mlsanityData to 7 Oct 2026

Predictive Linear Online Tracking for Unknown Targets

arXiv 2402.10036 ↗First posted 15 Feb 2024eess.SY cs.LG cs.SYcited by 5

Not on the map. Why?

Abstract (arXiv)

In this paper, we study the problem of online tracking in linear control systems, where the objective is to follow a moving target. Unlike classical tracking control, the target is unknown, non-stationary, and its state is revealed sequentially, thus, fitting the framework of online non-stochastic control. We consider the case of quadratic costs and propose a new algorithm, called predictive linear online tracking (PLOT). The algorithm uses recursive least squares with exponential forgetting to learn a time-varying dynamic model of the target. The learned model is used in the optimal policy under the framework of receding horizon control. We show the dynamic regret of PLOT scales with O(√TVT), where VT is the total variation of the target dynamics and T is the time horizon. Unlike prior work, our theoretical results hold for non-stationary targets. We implement PLOT on a real quadrotor and provide open-source software, thus, showcasing one of the first successful applications of online control methods on real hardware.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 36 of its 67 references that are in the map. First posted on arXiv 15 Feb 2024.

Builds on

36 of 67 references.

References · 36

  1. 2013Online Learning under Delayed Feedbackcited by 137
  2. 2020Naive Exploration is Optimal for Online LQRcited by 111
  3. 2019Online Control with Adversarial Disturbancescited by 92
  4. 2013Relative Loss Bounds for On-line Density Estimation with the Exponential Family of Distributionscited by 59
  5. 2020Black-Box Control for Linear Dynamical Systemscited by 43
  6. 2020Logarithmic Regret for Adversarial Online Controlcited by 41
  7. 2019Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysiscited by 40
  8. 2019Logarithmic Regret for Online Controlcited by 38
  9. 2020Adaptive Regret for Control of Time-Varying Dynamicscited by 38
  10. 2013Online Learning for Time Series Predictioncited by 33
  11. 2021Non-stationary Online Learning with Memory and Non-stochastic Controlcited by 33
  12. 2020The Power of Predictions in Online Controlcited by 31
24 more
  1. 2020Making Non-Stochastic Control (Almost) as Easy as Stochasticcited by 24
  2. 2021On the Regret Analysis of Online LQR Control with Predictionscited by 22
  3. 2020Online Learning of the Kalman Filter with Logarithmic Regretcited by 21
  4. 2020Online Optimal Control with Affine Constraintscited by 20
  5. 2020No-Regret Prediction in Marginally Stable Systemscited by 18
  6. 2022Introduction to Online Controlcited by 17
  7. 2018On-Line Learning of Linear Dynamical Systems: Exponential Forgetting in Kalman Filterscited by 16
  8. 2021Adversarial Tracking Control via Strongly Adaptive Online Learning with Memorycited by 14
  9. 2022Online Control of Unknown Time-Varying Dynamical Systemscited by 13
  10. 2019Trading-Off Static and Dynamic Regret in Online Least-Squares and Beyondcited by 12
  11. 2020SLIP: Learning to Predict in Unknown Dynamical Systems with Long-Term Memorycited by 11
  12. 2022Regret Lower Bounds for Learning Linear Quadratic Gaussian Systemscited by 11
  13. 2020The Power of Linear Controllers in LQR Controlcited by 10
  14. 2021Regret-optimal Estimation and Controlcited by 10
  15. 2021Machine Learning for Mechanical Ventilation Controlcited by 8
  16. 2021A Historical Perspective of Adaptive Control and Learningcited by 8
  17. 2022Optimal Dynamic Regret in LQR Controlcited by 6
  18. 2023Online Linear Quadratic Tracking with Regret Guaranteescited by 3
  19. 2023Online Learning for Obstacle Avoidancecited by 3
  20. 2019A nonlinear tracking model predictive control scheme for dynamic target signalscited by 2
  21. 2022An explicit dual control approach for constrained reference tracking of uncertain linear systemscited by 1
  22. 2022Regret Analysis of Online Gradient Descent-based Iterative Learning Control with Model Mismatchcited by 1
  23. 2022Online convex optimization for constrained control of linear systems using a reference governorcited by 1
  24. 2023Safe Non-Stochastic Control of Control-Affine Systems: An Online Convex Optimization Approachcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 1.

5 papers.

  1. 2025Model-free Online Learning for the Kalman Filter: Forgetting Factor and Logarithmic Regretcited by 2
  2. 2024Online Residual Learning from Offline Experts for Pedestrian Trackingcited by 1
  3. 2025Logarithmic Regret and Polynomial Scaling in Online Multi-step-ahead Predictioncited by 1
  4. 2025Online Multi-Agent Control with Adversarial Disturbancescited by 0
  5. 2026Self-Adaptive Learning and Model Predictive Control for Tracking Unknown Dynamics with No Regretcited by 0