@article{zhou-ijrr20,
title = {Deep neural networks as add-on modules for enhancing robot performance in impromptu trajectory tracking},
author = {Siqi Zhou and Mohamed K. Helwa and Angela P. Schoellig},
journal = {{The International Journal of Robotics Research}},
year = {2020},
volume = {0},
number = {0},
pages = {1--22},
doi = {10.1177/0278364920953902},
urllink = {https://doi.org/10.1177/0278364920953902},
urlvideo = {https://youtu.be/K-DrZGFvpN4},
abstract = {High-accuracy trajectory tracking is critical to many robotic applications, including search and rescue, advanced manufacturing, and industrial inspection, to name a few. Yet the unmodeled dynamics and parametric uncertainties of operating in such complex environments make it difficult to design controllers that are capable of accurately tracking arbitrary, feasible trajectories from the first attempt (i.e., impromptu trajectory tracking). This article proposes a platform-independent,
learning-based ‘‘add-on’’ module to enhance the tracking performance of black-box control systems in impromptu tracking tasks. Our approach is to pre-cascade a deep neural network (DNN) to a stabilized baseline control system, in order to establish an identity mapping from the desired output to the actual output. Previous research involving quadrotors showed that, for 30 arbitrary hand-drawn trajectories, the DNN-enhancement control architecture reduces tracking errors by 43\% on average, as compared with the baseline controller. In this article, we provide a platform-independent formulation and practical design guidelines for the DNN-enhancement approach. In particular, we: (1) characterize the underlying function of the DNN module; (2) identify necessary conditions for the approach to be effective; (3) provide theoretical insights into the stability of the overall DNN-enhancement control architecture; (4) derive a condition that supports dataefficient training of the DNN module; and (5) compare the novel theory-driven DNN design with the prior trial-and-error design using detailed quadrotor experiments. We show that, as compared with the prior trial-and-error design, the novel theory-driven design allows us to reduce the input dimension of the DNN by two thirds while achieving similar tracking performance.}
}

@INPROCEEDINGS{sorocky-icra20,
author = {Michael J. Sorocky and Siqi Zhou and Angela P. Schoellig},
title = {Experience Selection Using Dynamics Similarity for Efficient Multi-Source Transfer Learning Between Robots},
booktitle = {{Proc. of the IEEE International Conference on Robotics and Automation (ICRA)}},
year = {2020},
pages = {2739--2745},
urllink = {https://ieeexplore.ieee.org/document/9196744},
urlvideo = {https://youtu.be/8m3mOkljujM},
abstract = {In the robotics literature, different knowledge transfer approaches have been proposed to leverage the experience from a source task or robot—real or virtual—to accelerate the learning process on a new task or robot. A commonly made but infrequently examined assumption is that incorporating experience from a source task or robot will be beneficial. For practical applications, inappropriate knowledge transfer can result in negative transfer or unsafe behaviour. In this work, inspired by a system gap metric from robust control theory, the nu-gap, we present a data-efficient algorithm for estimating the similarity between pairs of robot systems. In a multi-source inter-robot transfer learning setup, we show that this similarity metric allows us to predict relative transfer performance and thus informatively select experiences from a source robot before knowledge transfer. We demonstrate our approach with quadrotor experiments, where we transfer an inverse dynamics model from a real or virtual source quadrotor to enhance the tracking performance of a target quadrotor on arbitrary hand-drawn trajectories. We show that selecting experiences based on the proposed similarity metric effectively facilitates the learning of the target quadrotor, improving performance by 62\% compared to a poorly selected experience.},
}

@INPROCEEDINGS{zhou-cdc19,
author = {Siqi Zhou and Angela P. Schoellig},
title = {Active Training Trajectory Generation for Inverse Dynamics Model Learning with Deep Neural Networks},
booktitle = {{Proc. of the IEEE Conference on Decision and Control (CDC)}},
year = {2019},
pages = {1784--1790},
abstract = {Inverse dynamics models have been used in robot control algorithms to realize a desired motion or to enhance a robot’s performance. As robot dynamics and their operating environments become more complex, there is a growing trend of learning uncertain or unknown dynamics from data. While techniques such as deep neural networks (DNNs) have been successfully used to learn inverse dynamics, it is usually implicitly assumed that the learning modules are trained on sufficiently rich datasets. In practical implementations, this assumption typically results in a trial-and-error training process, which can be inefficient or unsafe for robot applications. In this paper, we present an active trajectory generation framework that allows us to systematically design informative trajectories for training DNN inverse dynamics modules. In particular, we introduce an episode-based algorithm that integrates a spline trajectory optimization approach with DNN active learning for efficient data collection. We consider different DNN uncertainty estimation techniques and active learning heuristics in our work and illustrate the proposed active training trajectory generation approach in simulation. We show that the proposed active training trajectory generation outperforms adhoc, intuitive training approaches.},
}

@INPROCEEDINGS{zhou-ecc19,
author = {Siqi Zhou and Andriy Sarabakha and Erdal Kayacan and Mohamed K. Helwa and Angela P. Schoellig},
title = {Knowledge Transfer Between Robots with Similar Dynamics for High-Accuracy Impromptu Trajectory Tracking},
booktitle = {{Proc. of the European Control Conference (ECC)}},
year = {2019},
pages = {1--8},
urlvideo = {https://youtu.be/Pj_irRLHsD8},
abstract = {In this paper, we propose an online learning approach that enables the inverse dynamics model learned for a source robot to be transferred to a target robot (e.g., from one quadrotor to another quadrotor with different mass or aerodynamic properties). The goal is to leverage knowledge from the source robot such that the target robot achieves high-accuracy trajectory tracking on arbitrary trajectories from the first attempt with minimal data recollection and training. Most existing approaches for multi-robot knowledge transfer are based on post-analysis of datasets collected from both robots. In this work, we study the feasibility of impromptu transfer of models across robots by learning an error prediction module online. In particular, we analytically derive the form of the mapping to be learned by the online module for exact tracking, propose an approach for characterizing similarity between robots, and use these results to analyze the stability of the overall system. The proposed approach is illustrated in simulation and verified experimentally on two different quadrotors performing impromptu trajectory tracking tasks, where the quadrotors are required to accurately track arbitrary hand-drawn trajectories from the first attempt.},
}

@MISC{zhou-icra19,
author = {Siqi Zhou and Andriy Sarabakha and Erdal Kayacan and Mohamed K. Helwa and Angela P. Schoellig},
title = {Knowledge Transfer Between Robots with Online Learning for Enhancing Robot Performance in Impromptu Trajectory Tracking},
year = {2019},
howpublished = {Abstract and Presentation, in Proc. of the Resilient Robot Teams Workshop at the IEEE International Conference on Robotics and Automation (ICRA)},
abstract = {As robot dynamics become more complex, learning from data is emerging as an alternative for obtaining accurate dynamic models to assist control system designs or to enhance robot performance. Though being effective, common model learning techniques rely on rich datasets collected from the robots, and the learned experience is often platform-specific. In this work, we propose an online learning approach for transferring deep neural network (DNN) inverse dynamics models across two robots and analyze the role of dynamic similarity in the transfer problem. We demonstrate our proposed knowledge transfer approach with two different quadrotors on impromptu trajectory tracking tasks, in which the quadrotors are required to track arbitrary hand-drawn trajectories accurately from the first attempt. With this work, we illustrate that (i) we can relate the transferability of DNN inverse models to the robot dynamic properties, and (ii) when the transfer is feasible, we can significantly reduce data recollections that would be otherwise costly or risky for robot applications. Given a heterogeneous robot team, we envision having to train only one of the agents to allow the whole team achieving higher performance.}
}

@article{zhou-ral18,
title = {An Inversion-Based Learning Approach for Improving Impromptu Trajectory Tracking of Robots With Non-Minimum Phase Dynamics},
author = {SiQi Zhou and Mohamed K. Helwa and Angela P. Schoellig},
journal = {{IEEE Robotics and Automation Letters}},
year = {2018},
volume = {3},
number = {3},
doi = {10.1109/LRA.2018.2801471},
pages = {1663--1670},
urllink = {https://arxiv.org/pdf/1709.04407.pdf},
abstract = {This letter presents a learning-based approach for impromptu trajectory tracking for non-minimum phase systems, i.e., systems with unstable inverse dynamics. Inversion-based feedforward approaches are commonly used for improving tracking performance; however, these approaches are not directly applicable to non-minimum phase systems due to their inherent instability. In order to resolve the instability issue, existing methods have assumed that the system model is known and used preactuation or inverse approximation techniques. In this work, we propose an approach for learning a stable, approximate inverse of a non-minimum phase baseline system directly from its input–output data. Through theoretical discussions, simulations, and experiments on two different platforms, we show the stability of our proposed approach and its effectiveness for high-accuracy, impromptu tracking. Our approach also shows that including more information in the training, as is commonly assumed to be useful, does not lead to better performance but may trigger instability and impact the effectiveness of the overall approach.},
}

@INPROCEEDINGS{zhou-cdc17,
author={SiQi Zhou and Mohamed K. Helwa and Angela P. Schoellig},
title={Design of Deep Neural Networks as Add-on Blocks for Improving Impromptu Trajectory Tracking},
booktitle = {{Proc. of the IEEE Conference on Decision and Control (CDC)}},
year = {2017},
pages={5201--5207},
urllink = {https://arxiv.org/pdf/1705.10932.pdf},
abstract = {This paper introduces deep neural networks (DNNs) as add-on blocks to baseline feedback control systems to enhance tracking performance of arbitrary desired trajectories. The DNNs are trained to adapt the reference signals to the feedback control loop. The goal is to achieve a unity map between the desired and the actual outputs. In previous work, the efficacy of this approach was demonstrated on quadrotors; on 30 unseen test trajectories, the proposed DNN approach achieved an average impromptu tracking error reduction of 43% as compared to the baseline feedback controller. Motivated by these results, this work aims to provide platform-independent design guidelines for the proposed DNN-enhanced control architecture. In particular, we provide specific guidelines for the DNN feature selection, derive conditions for when the proposed approach is effective, and show in which cases the training efficiency can be further increased.}
}

@INPROCEEDINGS{li-icra17,
author = {Qiyang Li and Jingxing Qian and Zining Zhu and Xuchan Bao and Mohamed K. Helwa and Angela P. Schoellig},
title = {Deep neural networks for improved, impromptu trajectory tracking of quadrotors},
booktitle = {{Proc. of the IEEE International Conference on Robotics and Automation (ICRA)}},
year = {2017},
pages = {5183--5189},
doi = {10.1109/ICRA.2017.7989607},
urllink = {https://arxiv.org/abs/1610.06283},
urlvideo = {https://youtu.be/r1WnMUZy9-Y},
abstract = {Trajectory tracking control for quadrotors is important for applications ranging from surveying and inspection, to film making. However, designing and tuning classical controllers, such as proportional-integral-derivative (PID) controllers, to achieve high tracking precision can be time-consuming and difficult, due to hidden dynamics and other non-idealities. The Deep Neural Network (DNN), with its superior capability of approximating abstract, nonlinear functions, proposes a novel approach for enhancing trajectory tracking control. This paper presents a DNN-based algorithm as an add-on module that improves the tracking performance of a classical feedback controller. Given a desired trajectory, the DNNs provide a tailored reference input to the controller based on their gained experience. The input aims to achieve a unity map between the desired and the output trajectory. The motivation for this work is an interactive �fly-as-you-draw� application, in which a user draws a trajectory on a mobile device, and a quadrotor instantly flies that trajectory with the DNN-enhanced control system. Experimental results demonstrate that the proposed approach improves the tracking precision for user-drawn trajectories after the DNNs are trained on selected periodic trajectories, suggesting the method�s potential in real-world applications. Tracking errors are reduced by around 40-50% for both training and testing trajectories from users, highlighting the DNNs� capability of generalizing knowledge.},
}