The motion of magnetic microrobots relies on an external magnetic field. Current electromagnetic propulsion systems are often complex in structural design, challenging in control strategies, and associated with high energy consumption. In this study, we introduce a mechano-electromagnetic hybrid actuation system that employs only a pair of Helmholtz coils to generate an oscillating uniform magnetic field, combined with a rotating platform to modify the field’s direction, thereby enabling the control of microrobot speed and direction. The properties of this hybrid actuation system were modeled and validated to analyze the magnetic field distribution within the workspace. The design and actuation of two microrobots are described in detail. Furthermore, a visual feedback closed-loop control strategy for the system was developed. A series of navigation control experiments were conducted, demonstrating that the proposed hybrid actuation system achieves effective microrobot actuation and precise control while reducing manufacturing costs and simplifying control strategies. The proposed novel mechano-electromagnetic hybrid structure contributes to the field of electromagnetically driven systems and magnetically controlled microrobots.

Dongqin Xu, Junhui Li, Muhua Zhu, Min Zhang, Guodong Zhou. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

In the literature, the research on abstract meaning representation (AMR) parsing is much restricted by the size of human-curated dataset which is critical to build an AMR parser with good performance.To alleviate such data size restriction, pre-trained models have been drawing more and more attention in AMR parsing.However, previous pre-trained models, like BERT, are implemented for general purpose which may not work as expected for the specific task of AMR parsing.In this paper, we focus on sequence-to-sequence (seq2seq) AMR parsing and propose a seq2seq pre-training approach to build pre-trained models in both single and joint way on three relevant tasks, i.e., machine translation, syntactic parsing, and AMR parsing itself.Moreover, we extend the vanilla fine-tuning method to a multi-task learning fine-tuning method that optimizes for the performance of AMR parsing while endeavors to preserve the response of pre-trained models.Extensive experimental results on two English benchmark datasets show that both the single and joint pre-trained models significantly improve the performance (e.g., from 71.5 to 80.2 on AMR 2.0), which reaches the state of the art.The result is very encouraging since we achieve this with seq2seq models rather than complex models.We make our code and model available at https:// github.com/xdqkid/S2S-AMR-Parser.