Companion Website for:

Curriculum is more influential than haptic feedback when learning object manipulation

Science Advances - May 2025

Link to PDF version from Valero Lab
Link to Science Advances Article
Link to Viterbi Press Release

Learning to lift and rotate objects with the fingertips is necessary for autonomous in-hand dexterous manipulation. In our study, we explore the impact of various factors on successful learning strategies for this task. Specifically, we investigate the role of curriculum learning and haptic feedback in enabling the learning of dexterous manipulation. Using model-free Reinforcement Learning, we compare different curricula and two haptic information modalities (No-tactile vs. 3D-force sensing) for lifting and rotating a ball against gravity with a three-fingered simulated robotic hand with no visual input. Note that our best results were obtained when we used a novel curriculum based learning rate scheduler, which adjusts the linearly-decaying learning rate when the reward is changed as it accelerates convergence to higher rewards. Our findings demonstrate that the choice of curriculum greatly biases the acquisition of different features of dexterous manipulation. Surprisingly, successful learning can be achieved even in the absence of tactile feedback, challenging conventional assumptions about the necessity of haptic information for dexterous manipulation tasks. We demonstrate the generalizability of our results to balls of different weights and sizes, underscoring the robustness of our learning approach. This work, therefore, emphasizes the importance of the choice curriculum and challenges long-held notions about the need for tactile information to autonomously learn in-hand dexterous manipulation.

Citation

Ojaghi, P., Mir, R., Marjaninejad, A., Erwin, A., Wehner, M., & Valero-Cuevas, F. J. (2025). Curriculum is more influential than haptic feedback when learning object manipulation. Science Advances, 11(14), eadp8407.

Acknowledgements

In this collaboration between the Viterbi School of Engineering and the University of California in Santa Cruz (UCSC), doctoral students Parmita Ojaghi (UCSC) and Romina Mir (USC) co-led this work in collaboration with Profs. Francisco Valero-Cuevas (UCS) and Michael Wehner (UCSC). Drs. Ali Marjaninejad and Andrew Erwin (USC) also contributed to this work.

For questions and more information, please send us an email: [email protected]