The Road to Learning Explainable Inverse Kinematic Models: Graph Neural Networks as Inductive Bias for Symbolic Regression
This work addresses the challenge of creating interpretable and generalizable inverse kinematics models for robotics, though it is incremental as it builds on existing GNN and symbolic regression methods.
This paper tackles the problem of learning explainable inverse kinematic models for robotic manipulators by using a Graph Neural Network (GNN) to generate models that generalize across manipulators with the same degree of freedom but varying link lengths, achieving position errors of less than 1.0 cm for 3 DOF and 4.5 cm for 5 DOF, and orientation errors of 2° for 3 DOF and 8.2° for 6 DOF.
This paper shows how a Graph Neural Network (GNN) can be used to learn an Inverse Kinematics (IK) based on an automatically generated dataset. The generated Inverse Kinematics is generalized to a family of manipulators with the same Degree of Freedom (DOF), but varying link length configurations. The results indicate a position error of less than 1.0 cm for 3 DOF and 4.5 cm for 5 DOF, and orientation error of 2$^\circ$ for 3 DOF and 8.2$^\circ$ for 6 DOF, which allows the deployment to certain real world-problems. However, out-of-domain errors and lack of extrapolation can be observed in the resulting GNN. An extensive analysis of these errors indicates potential for enhancement in the future. Consequently, the generated GNNs are tailored to be used in future work as an inductive bias to generate analytical equations through symbolic regression.