![]() |
People | Publications | Research | Robots |
Check out the Google Scholar page for a full and up-to-date publication list. * denotes equal contribution. |
|
![]() |
Andrew Wagenmaker, Guanya Shi, Kevin Jamieson Neural Information Processing Systems (NeurIPS), 2023 (Spotlight) paperTL;DR: Not all model parameters are equally important. We develop an instance-optimal exploration algorithm for MBRL in nonlinear systems. |
![]() |
Yifang Chen, Yingbing Huang, Simon S. Du, Kevin Jamieson, Guanya Shi Neural Information Processing Systems (NeurIPS), 2023 paper TL;DR: Inspired by robotics applications, we study algorithms for active representation learning with continuous task parametrization. |
![]() ![]() |
Kevin Huang, Rwik Rana, Alexander Spitzer, Guanya Shi, Byron Boots Conference on Robot Learning (CoRL), 2023 (Oral presentation, 6.6%) paper (coming soon)   websiteTL;DR: DATT can precisely track arbitrary, potentially infeasible trajectories in the presence of large disturbances. |
![]() |
Yuxiang Yang, Guanya Shi, Xiangyun Meng, Wenhao Yu, Tingnan Zhang, Jie Tan, Byron Boots Conference on Robot Learning (CoRL), 2023 paper   video   website   code TL;DR: CAJun is a hierarchical learning and control framework that enables legged robots to jump continuously with adaptive distances. |
![]() |
Wenqi Cui, Guanya Shi, Yuanyuan Shi, Baosen Zhang IEEE Conference on Decision and Control (CDC), 2023 paper TL;DR: We combine adaptive nonlinear control and neural control for frequency restoration in power systems. |
|
![]() |
Michael O'Connell*, Guanya Shi*, Xichen Shi, Kamyar Azizzadenesheli, Animashree Anandkumar, Yisong Yue, Soon-Jo Chung Science Robotics paper   video   Caltech news   Reuters   CNN   code TL;DR: Neural-Fly uses adaptive control to online fine-tune a meta-pretrained DNN representation, enabling rapid adaptation in strong winds. |
![]() |
Weici Pan, Guanya Shi, Yiheng Lin, Adam Wierman Proceedings of the ACM on Measurement and Analysis of Computing Systems (SIGMETRICS) paper TL;DR: We propose a new online optimization setting with delay and nonlinear switching cost, and provide compeititve algorithms. |
![]() |
Tongxin Li, Ruixiao Yang, Guannan Qu, Guanya Shi, Chenkai Yu, Adam Wierman, Steven Low Proceedings of the ACM on Measurement and Analysis of Computing Systems (SIGMETRICS) paper TL;DR: For online control with noisy predictions, we design an algorithm to optimally balance robustness and consistency (performance if no noise). |
![]() |
Chenkai Yu, Guanya Shi, Soon-Jo Chung, Yisong Yue, Adam Wierman American Control Conference (ACC), 2022 paper   blog TL;DR: We study MPC's dynamic regret and competitive ratio in the presence of prediction inaccuracy and feedback delay. |
|
![]() |
Yiheng Lin*, Yang Hu*, Guanya Shi*, Haoyuan Sun*, Guannan Qu*, Adam Wierman Neural Information Processing Systems (NeurIPS), 2021 (Spotlight, 2.9%) paper   blogTL;DR: We prove MPC's dynamic regret and competitive ratio exponentially improve as its prediction gets longer, in LTV systems. |
![]() |
Guanya Shi, Kamyar Azizzadenesheli, Michael O'Connell, Soon-Jo Chung, Yisong Yue Neural Information Processing Systems (NeurIPS), 2021 paper   code TL;DR: We present an online multi-task learning approach for adaptive nonlinear control with non-asymptotic guarantees. |
![]() |
Guanya Shi, Yifeng Zhu, Jonathan Tremblay, Stan Birchfield, Fabio Ramos, Animashree Anandkumar, Yuke Zhu International Conference on Robotics and Automation (ICRA), 2021 paper   website   blog   code TL;DR: We develop a simple and efficient UQ method for 6-DoF pose estimation, and apply it in real-world grasping tasks. |
![]() |
Guanya Shi, Wolfgang Hönig, Xichen Shi, Yisong Yue, Soon-Jo Chung IEEE Transactions on Robotics paper   video   Caltech news   Yahoo! news   code TL;DR: Neural-Swarm is a learning-based controller and planner for close-proximity flight of heterogeneous multirotor swarms. |
|
![]() |
Yashwanth Kumar Nakka, Anqi Liu, Guanya Shi, Animashree Anandkumar, Yisong Yue, Soon-Jo Chung IEEE Robotics and Automation Letters (RA-L) paper   blog TL;DR: We derive an iterative algorithm to solve information-cost stochastic nonlinear optimal control problems for safe episodic learning. |
![]() |
Anqi Liu, Guanya Shi, Soon-Jo Chung, Animashree Anandkumar, Yisong Yue Conference on Learning for Dynamics and Control (L4DC), 2020 paper TL;DR: We derive generalization bounds under domain shift and connect them with safety bounds in control, for end-to-end safe explorations. |
![]() |
Chenkai Yu, Guanya Shi, Soon-Jo Chung, Yisong Yue, Adam Wierman Neural Information Processing Systems (NeurIPS), 2020 paper   video   blog TL;DR: We give the first non-asymptotic guarantee for MPC. MPC's dynamic regret exponentially decreases as its prediction gets longer. |
![]() |
Guanya Shi*, Yiheng Lin*, Soon-Jo Chung, Yisong Yue, Adam Wierman Neural Information Processing Systems (NeurIPS), 2020 paper TL;DR: We show competitive algorithms for a new class of online optimization problems, with applications in online competitive control. |
![]() |
Guanya Shi, Wolfgang Hönig, Yisong Yue, Soon-Jo Chung International Conference on Robotics and Automation (ICRA), 2020 paper   video   TL;DR: We deploy Deep Sets to learn complex interactions between multirotors, for decentralized close-proximity control. |
|
![]() |
Guanya Shi*, Xichen Shi*, Michael O'Connell*, Rose Yu, Kamyar Azizzadenesheli, Animashree Anandkumar, Yisong Yue, Soon-Jo Chung International Conference on Robotics and Automation (ICRA), 2019 paper   video   Caltech homepage news   code TL;DR: Spectrally normalized deep learning and nonlinear control enable provably stable agile drone landing. |
|
![]() |
Hongbo Gao, Guanya Shi, Guotao Xie, Bo Cheng International Journal of Advanced Robotic Systems paper TL;DR: We use inverse RL to learn reward models for human-like autonomous car following. |