LBE-DDIK: Is One Model Good Enough to Learn-By-Example the Inverse Kinematics of Multiple Serial Robots?

Abstract

Data-Driven Inverse Kinematics (DDIK) solvers emerged as promising Inverse Kinematics (IK) methods for reliably approximating the IK of robotic manipulators. However, these solvers remain heavily robot-dependent, where for each robot of interest, a network needs to be trained in an one-solver-one-robot framework. In this paper, we build on our previous work on Learning-By-Example (LBE) for DDIK, and introduce an one-solver-many-robots framework; where a single neural network is used to predict the IK of multiple robots – mainly with 6 and 7 Degrees of Freedom (DoF). In our LBE approach, the neural network input includes an example of joint-pose tuple (e.g. any previous joint and corresponding pose tuple in the path) along with the queried pose as the same network outputs the desired robot joint configuration. Here, we investigate five network architectures: a Plain Multilayer Perceptron (MLP), a Residual-Based MLP (RMLP), a Densely Connected MLP (DMLP), and two transformers inspired by Generative Pre-Trained Transformer (GPT) and tested them using 3 diverse datasets with 20 real-world robotic arms with 6 and 7 DoF. Our experimental results demonstrate that a single lightweight, LBE-based DDIK solver can reliably predict the IK for multiple and hitherto unseen robots, within each of the 6 or 7DoF family as well as across both 6 and 7DoF robot families with position errors below 1mm and orientation errors below 1deg. Additionally, we compare all proposed LBE-DDIK solvers with three established numerical IK solvers: Selectively Damped Least-Squares (SD), Singular Value Filtering (SVF), and Mixed Inverse (MX) and observe that our LBE-DDIK solvers achieve comparable accuracy, with the advantage of being a one-solver-many-robots framework.