Journal Articles
Bridging the model-reality gap with Lipschitz network adaptation
S. Zhou, K. Pereida, W. Zhao, and A. P. Schoellig
in the IEEE Robotics and Automation Letters (RA-L)
arXiv preprint: 2112.03756 | final version
Safe learning in robotics: from learning-based control to safe reinforcement learning
L. Brunke*, M. Greeff*, A. W. Hall*, Z. Yuan*, S. Zhou*, J. Panerati, and A. P. Schoellig
in Annual Review of Control, Robotics, and Autonomous Systems 2021
arXiv preprint: 2108.06266
*equal contribution
Deep neural networks as add-on modules for enhancing robot performance in impromptu trajectory tracking
S. Zhou, M. K. Helwa, and A. P. Schoellig
in the International Journal of Robotics Research (IJRR) 2020
preprint | final version | video
To share or not to share? Performance guarantees and the asymmetric nature of cross-robot experience transfer
M. J. Sorocky, S. Zhou, and A. P. Schoellig
in the IEEE Control Systems Letters (L-CSS) 2020 and presented at the IEEE Conference on Decision and Control (CDC) 2020
arXiv preprint: 2006.16126 | final version | video
An inversion-based learning approach for improving impromptu trajectory tracking of robots with non-minimum phase dynamics
S. Zhou, M. K. Helwa, and A. P. Schoellig
in the IEEE Robotics and Automation Letters (RA-L) 2018
arXiv preprint: 1709.04407 | final version
Conference Papers
RLO-MPC: Robust learning-based output feedback MPC for improving the performance of uncertain systems in iterative tasks
L. Brunke, S. Zhou and A. P. Schoellig
presented at the IEEE Conference on Decision and Control (CDC) 2021
arXiv preprint: 2110.00542
Learning to fly: A Gym environment with PyBullet physics for reinforcement learning of multi-agent quadcopter control
J. Panerati, H. Zheng, S. Zhou, J. Xu, A. Prorok, and A. P. Schoellig
presented at the IEEE International Conference on Intelligent Robots and Systems (IROS) 2021
arXiv preprint: 2103.02142
Experience selection using dynamics similarity for efficient multi-source transfer learning between robots
M. J. Sorocky*, S. Zhou*, and A. P. Schoellig
presented at the IEEE International Conference on Robotics and Automation (ICRA) 2020
arXiv preprint: 2003.13150 | video | talk
*equal contribution
Active training trajectory generation for inverse dynamics model learning with deep neural networks
S. Zhou and A. P. Schoellig
presented at the IEEE Conference on Decision and Control (CDC) 2019
final version
Knowledge transfer between robots with similar dynamics for high-accuracy impromptu trajectory tracking
S. Zhou, A. Sarabakha, E. Kayacan, M. K. Helwa, and A. P. Schoellig
presented at the European Control Conference (ECC) 2019
arXiv preprint: 1904.00249 | video
Design of deep neural networks as add-on blocks for improving impromptu trajectory tracking
S. Zhou, M. K. Helwa, and A. P. Schoellig
presented at the IEEE Conference on Decision and Control (CDC) 2017
arXiv preprint: 1705.10932 | final version | video
Extended Abstracts
Knowledge Transfer Between Robots with Online Learning for Enhancing Robot Performance in Impromptu Trajectory Tracking
S. Zhou, A. Sarabakha, E. Kayacan, M. K. Helwa, and A. P. Schoellig
to be presented at the ICRA 2019 Workshop on Resilient Robot Teams: Composing, Acting, and Learning
abstract | poster | spotlight talk
Deep neural networks as add-on modules for high-accuracy impromptu trajectory tracking
S. Zhou, M. K. Helwa, and A. P. Schoellig
presented at the Conference on Robot Learning (CoRL) 2017
abstract | supplementary materials | spotlight talk video
A comparison of probabilistic population code and sampling-based code in neural state estimations
S. Zhou
presented at the Conference on Cognitive Computational Neuroscience (CCN) 2017
abstract | poster
Other Contributions
An analysis of the expressiveness of deep neural network architectures based on their Lipschitz constants
S. Zhou and A. P. Schoellig
arXiv preprint: 1912.11511