日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

マイクロロボティクス/設計最適化arXiv:2407.15243

遺伝的アルゴリズムによるマイクロ手術用ハサミの設計最適化

Genetic Algorithm to Optimize Design of Micro-Surgical Scissors

シェア:XThreadsFacebookLINEはてブBluesky

脳深部の腫瘍切除などに用いる無拘束マイクロ手術用ハサミについて、磁石の位置と磁気モーメントの向きを遺伝的アルゴリズムで最適化し、切断力を1.65倍に向上させた。

著者: Fatemeh Norouziani, Veerash Palanichamy, Shivam Gupta, Onaizah Onaizah

分類: cs.RO, cs.AI

原文アブストラクト

Microrobotics is an attractive area of research as small-scale robots have the potential to improve the precision and dexterity offered by minimally invasive surgeries. One example of such a tool is a pair of micro-surgical scissors that was developed for cutting of tumors or cancerous tissues present deep inside the body such as in the brain. This task is often deemed difficult or impossible with conventional robotic tools due to their size and dexterity. The scissors are designed with two magnets placed a specific distance apart to maximize deflection and generate cutting forces. However, remote actuation and size requirements of the micro-surgical scissors limits the force that can be generated to puncture the tissue. To address the limitation of small output forces, we use an evolutionary algorithm to further optimize the performance of the scissors. In this study, the design of the previously developed untethered micro-surgical scissors has been modified and their performance is enhanced by determining the optimal position of the magnets as well as the direction of each magnetic moment. The developed algorithm is successfully applied to a 4-magnet configuration which results in increased net torque. This improvement in net torque is directly translated into higher cutting forces. The new configuration generates a cutting force of 58 mN from 80 generations of the evolutionary algorithm which is a 1.65 times improvement from the original design. Furthermore, the developed algorithm has the advantage that it can be deployed with minor modifications to other microrobotic tools and systems, opening up new possibilities for various medical procedures and applications.

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI