A Semi-Autonomous Telemanipulation Order-Picking Control Based on Estimating Operator Intent for Box-Stacking Storage Environments.

Teleoperation-based order picking in logistics warehouse environments has been advancing steadily. However, the accuracy of such operations varies depending on the type of human-robot interface (HRI) employed. Immersive HRI, which uses a head-mounted display (HMD) and controllers, can significantly reduce task accuracy due to the limited field of view in virtual environments. To address this limitation, this study proposes a semi-autonomous telemanipulation order-picking control method based on operator intent estimation using intersection points between the end-effector and the target logistics plane in box-stacking storage environments. The proposed method consists of two stages. The first stage involves operator intent estimation, which approximates the target logistics plane using objects identified through camera vision and calculates the intersection points by intersecting the end-effector heading vector with the plane. These points are accumulated and modeled as a Gaussian distribution, with the probability density function (PDF) of each target object treated as its likelihood. Bayesian probability filtering is then applied to estimate target probabilities, and predefined conditions are used to switch control between autonomous and manual controllers. Results show that the proposed operator intent estimation method identified the correct target in 74.6% of the task's duration. The proposed semi-autonomous control method successfully transferred control to the autonomous controller within 32.2% of the total task duration using a combination of three parameters. This approach inferred operator intent based solely on manipulator motion and reduced the fatigue of the operator. This method demonstrates potential for broad application in teleoperation systems, offering high operational efficiency regardless of operator expertise or training level.