Adaptive Capture Control of a Continuum Manipulator With Self-Powered Sensors

Abstract

Perception is an essential component of an intelligent autonomous system. However, the traditional sensors used in robotics and industry are limited when considering high mobility, wide distribution, and possible wireless operation of the sensors in sensor networks. The self-powered sensing solves the most shackling issue in the current sensing field, thus enabling many previously unattainable application scenarios. In this article, a novel variable-length continuum manipulator with self-powered sensors is designed, and an adaptive capture control scheme based on deep-learning prediction is proposed for the envelope grasp of a fixed cylinder target and the hook grasp of a ring target moving in a small range. First, adaptive capture parameters of the manipulator are generated according to a target’s size and position. Then, deep neural networks are utilized to accurately predict the bending angle of the manipulator with a large displacement motion at the tip of the continuum manipulator. Finally, based on the feedback data from the driving motor’s built-in angular velocity sensor on the continuum manipulator, a set of capture criteria is presented to identify the envelope and capture states of the target. The capture experimental results on a prototype reveal that the generated parameters highly match the targets. The prediction method’s accuracy is higher than that of conventional feedforward neural networks (FNNs). The capture criteria based on the feedback data from the driving motor’s built-in angular velocity sensor can correctly identify the target capture states. In addition, future research on adaptive capture control based on self-powered sensors is discussed.