More Like this

1. Adaptive-Control-Oriented Meta-Learning for Nonlinear Systems

   Richards, S. M. ; Azizan, N. ; Slotine, J.-J. E. ; Pavone, M. ( July 2021 , Robotics science and systems)

   null (Ed.)

   Real-time adaptation is imperative to the control of robots operating in complex, dynamic environments. Adaptive control laws can endow even nonlinear systems with good trajectory tracking performance, provided that any uncertain dynamics terms are linearly parameterizable with known nonlinear features. However, it is often difficult to specify such features a priori, such as for aerodynamic disturbances on rotorcraft or interaction forces between a manipulator arm and various objects. In this paper, we turn to data-driven modeling with neural networks to learn, offline from past data, an adaptive controller with an internal parametric model of these nonlinear features. Our key insight is that we can better prepare the controller for deployment with control-oriented meta-learning of features in closed-loop simulation, rather than regression-oriented meta-learning of features to fit input-output data. Specifically, we meta-learn the adaptive controller with closed-loop tracking simulation as the base-learner and the average tracking error as the meta-objective. With a nonlinear planar rotorcraft subject to wind, we demonstrate that our adaptive controller outperforms other controllers trained with regression-oriented meta-learning when deployed in closed-loop for trajectory tracking control. 

   more » « less
2. Inferring Task-Space Central Pattern Generator Parameters for Closed-loop Control of Underactuated Robots

   https://doi.org/10.1109/ICRA40945.2020.9196957  

   Kent, Nathan D. ; Bhirangi, Raunaq M. ; Travers, Matthew ; Howard, Thomas M. ( May 2020 , 2020 IEEE International Conference on Robotics and Automation (ICRA))

   The complexity associated with the control of highly-articulated legged robots scales quickly as the number of joints increases. Traditional approaches to the control of these robots are often impractical for many real-time applications. This work thus presents a novel sampling-based planning ap- proach for highly-articulated robots that utilizes a probabilistic graphical model (PGM) to infer in real-time how to optimally modify goal-driven, locomotive behaviors for use in closed-loop control. Locomotive behaviors are quantified in terms of the parameters associated with a network of neural oscillators, or rather a central pattern generator (CPG). For the first time, we show that the PGM can be used to optimally modulate different behaviors in real-time (i.e., to select of optimal choice of parameter values across the CPG model) in response to changes both in the local environment and in the desired control signal. The PGM is trained offline using a library of optimal behaviors that are generated using a gradient-free optimization framework. 

   more » « less
3. Optimizing Thermoacoustic Characterization Experiments for Identifiability Improves Both Parameter Estimation Accuracy and Closed-Loop Controller Robustness Guarantees

   https://doi.org/10.1080/00102202.2020.1858818  

   Chen, Xiaoling ; O’Connor, Jacqueline ; Fathy, Hosam ( January 2021 , Combustion Science and Technology)

   null (Ed.)

   This article examines the degree to which optimizing a Rijke tube experiment can improve the accuracy of thermoacoustic model parameter estimation, thereby facilitating robust stability control. We use a one-dimensional thermoacoustic model to describe the combustion dynamics in a Rijke tube. This model contains two unknown parameters that relate velocity perturbations to heat release rate oscillations, namely, a time delay τ and amplification factor β. The parameters are estimated from experiments where the system input is the acoustic excitation from a loudspeaker and the output is the pressure response captured by a microphone. Our work is grounded in the insight that optimizing an experiment’s design for higher Fisher identifiability leads to more accurate parameter estimates. The novel goal of this paper is to apply this insight in the laboratory using a flame-driven Rijke tube setup. For comparison purposes, we conduct a benchmark experiment with a broadband chirp signal as the excitation input. Next, we excite the Rijke tube at two frequencies optimized for Fisher identifiability. Repeats of both experiments show that the optimal experiment achieves parameter estimates with uncertainties at least one order of magnitude smaller than the benchmark. With smaller parameter estimate uncertainties, an LQG controller designed to attenuate combustion instabilities is able to achieve stronger robustness guarantees, quantified in terms of closed-loop structured singular values that account for parameter estimation uncertainty. 

   more » « less
4. Online Gain Adaptation of Whole-Body Control for Legged Robots with Unknown Disturbances

   https://doi.org/10.3389/frobt.2021.788902  

   Lee, Jaemin ; Ahn, Junhyeok ; Kim, Donghyun ; Bang, Seung Hyeon ; Sentis, Luis ( January 2022 , Frontiers in Robotics and AI)

   This paper proposes an online gain adaptation approach to enhance the robustness of whole-body control (WBC) framework for legged robots under unknown external force disturbances. Without properly accounting for external forces, the closed-loop control system incorporating WBC may become unstable, and therefore the desired task goals may not be achievable. To study the effects of external disturbances, we analyze the behavior of our current WBC framework via the use of both full-body and centroidal dynamics. In turn, we propose a way to adapt feedback gains for stabilizing the controlled system automatically. Based on model approximations and stability theory, we propose three conditions to ensure that the adjusted gains are suitable for stabilizing a robot under WBC. The proposed approach has four contributions. We make it possible to estimate the unknown disturbances without force/torque sensors. We then compute adaptive gains based on theoretic stability analysis incorporating the unknown forces at the joint actuation level. We demonstrate that the proposed method reduces task tracking errors under the effect of external forces on the robot. In addition, the proposed method is easy-to-use without further modifications of the controllers and task specifications. The resulting gain adaptation process is able to run in real-time. Finally, we verify the effectiveness of our method both in simulations and experiments using the bipedal robot Draco2 and the humanoid robot Valkyrie . 

   more » « less
5. Motion Planning for Agile Legged Locomotion using Failure Margin Constraints

   https://doi.org/10.1109/IROS47612.2022.9981903  

   Green, Kevin ; Warila, John ; Hatton, Ross L. ; Hurst, Jonathan ( October 2022 , 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS))

   The complex dynamics of agile robotic legged locomotion requires motion planning to intelligently adjust footstep locations. Often, bipedal footstep and motion planning use mathematically simple models such as the linear inverted pendulum, instead of dynamically-rich models that do not have closed-form solutions. We propose a real-time optimization method to plan for dynamical models that do not have closed form solutions and experience irrecoverable failure. Our method uses a data-driven approximation of the step-to-step dynamics and of a failure margin function. This failure margin function is an oriented distance function in state-action space where it describes the signed distance to success or failure. The motion planning problem is formed as a nonlinear program with constraints that enforce the approximated forward dynamics and the validity of state-action pairs. For illustration, this method is applied to create a planner for an actuated spring-loaded inverted pendulum model. In an ablation study, the failure margin constraints decreased the number of invalid solutions by between 24 and 47 percentage points across different objectives and horizon lengths. While we demonstrate the method on a canonical model of locomotion, we also discuss how this can be applied to data-driven models and full-order robot models. 

   more » « less