skip to main content

Attention:

The NSF Public Access Repository (PAR) system and access will be unavailable from 11:00 PM ET on Friday, December 13 until 2:00 AM ET on Saturday, December 14 due to maintenance. We apologize for the inconvenience.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Accurate Pouring using Model Predictive Control Enabled by Recurrent Neural Network
Humans perform the task of pouring often and in which exhibit consistent accuracy regardless of the complicated dynamics of the liquid. Model predictive control (MPC) appears to be a natural candidate solution for the task of accurate pouring considering its wide use in industrial applications. However, MPC requires the model of the system in question. Since an accurate model of the liquid dynamics is difficult to obtain, the usefulness of MPC for the pouring task is uncertain. In this work, we model the dynamics of water using a recurrent neural network (RNN), which enables the use of MPC for pouring control. We evaluated our RNN-enabled MPC controller using a physical system we made ourselves and averaged a pouring error of 16.4 mL over 5 different source containers. We also compared our controller with a baseline switch controller and showed that our controller achieved a much higher accuracy than the baseline controller.  more » « less
Award ID(s):
1812933
PAR ID:
10169419
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Page Range / eLocation ID:
7688 to 7694
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ( , American Control Conference)
    null (Ed.)
    With increase in the frequency of natural disasters such as hurricanes that disrupt the supply from the grid, there is a greater need for resiliency in electric supply. Rooftop solar photovoltaic (PV) panels along with batteries can provide resiliency to a house in a blackout due to a natural disaster. Our previous work showed that intelligence can reduce the size of a PV+battery system for the same level of post-blackout service compared to a conventional system that does not employ intelligent control. The intelligent controller proposed is based on model predictive control (MPC), which has two main challenges. One, it requires simple yet accurate models as it involves real-time optimization. Two, the discrete actuation for residential loads (on/off) makes the underlying optimization problem a mixed-integer program (MIP) which is challenging to solve. An attractive alternative to MPC is reinforcement learning (RL) as the real-time control computation is both model-free and simple. These points of interest accompany certain trade-offs; RL requires computationally expensive offline learning, and its performance is sensitive to various design choices. In this work, we propose an RL-based controller. We compare its performance with the MPC controller proposed in our prior work and a non-intelligent baseline controller. The RL controller is found to provide a resiliency performance — by commanding critical loads and batteries—similar to MPC with a significant reduction in computational effort. 
    more » « less
  2. ; ; ( , 2020-2021 International Conference on High Performance Buildings)
    null (Ed.)
    Model predictive control (MPC) has been widely investigated for climate control of commercial buildings for both energy efficiency and demand flexibility. However, most MPC formulations ignore humidity and latent heat. The inclusion of moisture makes the problem considerably more challenging, primarily since a cooling and dehumidifying coil model which accounts for both sensible and latent heat transfers is needed. In our recent work, we proposed an MPC controller in which humidity and latent heat were incorporated in a principled manner, by using a reduced-order model of the cooling coil. Because of the highly nonlinear nature of the process in a cooling coil, the model needs to be modified based on certain weather/climatic conditions to have sufficient prediction accuracy. Doing so, however, leads to a mixed-integer nonlinear program (MINLP) that is challenging to solve. In this work, we propose an MPC formulation that retains the NLP (nonlinear programming problem) structure in all climate zones/weather conditions. This feature makes the control system capable of autonomous operation. Simulations in multiple climate zones and weather conditions verify the energy savings performance, and autonomy of the proposed controller. We also compare the performance of the proposed MPC controller with an MPC formulation that does not explicitly consider humidity. Under certain conditions, it is found that the MPC controller that excludes humidity leads to poor humidity control, or higher energy usage as it is unaware of the latent load on the cooling coil. 
    more » « less
  3. ; ( , ASME Journal of Engineering for Sustainable Buildings and Cities)
    null (Ed.)
    Abstract An autonomous adaptive model predictive control (MPC) architecture is presented for control of heating, ventilation, and air condition (HVAC) systems to maintain indoor temperature while reducing energy use. Although equipment use and occupant changes with time, existing MPC methods are not capable of automatically relearning models and computing control decisions reliably for extended periods without intervention from a human expert. We seek to address this weakness. Two major features are embedded in the proposed architecture to enable autonomy: (i) a system identification algorithm from our prior work that periodically re-learns building dynamics and unmeasured internal heat loads from data without requiring re-tuning by experts. The estimated model is guaranteed to be stable and has desirable physical properties irrespective of the data; (ii) an MPC planner with a convex approximation of the original nonconvex problem. The planner uses a descent and convergent method, with the underlying optimization problem being feasible and convex. A yearlong simulation with a realistic plant shows that both of the features of the proposed architecture—periodic model and disturbance update and convexification of the planning problem—are essential to get performance improvement over a commonly used baseline controller. Without these features, long-term energy savings from MPC can be small while with them, the savings from MPC become substantial. 
    more » « less
  4. ; ; ( , Proceedings of The 6th Conference on Robot Learning, PMLR)
    Liu, Karen ; Kulic, Dana ; Ichnowski, Jeff (Ed.)
    In this work, we consider the task of improving the accuracy of dynamic models for model predictive control (MPC) in an online setting. Although prediction models can be learned and applied to model-based controllers, these models are often learned offline. In this offline setting, training data is first collected and a prediction model is learned through an elaborated training procedure. However, since the model is learned offline, it does not adapt to disturbances or model errors observed during deployment. To improve the adaptiveness of the model and the controller, we propose an online dynamics learning framework that continually improves the accuracy of the dynamic model during deployment. We adopt knowledge-based neural ordinary differential equations (KNODE) as the dynamic models, and use techniques inspired by transfer learning to continually improve the model accuracy. We demonstrate the efficacy of our framework with a quadrotor, and verify the framework in both simulations and physical experiments. Results show that our approach can account for disturbances that are possibly time-varying, while maintaining good trajectory tracking performance. 
    more » « less
  5. ; ; ( , Proceedings of The 6th Conference on Robot Learning)
    Liu, Karen ; Kulic, Dana ; Ichnowski, Jeff (Ed.)
    In this work, we consider the task of improving the accuracy of dynamic models for model predictive control (MPC) in an online setting. Although prediction models can be learned and applied to model-based controllers, these models are often learned offline. In this offline setting, training data is first collected and a prediction model is learned through an elaborated training procedure. However, since the model is learned offline, it does not adapt to disturbances or model errors observed during deployment. To improve the adaptiveness of the model and the controller, we propose an online dynamics learning framework that continually improves the accuracy of the dynamic model during deployment. We adopt knowledge-based neural ordinary differential equations (KNODE) as the dynamic models, and use techniques inspired by transfer learning to continually improve the model accuracy. We demonstrate the efficacy of our framework with a quadrotor, and verify the framework in both simulations and physical experiments. Results show that our approach can account for disturbances that are possibly time-varying, while maintaining good trajectory tracking performance. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email