Deep learning on trajectory images

Imran, Omar; Pradeepan, Santhosh; Sévigny, Pascale; Carniglia, Peter; Rajan, Sreeraman; Balaji, Bhashyam; Doraiswami, R.

doi:10.1117/12.2619094

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning. The stochastic and the deterministic disturbances corrupting the input and the output are estimated using the machine learning approach (Imran et al, 2022):…”

Section: Linear Parameter-varying Modelmentioning

confidence: 99%

“…The output y ( k ) and the residual e ( k ) are (causally) invertible. In other words, e ( k ) can be generated from the output y ( k ) and r ( k ) using the (causal) predictor form, and y ( k ) can be generated from e ( k ) and r ( k ) using the innovation form (Imran et al, 2022). Moreover, ( bold-italicA 0 , bold-italicB 0 , bold-italicC 0 , bold-italicD 0 ) and ( ...…”

Section: System Model and The Kfmentioning

confidence: 99%

“…In the control area, which principally motivated this research, conventional approaches to this problem involve the use of feedback (adaptive) controllers, supplemented by some identification/estimation techniques that invariably required the use of some form of (assumed) knowledge of the statistics of the unknown disturbances and measurement noise. Refer, for example, to Bar-Shalom et al (1998), Ramachandra (2000), Imran et al (2022), and Jakob (2016) for a wide overview of tracking in control, dynamical, and radar systems. As this statistical information is seldom accurately available, if, at all, these conventional approaches are therefore based on some statistical assumptions whose validity would then directly impact the resulting tracking accuracy and performance achieved (see Saho (2017) and some references therein on various uses of the Kalman filter (KF) in tracking trajectories in different applications).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Tracking the trajectory of an object in a noisy environment with unknown statistics: A novel robust Kalman filter residue-based approach

Cheded¹,

Doraiswami

2023

Transactions of the Institute of Measurement and Control

Self Cite

View full text Add to dashboard Cite

A novel robust Kalman filter (KF)-based controller design approach is proposed to accurately track a specified trajectory under unknown stochastic disturbance, known deterministic disturbance, and measurement noise. The system is nonlinear and is approximated by a piecewise-linear dynamic model. The Box–Jenkins model is an augmented model of the signal and the disturbance, is non-controllable and observable, while the signal model is controllable and observable. An emulator-based two-stage identification is employed to obtain an accurate system model needed to design the robust controller. The system and its KF are identified, and the signal and output errors are estimated. From the identified models, the signal, its KF, the disturbance model, and the whitening filter are all obtained using balanced model reduction techniques. It is shown that the signal model is a transfer matrix description relating the system output and KF residual, and the residual is the whitened output error. The disturbance model is identified by inverse filtering. A new combined feedforward–feedback controller is designed and implemented using an internal model of the reference driven by both the error between the reference and the signal estimate, and by the feedforwarded reference signal. The proposed scheme was successfully evaluated on a simulated autonomously guided drone.

show abstract

“…Machine learning. The stochastic and the deterministic disturbances corrupting the input and the output are estimated using the machine learning approach (Imran et al, 2022):…”

Section: Linear Parameter-varying Modelmentioning

confidence: 99%