Alexander Schperberg
- Phone: 617-621-7589
- Email:
-
Position:
Research / Technical Staff
Research Scientist -
Education:
Ph.D., University of California, Los Angeles, 2024 -
Research Areas:
External Links:
Alexander's Quick Links
-
Biography
Alexander's background includes extensive experience in employing hybrid machine-learning and model-based approaches towards planning, control, and estimation in both simulation and hardware including legged, climbing, wheeled, and flying robots. His Ph.D work covers topics such as reinforcement learning, Active SLAM, stochastic model predictive control, force control for manipulation and grasping, and estimation using filtering methods combined with vision transformers and deep learning techniques. His current research interests focus on advancing learning methods, from traditional neural networks to large language models, through embedded
knowledge of the underlying physics of the environment, robots, and contacts between them. -
Recent News & Events
-
NEWS MERL Presents 4 Main Conference Papers and 6 Workshop Papers at ICML 2026 Date: July 6, 2026 - July 11, 2026
Where: COEX, Seoul, South Korea
MERL Contacts: Moitreya Chatterjee; Anoop Cherian; Stefano Di Cairano; Toshiaki Koike-Akino; Christopher R. Laughman; Jing Liu; Suhas Lohit; Kuan-Chuan Peng; Alexander Schperberg; Ye Wang; Gordon Wichern
Research Areas: Artificial Intelligence, Computer Vision, Machine Learning, Signal ProcessingBrief- MERL researchers are proud to present 4 main conference papers and 6 workshop papers at ICML 2026. ICML, taking place from July 6-11 in Seoul, South Korea, is a premier international conference in machine learning.
Main Conference Papers with MERL Authors:
1. Understanding Dynamic Compute Allocation in Recurrent Transformers by Ibraheem Muhammad Moosa, Suhas Lohit, Ye Wang, Moitreya Chatterjee, and Wenpeng Yin.
2. LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior by Qinhong Zhou, Chuang Gan, and Anoop Cherian.
3. Memory-Distilled Selection for Noise-Robust Anomaly Detection by Sirojbek Safarov, Jaewoo Park, Yoon G. Jung, Kuan-Chuan Peng, Wonchul Kim, Seongdeok Bang, and Octavia Camps.
4. Partial Ring Scan: Revisiting Scan Order in Vision State Space Models by Yi-Kuan Hsieh, Kuan-Chuan Peng, Xin Li, Ming-Ching Chang, Yu-Chee Tseng, and Jun-Wei Hsieh.
Workshop Papers with MERL Authors:
1. WISE: Weighted Iterative Society-of-Experts for Multimodal Multi-Agent Debate with Probabilistic Consensus by Anoop Cherian, Suhas Lohit, and Kuan-Chuan Peng. (Workshop on Scalable Learning and Optimization for Efficient Multimodal AI Agents (SCALE))
2. MIRROR: Multisensory Implicit Rejection-sampled RObotic policy by Amisha Bhaskar, Pratap Tokekar, Stefano Di Cairano, and Alexander Schperberg. (Workshop on Structured Probabilistic Inference & Generative Modeling)
3. Reinforced Neural Processes: Memory-Efficient Time-Series Forecasting with a World-Feedback-Trained Memory Policy by Nibraas Khan, Gordon Wichern, and Christopher R. Laughman. (Workshop on Reinforcement Learning from World Feedback (RLxF))
4. Connecting Low-Rank Adapters and Policy Stability in GRPO Fine-Tuning by Antonin Rottman, Francesco Tonin, Yongtao Wu, Toshiaki Koike-Akino, and Volkan Cevher. (Workshop on Connecting Low-rank Representations in AI (CoLorAI))
5. EinSort: Sorting is All We Need for Tensorizing LLM by Toshiaki Koike-Akino, Jing Liu, and Ye Wang. (Workshop on Connecting Low-rank Representations in AI (CoLorAI))
6. Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment by Ye Wang, and Jing Liu, and Toshiaki Koike-Akino. (Workshop on Agents in the Wild: Safety, Security, and Beyond)
- MERL researchers are proud to present 4 main conference papers and 6 workshop papers at ICML 2026. ICML, taking place from July 6-11 in Seoul, South Korea, is a premier international conference in machine learning.
-
NEWS MERL researchers present 9 papers at IEEE ICRA 2026 Date: June 1, 2026 - June 5, 2026
Where: Vienna, Austria
MERL Contacts: Radu Corcodel; Stefano Di Cairano; Purnanand Elango; Siddarth Jain; Alexander Schperberg; Kento Tomita
Research Areas: Artificial Intelligence, Computer Vision, Control, Dynamical Systems, Machine Learning, Optimization, RoboticsBrief- MERL researchers presented nine papers at the recently concluded IEEE International Conference on Robotics and Automation (ICRA) 2026 in Vienna, Austria. The papers covered a broad set of topics in robotics, including robot perception, visuo-tactile sensing, contact and pose estimation, manipulation, reinforcement learning, diffusion policies, loco-manipulation, contact-implicit trajectory optimization, legged locomotion, localization, and perception-aware planning.
IEEE ICRA is the flagship conference of the IEEE Robotics and Automation Society and the world’s largest and most comprehensive technical conference focused on research advances and the latest technological developments in robotics. The event attracts nearly 8,000 participants and receives more than 5,000 paper submissions.
- MERL researchers presented nine papers at the recently concluded IEEE International Conference on Robotics and Automation (ICRA) 2026 in Vienna, Austria. The papers covered a broad set of topics in robotics, including robot perception, visuo-tactile sensing, contact and pose estimation, manipulation, reinforcement learning, diffusion policies, loco-manipulation, contact-implicit trajectory optimization, legged locomotion, localization, and perception-aware planning.
-
-
MERL Publications
- , "MIRROR: Multisensory Implicit Rejection-sampled RObotic policy", ICML 2026 Workshop on Structured Probabilistic Inference & Generative Modeling, July 2026.BibTeX TR2026-096 PDF
- @inproceedings{Bhaskar2026jul,
- author = {Bhaskar, Amisha and Tokekar, Pratap and {Di Cairano}, Stefano and Schperberg, Alexander},
- title = {{MIRROR: Multisensory Implicit Rejection-sampled RObotic policy}},
- booktitle = {ICML 2026 Workshop on Structured Probabilistic Inference \& Generative Modeling},
- year = 2026,
- month = jul,
- url = {https://www.merl.com/publications/TR2026-096}
- }
- , "RoboAtlas: Contextual Active SLAM", arXiv, June 2026.
- , "Safe Whole-Body Loco-Manipulation via Combined Model and Learning-based Control", IEEE International Conference on Robotics and Automation (ICRA), June 2026.BibTeX TR2026-072 PDF Video
- @inproceedings{Schperberg2026jun,
- author = {Schperberg, Alexander and Wang, Yeping and {Di Cairano}, Stefano},
- title = {{Safe Whole-Body Loco-Manipulation via Combined Model and Learning-based Control}},
- booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
- year = 2026,
- month = jun,
- url = {https://www.merl.com/publications/TR2026-072}
- }
- , "GRAM: Generalization in Deep RL with a Robust Adaptation Module", IEEE Robotics and Automation Letters (RA-L), May 2026.BibTeX TR2026-057 PDF
- @article{Queeney2026may,
- author = {Queeney, James and Cai, Xiaoyi and Schperberg, Alexander and Corcodel, Radu and Benosman, Mouhacine and How, Jonathan},
- title = {{GRAM: Generalization in Deep RL with a Robust Adaptation Module}},
- journal = {IEEE Robotics and Automation Letters (RA-L)},
- year = 2026,
- month = may,
- url = {https://www.merl.com/publications/TR2026-057}
- }
- , "MOBIUS: A Multi-Modal Bipedal Robot that can Walk, Crawl, Climb, and Roll", arXiv, November 2025.BibTeX arXiv
- @article{Schperberg2025nov,
- author = {Schperberg, Alexander and Tanaka, Yusuke and {Di Cairano}, Stefano and Hong, Dennis},
- title = {{MOBIUS: A Multi-Modal Bipedal Robot that can Walk, Crawl, Climb, and Roll}},
- journal = {arXiv},
- year = 2025,
- month = nov,
- url = {https://arxiv.org/abs/2511.01774}
- }
- , "MIRROR: Multisensory Implicit Rejection-sampled RObotic policy", ICML 2026 Workshop on Structured Probabilistic Inference & Generative Modeling, July 2026.
-
Other Publications
- , "Adaptive Force Controller for Contact-Rich Robotic Systems using an Unscented Kalman Filter", IEEE/RSJ International Conference on Intelligent Robots and Systems (Humanoids), December 2024.BibTeX
- @Inproceedings{schperberg2024adaptive,
- author = {Schperberg, Alexander and Shirai, Yusuke and Lin, X. and Tanaka, Yusuke and Hong, Dennis},
- title = {Adaptive Force Controller for Contact-Rich Robotic Systems using an Unscented Kalman Filter},
- booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (Humanoids)},
- year = 2024,
- month = dec
- }
- , "Towards Intelligent Robotic Systems: Unifying Model-based Optimization and Machine Learning for Planning, Control, and Estimation", June 2024, University of California, Los Angeles.BibTeX
- @Other{schperberg2024thesis,
- author = {Schperberg, Alexander V.},
- title = {Towards Intelligent Robotic Systems: Unifying Model-based Optimization and Machine Learning for Planning, Control, and Estimation},
- school = {University of California, Los Angeles},
- year = 2024,
- month = jun
- }
- , "Planning, Control, and Estimation of a Complex and Underactuated Multi-Modal Robot", ICRA 2024 Workshop: Unconventional Robots: Universal Lessons for Designing Unique Systems, May 2024.BibTeX
- @Inproceedings{schperberg2024complex,
- author = {Schperberg, Alexander and Tanaka, Yusuke and Hong, Dennis},
- title = {Planning, Control, and Estimation of a Complex and Underactuated Multi-Modal Robot},
- booktitle = {ICRA 2024 Workshop: Unconventional Robots: Universal Lessons for Designing Unique Systems},
- year = 2024,
- address = {Yokohama, Japan},
- month = may
- }
- , "OptiState: State Estimation of Legged Robots using Gated Networks with Transformer-based Vision and Kalman Filtering", IEEE International Conference on Robotics and Automation (ICRA), May 2024.BibTeX
- @Inproceedings{schperberg2024optistate,
- author = {Schperberg, Alexander and Tanaka, Yusuke and Mowlavi, Soheil and Xu, Feng and Balaji, Balaji and Hong, Dennis},
- title = {OptiState: State Estimation of Legged Robots using Gated Networks with Transformer-based Vision and Kalman Filtering},
- booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
- year = 2024,
- month = may
- }
- , "Exploring the Potentials of Multi-Modal Robotics with SCALER-B", ICRA 2024 Workshop: Unconventional Robots: Universal Lessons for Designing Unique Systems, May 2024.BibTeX
- @Inproceedings{schperberg2024scalerb,
- author = {Tanaka, Yusuke and Schperberg, Alexander and Hong, Dennis},
- title = {Exploring the Potentials of Multi-Modal Robotics with SCALER-B},
- booktitle = {ICRA 2024 Workshop: Unconventional Robots: Universal Lessons for Designing Unique Systems},
- year = 2024,
- address = {Yokohama, Japan},
- month = may
- }
- , "Planner for Robotic Free-Climbing using Reinforcement Learning", Southern California Robotics Symposium (SCR), September 2023.BibTeX
- @Inproceedings{schperberg2023planner,
- author = {Schperberg, Alexander and Tanaka, Yusuke and Xu, Feng and Khan, Arash and Balaji, Balaji and Hong, Dennis},
- title = {Planner for Robotic Free-Climbing using Reinforcement Learning},
- booktitle = {Southern California Robotics Symposium (SCR)},
- year = 2023,
- month = sep
- }
- , "Real-to-Sim: Predicting Residual Error of Robotic Systems using a Learning-based Unscented Kalman Filter", IEEE 20th International Conference on Ubiquitous Robots (UR), June 2023.BibTeX
- @Inproceedings{schperberg2023real_to_sim,
- author = {Schperberg, Alexander and Tanaka, Yusuke and Xu, Feng and Menner, Maximilian and Hong, Dennis},
- title = {Real-to-Sim: Predicting Residual Error of Robotic Systems using a Learning-based Unscented Kalman Filter},
- booktitle = {IEEE 20th International Conference on Ubiquitous Robots (UR)},
- year = 2023,
- month = jun
- }
- , "Learning Near-global-optimal Strategies for Hybrid Non-convex Model Predictive Control of Single Rigid Body Locomotion", arXiv preprint arXiv:2207.07846, June 2022.BibTeX
- @Article{lin2022near_optimal,
- author = {Lin, X. and Xu, Feng and Schperberg, Alexander and Hong, Dennis},
- title = {Learning Near-global-optimal Strategies for Hybrid Non-convex Model Predictive Control of Single Rigid Body Locomotion},
- journal = {arXiv preprint arXiv:2207.07846},
- year = 2022,
- month = jun
- }
- , "Simultaneous Efficient Contact-Rich Grasping and Locomotion Optimization Enabling Free-Climbing for Multi-Limbed Robots", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), March 2022.BibTeX
- @Inproceedings{shirai2022contact_optimization,
- author = {Shirai, Yusuke and Lin, X. and Schperberg, Alexander and Tanaka, Yusuke and Kato, H. and Vichathorn, V. and Hong, Dennis},
- title = {Simultaneous Efficient Contact-Rich Grasping and Locomotion Optimization Enabling Free-Climbing for Multi-Limbed Robots},
- booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
- year = 2022,
- month = mar
- }
- , "SCALER: A Tough Versatile Quadruped Free-Climber Robot", 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), March 2022.BibTeX
- @Inproceedings{tanaka2022scaler,
- author = {Tanaka, Yusuke and Shirai, Yusuke and Lin, X. and Schperberg, Alexander and Kato, H. and Swerdlow, A. and Kumagai, N. and Hong, Dennis},
- title = {SCALER: A Tough Versatile Quadruped Free-Climber Robot},
- booktitle = {2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
- year = 2022,
- month = mar
- }
- , "SABER: Data-Driven Motion Planner for Autonomously Navigating Heterogeneous Robots", IEEE Robotics and Automation Letters (RA-L), May 2021.BibTeX
- @Article{schperberg2024saber,
- author = {Schperberg, Alexander and Tsuei, S. and Soatto, Stefano and Hong, Dennis},
- title = {SABER: Data-Driven Motion Planner for Autonomously Navigating Heterogeneous Robots},
- journal = {IEEE Robotics and Automation Letters (RA-L)},
- year = 2021,
- month = may
- }
- , "Synthetic lethality-mediated precision oncology via the tumor transcriptome", Cell, Vol. 184, No. 9, pp. 2487-2502.e13, 2021.BibTeX
- @Article{lee2021synthetic_lethality,
- author = {Lee, J. S. and Lee, N. U. and Nair, G. and Dinstag, L. and Chapman, Y. and Chung, K. and Wang, S. and Sinha, H. and Cha, D. and Kim, A. V. and Schperberg, Alexander and Srinivasan, V. and Lazar, E. and Rubin, S. and Hwang, R. and Berger, T. and Beker, Z. and Ronai, S. and Hannenhalli, M. R. and Kurzrock, S.-H.},
- title = {Synthetic lethality-mediated precision oncology via the tumor transcriptome},
- journal = {Cell},
- year = 2021,
- volume = 184,
- number = 9,
- pages = {2487--2502.e13}
- }
- , "Risk-Averse MPC via Visual-Inertial Input and Recurrent Networks for Online Collision Avoidance", 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), November 2020.BibTeX
- @Inproceedings{schperberg2020risk_averse,
- author = {Schperberg, Alexander and Chen, K. and Tsuei, S. and Jewett, M. and Hooks, J. and Soatto, Stefano and Mehta, Aaron and Hong, Dennis},
- title = {Risk-Averse MPC via Visual-Inertial Input and Recurrent Networks for Online Collision Avoidance},
- booktitle = {2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
- year = 2020,
- month = nov
- }
- , "Machine learning model to predict oncologic outcomes for drugs in randomized clinical trials", International Journal of Cancer, pp. 1-13, 2020.BibTeX
- @Article{schperberg2020oncology,
- author = {Schperberg, Alexander and Boichard, Alice and Tsigelny, Igor and Richard, Shumei and Kurzrock, Razelle},
- title = {Machine learning model to predict oncologic outcomes for drugs in randomized clinical trials},
- journal = {International Journal of Cancer},
- year = 2020,
- pages = {1--13}
- }
- , "Reducing Motion Perturbation for a Bipedal Robot using Model Predictive Control", September 2019.BibTeX
- @Misc{schperberg2019bipedal_mpc,
- author = {Schperberg, Alexander and Shirai, Yusuke and Tanaka, Yusuke},
- title = {Reducing Motion Perturbation for a Bipedal Robot using Model Predictive Control},
- year = 2019,
- month = sep
- }
- , "Resting State and Task-Related Brain Dynamics Supporting Creativity", Neuroscience 2018 Conference, 2018.BibTeX
- @Inproceedings{raj2018brain_dynamics,
- author = {Raj, S. and Schperberg, Alexander and Tsai, B. and Brown, S. and Jung, T.P. and Wu, Y.},
- title = {Resting State and Task-Related Brain Dynamics Supporting Creativity},
- booktitle = {Neuroscience 2018 Conference},
- year = 2018
- }
- , "MoBI-Box: A next generation Mobile Brain-Body Imaging Platform", 2016 IEEE International Multi-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support (CogSIMA), 2016, pp. 93-96.BibTeX
- @Inproceedings{wu2016mobibox,
- author = {Wu, Y. and Wang, J. and Tran, A. and Schperberg, Alexander and Caldwell, J. and Jung, T.P. and Kuo, P.C.},
- title = {MoBI-Box: A next generation Mobile Brain-Body Imaging Platform},
- booktitle = {2016 IEEE International Multi-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support (CogSIMA)},
- year = 2016,
- pages = {93--96},
- address = {San Diego, CA, USA}
- }
- , "Adaptive Force Controller for Contact-Rich Robotic Systems using an Unscented Kalman Filter", IEEE/RSJ International Conference on Intelligent Robots and Systems (Humanoids), December 2024.
-
Videos
-
MERL Issued Patents
-
Title: "Task-Specific and Environment-Specific Adaptive Control of Legged Robot"
Inventors: Menner, Marcel; Di Cairano, Stefano; Schperberg, Alexander
Patent No.: 12,474,705
Issue Date: Nov 18, 2025
-
Title: "Task-Specific and Environment-Specific Adaptive Control of Legged Robot"