Efficient implementation of Randomized MPC for miniature race cars

Carrau, Jesús Velasco; Liniger, Alexander; Zhang, Xiaojing; Lygeros, John

doi:10.1109/ecc.2016.7810413

Cited by 38 publications

(21 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prediction horizon is chosen as N = 30 and we formulate the chance constraints (19) with χ 2 2 (p x ) = 1. To reduce conservatism of the controller, constraints are instead only tightened for the first 20 prediction steps and are applied to the mean for the remainder of the prediction horizon, similar to the method used in [46]. We reduce computation times by making use of the dynamic sparse approximations with 10 inducing points as outlined in Section III-C, placing the inducing inputs regularly along the previous solution trajectory.…”

Section: B Gp-based Racing Controllermentioning

confidence: 99%

Cautious Model Predictive Control Using Gaussian Process Regression

Hewing

Kabzan

Zeilinger

2020

IEEE Trans. Contr. Syst. Technol.

441

334

View full text Add to dashboard Cite

Gaussian process (GP) regression has been widely used in supervised machine learning due to its flexibility and inherent ability to describe uncertainty in function estimation. In the context of control, it is seeing increasing use for modeling of nonlinear dynamical systems from data, as it allows the direct assessment of residual model uncertainty. We present a model predictive control (MPC) approach that integrates a nominal system with an additive nonlinear part of the dynamics modeled as a GP. Approximation techniques for propagating the state distribution are reviewed and we describe a principled way of formulating the chance constrained MPC problem, which takes into account residual uncertainties provided by the GP model to enable cautious control. Using additional approximations for efficient computation, we finally demonstrate the approach in a simulation example, as well as in a hardware implementation for autonomous racing of remote controlled race cars, highlighting improvements with regard to both performance and safety over a nominal controller.

show abstract

Section: B Gp-based Racing Controllermentioning

confidence: 99%

Cautious Model Predictive Control Using Gaussian Process Regression

Hewing

Kabzan

Zeilinger

2020

IEEE Trans. Contr. Syst. Technol.

441

334

View full text Add to dashboard Cite

show abstract

“…Considering uncertainty explicitly in the control formulation can improve safety and performance in a race, as e.g. also demonstrated in [18].…”

Section: A State and Uncertainty Predictionmentioning

confidence: 85%

“…One could address this by implementing feedback over the planning horizon [8], but it is typically challenging to design a simple ancillary controller for highly nonlinear problems. For computational and simplicity reasons we therefore heuristically address this issue by limiting the tightening to a shorter horizon N shrink < N , which was shown to perform well in practice [18]. In addition to the track constraints, tire forces are limited to a tire-specific frictional ellipse…”

Section: Track Tire and Input Constraintsmentioning

confidence: 99%

Learning-Based Model Predictive Control for Autonomous Racing

Kabzan

Hewing

Liniger

et al. 2019

IEEE Robot. Autom. Lett.

Self Cite

320

155

View full text Add to dashboard Cite

In this paper, we present a learning-based control approach for autonomous racing with an application to the AMZ Driverless race car gotthard. One major issue in autonomous racing is that accurate vehicle models that cover the entire performance envelope of a race car are highly nonlinear, complex and complicated to identify, rendering them impractical for control. To address this issue, we employ a relatively simple nominal vehicle model, which is improved based on measurement data and tools from machine learning. The resulting formulation is an online learning data-driven Model Predictive Controller, which uses Gaussian Processes regression to take residual model uncertainty into account and achieve safe driving behavior. To improve the vehicle model online, we select from a constant inflow of data points according to a criterion reflecting the information gain, and maintain a small dictionary of 300 data points. The framework is tested on the full-size AMZ Driverless race car, where it is able to improve the vehicle model and reduce lap times by 10% while maintaining safety of the vehicle.

show abstract

“…In future work we will investigate how the lower level can be modified to improve the driving performance. For example by considering the model uncertainty in the MPC design, as proposed in [49]. Furthermore, we are investigating the use of the path planning model and the viability constraints in a racing game with multiple opposing cars.…”

Section: Resultsmentioning

confidence: 99%

Real-Time Control for Autonomous Racing Based on Viability Theory

Liniger

Lygeros

2019

IEEE Trans. Contr. Syst. Technol.

Self Cite

View full text Add to dashboard Cite

In this paper we consider autonomous driving of miniature race cars. The viability kernel is used to efficiently generate finite look-ahead trajectories that maximize progress while remaining recursively feasible with respect to static obstacles (e.g., stay inside the track). Together with a low-level model predictive controller, this method makes real-time autonomous racing possible. The viability kernel computation is based on space discretization. To make the calculation robust against discretization errors, we propose a novel numerical scheme based on game theoretical methods, in particular the discriminating kernel. We show that the resulting algorithm provides an inner approximation of the viability kernel and guarantees that, for all states in the cell surrounding a viable grid point, there exists a control that keeps the system within the kernel. The performance of the proposed control method is studied in simulation where we determine the effects of various design choices and parameters and in experiments on an autonomous racing set-up maintained at the Automatic Control Laboratory of ETH Zurich. Both simulation and experimental results suggest that the more conservative approximation using the discriminating kernel results in safer driving style at the cost of a small increase in lap time.Comment: 26 pages, 11 figure

show abstract

Efficient implementation of Randomized MPC for miniature race cars

Cited by 38 publications

References 27 publications

Cautious Model Predictive Control Using Gaussian Process Regression

Cautious Model Predictive Control Using Gaussian Process Regression

Learning-Based Model Predictive Control for Autonomous Racing

Real-Time Control for Autonomous Racing Based on Viability Theory

Contact Info

Product

Resources

About