Ablation Study on Features in Learning-based Joints Calibration of Cable-driven Surgical Robots

TL;DR

This paper presents a learning-based calibration method for cable-driven surgical robots that significantly improves joint pose accuracy, and an ablation study identifies the most critical features contributing to calibration performance.

Contribution

It introduces a deep neural network calibration approach and analyzes feature importance through ablation, highlighting the roles of joint poses and motor torques.

Findings

Joint pose RMSE reduced to approximately 0.3 degrees and 0.15 mm.

Motor torques are more influential when considering direction over amplitude.

Ablation results show raw joint poses can be inferred from end-effector data.

Abstract

With worldwide implementation, millions of surgeries are assisted by surgical robots. The cable-drive mechanism on many surgical robots allows flexible, light, and compact arms and tools. However, the slack and stretch of the cables and the backlash of the gears introduce inevitable errors from motor poses to joint poses, and thus forwarded to the pose and orientation of the end-effector. In this paper, a learning-based calibration using a deep neural network is proposed, which reduces the unloaded pose RMSE of joints 1, 2, 3 to 0.3003 deg, 0.2888 deg, 0.1565 mm, and loaded pose RMSE of joints 1, 2, 3 to 0.4456 deg, 0.3052 deg, 0.1900 mm, respectively. Then, removal ablation and inaccurate ablation are performed to study which features of the DNN model contribute to the calibration accuracy. The results suggest that raw joint poses and motor torques are the most important features. For joint poses, the removal ablation shows that DNN model can derive this information from end-effector pose and orientation. For motor torques, the direction is much more important than amplitude.