People Publications Research Robots Join

Check out the Google Scholar page for a full and up-to-date publication list. * denotes equal contribution.


Preprints
Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion
Tairan He*, Chong Zhang*, Wenli Xiao, Guanqi He, Changliu Liu, Guanya Shi
paper   website   IEEE Spectrum

TL;DR: ABS enables fully onboard, agile (>3m/s), and collision-free locomotion for quadrupedal robots in cluttered environments.


CoVO-MPC: Theoretical Analysis of Sampling-based MPC and Optimal Covariance Design
Zeji Yi*, Chaoyi Pan*, Guanqi He, Guannan Qu, Guanya Shi
paper   website   code

TL;DR: We quantify the convergence rate of sampling-based MPC, and design a practical and effective algorithm CoVO-MPC with optimal rate.


Model Predictive Control for Aggressive Driving Over Uneven Terrain
Tyler Han, Alex Liu, Anqi Li, Alex Spitzer, Guanya Shi, Byron Boots
paper   website

TL;DR: We design a terrain-aware MPC framework that enables agile driving over uneven offroad geometries such as hills, banks, and ditches.


Guardians as You Fall: Active Mode Transition for Safe Falling
Yikai Wang, Mengdi Xu, Guanya Shi, Ding Zhao
paper   website   code   video

TL;DR: GYF is a safe falling and recovery framework that can actively tumble and recover to stable modes to reduce damage.



2024
Hierarchical Meta-learning-based Adaptive Controller
Fengze Xie, Guanya Shi, Michael O'Connell, Yisong Yue, Soon-Jo Chung
International Conference on Robotics and Automation (ICRA), 2024
paper   website

TL;DR: HMAC handles both manageable and latent disturbances with hierarchical iterative learning and smoothed streaming meta-learning.


Safe Deep Policy Adaptation
Wenli Xiao*, Tairan He*, John Dolan, Guanya Shi
International Conference on Robotics and Automation (ICRA), 2024
paper   website   video

TL;DR: SafeDPA jointly tackles the problems of policy adaptation and safe reinforcement learning, under unseen disturbances in the real world.


Deep Model Predictive Optimization
Jacob Sacks, Rwik Rana, Kevin Huang, Alex Spitzer, Guanya Shi, Byron Boots
International Conference on Robotics and Automation (ICRA), 2024
paper   website   code

TL;DR: DMPO learns the inner-loop optimizer of sampling-based MPC directly via experience, outperforming MPC and end-to-end RL baselines.


Aerial Interaction with Tactile Sensing
Xiaofeng Guo, Guanqi He, Mohammadreza Mousaei, Junyi Geng, Guanya Shi, Sebastian Scherer
International Conference on Robotics and Automation (ICRA), 2024
paper   website

TL;DR: We introduce a new aerial manipulation system that leverages tactile feedback for accurate contact force control and texture detection.



2023
Optimal Exploration for Model-based RL in Nonlinear Systems
Andrew Wagenmaker, Guanya Shi, Kevin Jamieson
Neural Information Processing Systems (NeurIPS), 2023

(Spotlight, 3.1%)

paper

TL;DR: Not all model parameters are equally important. We develop an instance-optimal exploration algorithm for MBRL in nonlinear systems.


Active Representation Learning for General Task Space with Applications in Robotics
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.


DATT: Deep Adaptive Trajectory Tracking for Quadrotor Control
Kevin Huang, Rwik Rana, Alexander Spitzer, Guanya Shi, Byron Boots
Conference on Robot Learning (CoRL), 2023

(Oral presentation, 6.6%)

paper   website   code

TL;DR: DATT can precisely track arbitrary, potentially infeasible trajectories in the presence of large disturbances.


CAJun: Continuous Adaptive Jumping using a Learned Centroidal Controller
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.


Leveraging Predictions in Power System Frequency Control: an Adaptive Approach
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.



2022
Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds
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.


Online Optimization with Feedback Delay and Nonlinear Switching Cost
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.


Robustness and Consistency in Linear Quadratic Control with Predictions
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).


Competitive Control with Delayed Imperfect Information
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.



2021
Perturbation-based Regret Analysis of Predictive Control in LTV Systems
Yiheng Lin*, Yang Hu*, Guanya Shi*, Haoyuan Sun*, Guannan Qu*, Adam Wierman
Neural Information Processing Systems (NeurIPS), 2021

(Spotlight, 2.9%)

paper   blog

TL;DR: We prove MPC's dynamic regret and competitive ratio exponentially improve as its prediction gets longer, in LTV systems.


Meta-Adaptive Nonlinear Control: Theory and Algorithms
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.


Fast Uncertainty Quantification for Deep Object Pose Estimation
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.


Neural-Swarm2: Planning and Control of Heterogeneous Multirotor Swarms Using Learned Interactions
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.



2020
Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems
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.


Robust Regression for Safe Exploration in Control
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.


The Power of Predictions in Online Control
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.


Online Optimization with Memory and Competitive Control
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.


Neural-Swarm: Decentralized Close-Proximity Multirotor Control Using Learned Interactions
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.



2019
Neural Lander: Stable Drone Landing Control Using Learned Dynamics
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.



2018
Car-following Method Based on Inverse Reinforcement Learning for Autonomous Vehicle Decision-making
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.