An official website of the United States government
We introduced a working memory augmented adaptive controller in our recent work. The controller uses attention to read from and write to the working memory. Attention allows the controller to read specific information that is relevant and update its working memory with information based on its relevance, similar to how humans pick relevant information from the enormous amount of information that is received through various senses. The retrieved information is used to modify the final control input computed by the controller. We showed that this modification speeds up learning.In the above work, we used a soft-attention mechanism for the adaptive controller. Controllers that use soft attention update and read information from all memory locations at all the times, the extent of which is determined by their relevance. But, for the same reason, the information stored in the memory can be lost. In contrast, hard attention updates and reads from only one location at any point of time, which allows the memory to retain information stored in other locations. The downside is that the controller can fail to shift attention when the information in the current location becomes less relevant.We propose an attention mechanism that comprises of (i) a hard attention mechanism and additionally (ii) an attention reallocation mechanism. The attention reallocation enables the controller to reallocate attention to a different location when the relevance of the location it is reading from diminishes. The reallocation also ensures that the information stored in the memory before the shift in attention is retained which can be lost in both soft and hard attention mechanisms. Through detailed simulations of various scenarios for two link robot robot arm systems we illustrate the effectiveness of the proposed attention mechanism.
more »
« less
Working Memory Augmentation for Improved Learning in Neural Adaptive Control
In this paper, we propose a novel control architecture, inspired from neuroscience, for adaptive control of continuous time systems. The objective here is to design control architectures and algorithms that can learn and adapt quickly to changes that are even abrupt. The proposed architecture, in the setting of standard neural network (NN) based adaptive control, augments an external working memory to the NN. The learning system stores, in its external working memory, recently observed feature vectors from the hidden layer of the NN that are relevant and forgets the older irrelevant values. It retrieves relevant vectors from the working memory to modify the final control signal generated by the controller. The use of external working memory improves the context inducing the learning system to search in a particular direction. This directed learning allows the learning system to find a good approximation of the unknown function even after abrupt changes quickly. We consider two classes of controllers for illustration of our ideas (i) a model reference NN adaptive controller for linear systems with matched uncertainty (ii) backstepping NN controller for strict feedback systems. Through extensive simulations and specific metrics we show that memory augmentation improves learning significantly even when the system undergoes sudden changes. Importantly, we also provide evidence for the proposed mechanism by which this specific memory augmentation improves learning.
more »
« less
- Award ID(s):
- 1839429
- PAR ID:
- 10190799
- Date Published:
- Journal Name:
- 2019 IEEE Conference on Decision and Control
- Page Range / eLocation ID:
- 6785 to 6792
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)We present a control framework that enables safe simultaneous learning and control for systems subject to uncertainties. The two main constituents are contraction theory-based L1-adaptive (CL1) control and Bayesian learning in the form of Gaussian process (GP) regression. The CL1 controller ensures that control objectives are met while providing safety certificates. Furthermore, the controller incorporates any available data into GP models of uncertainties, which improves performance and enables the motion planner to achieve optimality safely. This way, the safe operation of the system is always guaranteed, even during the learning transients. Keywords: Safe Learning, Planning, Adaptive Control, Gaussian Process Regressionmore » « less
-
This paper is focused on the output tracking control problem of a wave equation with both matched and unmatched boundary uncertainties. An adaptive boundary feedback control scheme is proposed by utilizing radial basis function neural networks (RBF NNs) to deal with the effect of system uncertainties. Specifically, two RBF NN models are first developed to approximate the matched and unmatched system uncertain dynamics respectively. Based on this, an adaptive NN control scheme is derived, which consists of: (i) an adaptive boundary feedback controller embedded by the NN model approximating the matched uncertainty, for rendering stable and accurate tracking control; and (ii) a reference model embedded by the NN model approximating the unmatched uncertainty, for generating a prescribed reference trajectory. Rigorous analysis is performed using the Lyapunov theory and the C0-semigroup theory to prove that our proposed control scheme can guarantee closed-loop stability and wellposedness. Simulation study has been conducted to demonstrate effectiveness of the proposed approach.more » « less
-
Networked control systems (NCSs) are designed to control and monitor large-scale and complex systems remotely. The communication connectivity in an NCS allows agents to quickly communicate with each other to respond to abrupt changes in the system quickly, thus reducing complexity and increasing efficiency. Despite all these advantages, NCSs are vulnerable to cyberattacks. Injecting cyberattacks, such as a time-delay switch (TDS) attack, into communication channels has the potential to make NCSs inefficient or even unstable. This paper presents a Lyapunov-based approach to detecting and estimating TDS attacks in real time. A secure control strategy is designed to mitigate the effects of TDS attacks in real time. The stability of the secure control system is investigated using the Lyapunov theory. The proposed TDS attack estimator’s performance and secure control strategy are evaluated in simulations and a hardware-in-the-loop environment.more » « less
-
This paper presents a control architecture for an aerial manipulator operating in indoor environments. The objective is to provide a viable solution to the growing need for indoor assistive technology. The study tries to address the problem of payload pick-and-place with unknown mass. The control structure consists of i) a baseline pitch angle tracking controller that provides satisfactory performance for the quadrotor without a payload; ii) an adaptive augmentation that compensates for the disturbance in the rotational dynamics due to the unknown payload; iii) a horizontal position tracking controller that generates the pitch angle command; iv) a baseline vertical position tracking controller; and v) another adaptive augmentation controller that compensates for the disturbance in the vertical motion from the pick-and-place of the unknown payload. Since the robotic manipulator operates in the vertical plane of symmetry of the quadrotor, the control design is considered for the motion only in this plane. The controller is verified in a simulation environment.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/CDC40024.2019.9029549
