🤖 AI Summary
Kinematic modeling of displacement-driven continuum robots is challenging due to arbitrary joint placement and variable joint counts, hindering generalizable modeling and cross-configuration knowledge transfer.
Method: This paper proposes a modified Clarke transform tailored for asymmetric joint layouts, integrated into an encoder–decoder neural network architecture. Unlike conventional approaches constrained to symmetric configurations, the method enables joint-value mapping and forward/inverse kinematics for arbitrary joint numbers and positions.
Contribution/Results: The framework achieves high-precision trajectory tracking and closed-loop control under asymmetric configurations in simulation, while maintaining full compatibility with existing three-joint symmetric systems. Notably, this work pioneers the application of the Clarke transform to soft robotic kinematic representation—establishing a novel paradigm for universal modeling, cross-configuration knowledge sharing, and modular control of displacement-driven continuum robots.
📝 Abstract
In this paper, we consider an arbitrary number of joints and their arbitrary joint locations along the center line of a displacement-actuated continuum robot. To achieve this, we revisit the derivation of the Clarke transform leading to a formulation capable of considering arbitrary joint locations. The proposed modified Clarke transform opens new opportunities in mechanical design and algorithmic approaches beyond the current limiting dependency on symmetric arranged joint locations. By presenting an encoder-decoder architecture based on the Clarke transform, joint values between different robot designs can be transformed enabling the use of an analogous robot design and direct knowledge transfer. To demonstrate its versatility, applications of control and trajectory generation in simulation are presented, which can be easily integrated into an existing framework designed, for instance, for three symmetric arranged joints.