Exploiting Differential Flatness for Robust Learning-Based Tracking Control Using Gaussian Processes

Greeff, Melissa; Schoellig, Angela P.

doi:10.1109/lcsys.2020.3009177

Cited by 36 publications

(28 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GPR provides a variance estimate, which can be used for uncertainty evaluation [2], [8], [10]. In [2], GPR is used with feedback linearization to augment a linear quadratic regulator.…”

Section: Related Workmentioning

confidence: 99%

“…GPR provides a variance estimate, which can be used for uncertainty evaluation [2], [8], [10]. In [2], GPR is used with feedback linearization to augment a linear quadratic regulator. Furthermore, these researchers managed to probabilistically guarantee an ultimate bound on the tracking error via a robustness term derived from the GPR variance.…”

Section: Related Workmentioning

confidence: 99%

“…The problem outlined in this section follows similar methods presented in [2], [12] and others. Consider a robot model given by a nonlinear control-affine system defined by…”

Section: Problem Backgroundmentioning

confidence: 99%

“…In practice, estimated nominal inverse dynamics (4) and forward dynamics (11) models are used. We refer to the model error between the estimated nominal model and the actual dynamics as nonlinear mismatch, like in [2].…”

Section: Gaussian Process Regressionmentioning

confidence: 99%

“…Gaussian Process Regression (GPR) is a promising machine learning technique that has been employed for learning-based controllers with positive results. This approach also enables the use of GPR covariance for robustness and uncertainty propagation; e.g., see [2] and references therein.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Towards Efficient Learning-Based Model Predictive Control via Feedback Linearization and Gaussian Process Regression

Caldwell

Marshall

2021

2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

This paper presents a learning-based Model Predictive Control (MPC) methodology incorporating nonlinear predictions with robotics applications in mind. In particular, MPC is combined with feedback linearization for computational efficiency and Gaussian Process Regression (GPR) is used to model unknown system dynamics and nonlinearities. In this method, MPC predicts future states by leveraging a GPR model and optimizes a sequence of inputs over feedback linearized states. The controller was tested in simulation by using a twolink planar robot in the presence of model uncertainty. With respect to trajectory-tracking error, the proposed controller outperformed a conventional Proportional-Derivative Inverse Dynamics controller and a GPR-augmented version. Although a fully nonlinear MPC formulation achieved slightly better performance, the proposed controller had an average control calculation time that was 82× faster.

show abstract

“…GPR provides a variance estimate, which can be used for uncertainty evaluation [2], [8], [10]. In [2], GPR is used with feedback linearization to augment a linear quadratic regulator.…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…The problem outlined in this section follows similar methods presented in [2], [12] and others. Consider a robot model given by a nonlinear control-affine system defined by…”

Section: Problem Backgroundmentioning

confidence: 99%

Section: Gaussian Process Regressionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Towards Efficient Learning-Based Model Predictive Control via Feedback Linearization and Gaussian Process Regression

Caldwell

Marshall

2021

2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

show abstract

Learning‐based model predictive control for improved mobile robot path following using Gaussian processes and feedback linearization

Wang

Fader

Marshall

2023

Journal of Field Robotics

View full text Add to dashboard Cite

This paper proposes a high‐performance path following algorithm that combines Gaussian processes (GP) based learning and feedback linearization (FBL) with model predictive control (MPC) for ground mobile robots operating in off‐road terrains, referred to as GP‐FBLMPC. The algorithm uses a nominal kinematic model and learns unmodeled dynamics as GP models by using observation data collected during field experiments. Extensive outdoor experiments using a Clearpath Husky A200 mobile robot show that the proposed GP‐FBLMPC algorithm's performance is comparable to existing GP learning‐based nonlinear MPC (GP‐NMPC) methods with respect to the path following errors. The advantage of GP‐FBLMPC is that it is generalizable in reducing path following errors for different paths that are not included in the GP models training process, while GP‐NMPC methods only work well on exactly the same path on which GP models are trained. GP‐FBLMPC is also computationally more efficient than the GP‐NMPC because it does not conduct iterative optimization and requires fewer GP models to make predictions over the MPC prediction horizon loop at every time step. Field tests show the effectiveness and generalization of reducing path following errors of the GP‐FBLMPC algorithm. It requires little training data to perform GP modeling before it can be used to reduce path‐following errors for new, more complex paths on the same terrain (see video at https://youtu.be/tC09jJQ0OXM).

show abstract

Fault Detection for Re-initialization of Online Gaussian Process Regression Using Kernel Linear Independence Test

Kim,

Lee,

Lee

et al. 2024

Int. J. Control Autom. Syst.

View full text Add to dashboard Cite

Exploiting Differential Flatness for Robust Learning-Based Tracking Control Using Gaussian Processes

Cited by 36 publications

References 10 publications

Towards Efficient Learning-Based Model Predictive Control via Feedback Linearization and Gaussian Process Regression

Towards Efficient Learning-Based Model Predictive Control via Feedback Linearization and Gaussian Process Regression

Learning‐based model predictive control for improved mobile robot path following using Gaussian processes and feedback linearization

Fault Detection for Re-initialization of Online Gaussian Process Regression Using Kernel Linear Independence Test

Contact Info

Product

Resources

About