Design and Flight Evaluation of Deep Model Reference Adaptive Controller

Joshi, Girish; Virdi, Jasvir; Chowdhary, Girish

doi:10.2514/6.2020-1336

Cited by 17 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The event-times {t i k } ∞ k=0 that dictate when agent i samples and broadcasts its state estimate xi (t), as outlined in (7), are generated by the event-trigger mechanism…”

Section: Stability Analysismentioning

confidence: 99%

“…Inspired by [6], [7], and [10], we develop an adaptive eventtriggered distributed state observer that utilizes DNNs as a means to improve state reconstruction for an uncertain nonlinear system. Using a nonsmooth Lyapunov stability analysis, we prove that our observer is capable of UUB state reconstruction while being robust to a bounded exogenous disturbance.…”

Section: Introductionmentioning

confidence: 99%

“…Using a nonsmooth Lyapunov stability analysis, we prove that our observer is capable of UUB state reconstruction while being robust to a bounded exogenous disturbance. Similar to [7] and [10], we develop a multiple timescale learning strategy. In particular, the outer layer weights of each DNN are adjusted online using a Lyapunov-based update law that uses real-time feedback to ensure stability, while the inner layer weights and biases are updated offline using a supervised learning algorithm with collected input-output data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Distributed State Estimation with Deep Neural Networks for Uncertain Nonlinear Systems under Event-Triggered Communication

Zegers¹,

Sun²,

Chowdhary³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Distributed state estimation is examined for a sensor network tasked with reconstructing a system's state through the use of a distributed and event-triggered observer. Each agent in the sensor network employs a deep neural network (DNN) to approximate the uncertain nonlinear dynamics of the system, which is trained using a multiple timescale approach. Specifically, the outer weights of each DNN are updated online using a Lyapunov-based gradient descent update law, while the inner weights and biases are trained offline using a supervised learning method and collected input-output data. The observer utilizes event-triggered communication to promote the efficient use of network resources. A nonsmooth Lyapunov analysis shows the distributed event-triggered observer has a uniformly ultimately bounded state reconstruction error. A simulation study is provided to validate the result and demonstrate the performance improvements afforded by the DNNs.

show abstract

“…The event-times {t i k } ∞ k=0 that dictate when agent i samples and broadcasts its state estimate xi (t), as outlined in (7), are generated by the event-trigger mechanism…”

Section: Stability Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Distributed State Estimation with Deep Neural Networks for Uncertain Nonlinear Systems under Event-Triggered Communication

Zegers¹,

Sun²,

Chowdhary³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The weight W will replace the final layer network weights θ n in f θ to form the adaptive control element (4) in the total controller (3).…”

Section: A Deep Mrac: Total Controllermentioning

confidence: 99%

“…Deep Model Reference Adaptive Control (DMRAC) is a control architecture that seeks to learn a high-performance control policy in the presence of significant model uncertainties while guaranteeing stability [1]- [3]. DMRAC leverages deep neural networks, which have demonstrated their learning power in many supervised learning applications in computer vision, natural language processing, etc.…”

Section: Introductionmentioning

confidence: 99%

Deep Model Reference Adaptive Control

Joshi

Chowdhary

2019

2019 IEEE 58th Conference on Decision and Control (CDC)

Self Cite

View full text Add to dashboard Cite

We present a new neuroadaptive architecture: Deep Neural Network based Model Reference Adaptive Control (DMRAC). Our architecture utilizes the power of deep neural network representations for modeling significant nonlinearities while marrying it with the boundedness guarantees that characterize MRAC based controllers. We demonstrate through simulations and analysis that DMRAC can subsume previously studied learning based MRAC methods, such as concurrent learning and GP-MRAC. This makes DMRAC a highly powerful architecture for high-performance control of nonlinear systems with long-term learning properties.

show abstract