Collision Localization and Classification on the End-Effector of a Cable-Driven Manipulator Applied to EV Auto-Charging Based on DCNN-SVM

With the increasing popularity of electric vehicles, cable-driven serial manipulators have been applied in auto-charging processes for electric vehicles. To ensure the safety of the physical vehicle-robot interaction in this scenario, this paper presents a model-independent collision localization and classification method for cable-driven serial manipulators. First, based on the dynamic characteristics of the manipulator, data sets of terminal collision are constructed. In contrast to utilizing signals based on torque sensors, our data sets comprise the vibration signals of a specific compensator. Then, the collected data sets are applied to construct and train our collision localization and classification model, which consists of a double-layer CNN and an SVM. Compared to previous works, the proposed method can extract features without manual intervention and can deal with collision when the contact surface is irregular. Furthermore, the proposed method is able to generate the location and classification of the collision at the same time. The simulated experiment results show the validity of the proposed collision localization and classification method, with promising prediction accuracy.

Automated summary

This paper proposes a model-independent collision localization and classification method for cable-driven serial manipulators to ensure the safety of the physical vehicle-robot interaction in auto-charging processes for electric vehicles. The method constructs data sets of terminal collision based on the dynamic characteristics of the manipulator and utilizes a double-layer CNN and an SVM to construct and train the collision localization and classification model. The proposed method can extract features without manual intervention and can handle collision when the contact surface is irregular, showing promising prediction accuracy.