace.
• Figure 2: Proposed simulation environment designed for productivity-based motion priority optimization within a shared workspace. In the depicted scenario, the robot positioned in the foreground on the left is designated as a teleoperated recovery robot, while the others operate as autonomous manufacturing robots. To streamline the simulation, this study simplifies both recovery and manufacturing tasks, characterizing them as reaching tasks aimed at collecting datasets related to productivity and risk time.
• Figure 3: System structure of the proposed framework of productivity-based motion priority optimization, comprising 1) human prior knowledge (orange block), 2) manufacturing and recovery motion generators (green block), 3) HRC simulator (white block), 4) motion priority optimizer (blue block).
• Figure 4: Block diagram of the proposed multi-robot control, composed of manufacturing and recovery robots, their controllers, IKs, and a priority function block.
• Figure 5: Implementation of the proposed framework. The color notations for components are consistent with those presented in Fig. \ref{['fig:framework']}. To validate the viability of the proposed framework, we examine a simplified task employing versatile methodologies. The depictions in this figure presuppose a system consisting of one manufacturing robot and one recovery robot.