MobileCharger：インバーテッドデルタアクチュエータを備えた安全で堅牢な充電のための自律移動ロボット
MobileCharger: an Autonomous Mobile Robot with Inverted Delta Actuator for Robust and Safe Robot Charging
RGB-Dカメラと触覚センサーを組み合わせた視覚・触覚認識により、移動ロボット同士の電極を高精度に位置合わせして自動充電する移動充電ロボットを開発した。
著者: Iaroslav Okunevich, Daria Trinitatova, Pavel Kopanev, Dzmitry Tsetserukou
分類: cs.RO, cs.LG
原文アブストラクト
MobileCharger is a novel mobile charging robot with an Inverted Delta actuator for safe and robust energy transfer between two mobile robots. The RGB-D camera-based computer vision system allows to detect the electrodes on the target mobile robot using a convolutional neural network (CNN). The embedded high-fidelity tactile sensors are applied to estimate the misalignment between the electrodes on the charger mechanism and the electrodes on the main robot using CNN based on pressure data on the contact surfaces. Thus, the developed vision-tactile perception system allows precise positioning of the end effector of the actuator and ensures a reliable connection between the electrodes of the two robots. The experimental results showed high average precision (84.2%) for electrode detection using CNN. The percentage of successful trials of the CNN-based electrode search algorithm reached 83% and the average execution time accounted for 60 s. MobileCharger could introduce a new level of charging systems and increase the prevalence of autonomous mobile robots.
