The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"

Open-source datasets for serial robot calibration, collected for a Master's thesis on enhancing pose accuracy of UR5 and Barrett WAM robots using a hybrid MDH-ASTGCN method. Includes calibration/training data (grid-like poses) and test data (random poses) with different compensation results. Open-source for research use.