Repetitive learning model predictive control: An autonomous racing example

Brunner, Maximilian; Rosolia, Ugo; Gonzales, J.; Borrelli, Francesco

doi:10.1109/cdc.2017.8264027

Cited by 44 publications

(34 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Learning has been used in conjunction with MPC to learn driving models (Lefevre et al, 2015;Lefèvre et al, 2016), driving dynamics for race cars operating at their handling limits (Drews et al, 2017;Rosolia et al, 2017), as well as to improve path tracking accuracy (Brunner, Rosolia, Gonzales, & Borrelli, 2017;Ostafew et al, 2015Ostafew et al, , 2016. These methods use learning mechanisms to identify nonlinear dynamics that are used in the MPC's trajectory cost function optimization.…”

Section: Learning Controllersmentioning

confidence: 99%

A survey of deep learning techniques for autonomous driving

Grigorescu

Trasnea

Cocias

et al. 2019

Journal of Field Robotics

1,106

495

View full text Add to dashboard Cite

The last decade witnessed increasingly rapid progress in self‐driving vehicle technology, mainly backed up by advances in the area of deep learning and artificial intelligence (AI). The objective of this paper is to survey the current state‐of‐the‐art on deep learning technologies used in autonomous driving. We start by presenting AI‐based self‐driving architectures, convolutional and recurrent neural networks, as well as the deep reinforcement learning paradigm. These methodologies form a base for the surveyed driving scene perception, path planning, behavior arbitration, and motion control algorithms. We investigate both the modular perception‐planning‐action pipeline, where each module is built using deep learning methods, as well as End2End systems, which directly map sensory information to steering commands. Additionally, we tackle current challenges encountered in designing AI architectures for autonomous driving, such as their safety, training data sources, and computational hardware. The comparison presented in this survey helps gain insight into the strengths and limitations of deep learning and AI approaches for autonomous driving and assist with design choices.

show abstract

Section: Learning Controllersmentioning

confidence: 99%

A survey of deep learning techniques for autonomous driving

Grigorescu

Trasnea

Cocias

et al. 2019

Journal of Field Robotics

1,106

495

View full text Add to dashboard Cite

show abstract

“…Moreover, in Figure 6 we reported the computational time. It is interesting to notice that on average the finite time optimal control problem (8) is solved in less then 10ms, whereas it took 90ms to solve the finite time optimal control problem associated with [20]. We underline that both strategies have been tested with a prediction horizon of N = 12 and a sampling time of 10Hz.…”

Section: Affine Time Varying Modelmentioning

confidence: 99%

“…Furthermore, we linearize the kinematic equations of motion to approximate the evolution of the vehicle's position as a function of the velocities. Conversely to our previous works [20], [21], this strategy allow us to reformulate the LMPC as a Quadratic Program (QP) which can be solved efficiently.…”

Section: Introductionmentioning

confidence: 99%

Learning How to Autonomously Race a Car: A Predictive Control Approach

Rosolia

Borrelli

2020

IEEE Trans. Contr. Syst. Technol.

Self Cite

View full text Add to dashboard Cite

In this paper we present a Learning Model Predictive Controller (LMPC) for autonomous racing. We model the autonomous racing problem as a minimum time iterative control task, where an iteration corresponds to a lap. The system trajectory and input sequence of each lap are stored and used to systematically update the controller for the next lap. In the proposed approach the race time does not increase at each iteration. The first contribution of the paper is to propose a local LMPC which reduces the computational burden associated with existing LMPC strategies. In particular, we show how to construct a local safe set and approximation to the value function, using a subset of the stored data. The second contribution is to present a system identification strategy for the autonomous racing iterative control task. We use data from previous iterations and the vehicle's kinematic equations of motion to build an affine time-varying prediction model. The effectiveness of the proposed strategy is demonstrated by experimental results on the Berkeley Autonomous Race Car (BARC) platform.

show abstract

“…The input constraints are Finally, we underline that the autonomous racing problem is a repetitive task and the goal is not to steer the system to the origin. Therefore, we use the method from [18] to apply the proposed strategy to the autonomous racing repetitive control problem. In particular, we define the set of state beyond the finish line of the track of length L, X F = {x ∈ R 6 : e 5 x ≥ L} and we use the set X F to compute the cost associated with the stored trajectories For the first 29 laps of the experiment, we run the Learning Model Predictive Controller (LMPC) from [18] to learn a fast trajectory which drives the vehicle around the track.…”

Section: B Example Ii: Autonomous Racingmentioning

confidence: 99%

“…Therefore, we use the method from [18] to apply the proposed strategy to the autonomous racing repetitive control problem. In particular, we define the set of state beyond the finish line of the track of length L, X F = {x ∈ R 6 : e 5 x ≥ L} and we use the set X F to compute the cost associated with the stored trajectories For the first 29 laps of the experiment, we run the Learning Model Predictive Controller (LMPC) from [18] to learn a fast trajectory which drives the vehicle around the track. From the 30th lap, we run the local data-based policy (11) and (12) using the latest M = 8 laps and N = 10 stored data for each lap.…”

Section: B Example Ii: Autonomous Racingmentioning

confidence: 99%

Simple Policy Evaluation for Data-Rich Iterative Tasks

Rosolia

Zhang

Borrelli

2019

2019 American Control Conference (ACC)

Self Cite

View full text Add to dashboard Cite

A data-based policy for iterative control task is presented. The proposed strategy is model-free and can be applied whenever safe input and state trajectories of a system performing an iterative task are available. These trajectories, together with a user-defined cost function, are exploited to construct a piecewise affine approximation to the value function. The approximated value function is then used to evaluate the control policy by solving a linear program. We show that for linear system subject to convex cost and constraints, the proposed strategy guarantees closed-loop constraint satisfaction and performance bounds for the closed-loop trajectory. We evaluate the proposed strategy in simulations and experiments, the latter carried out on the Berkeley Autonomous Race Car (BARC) platform. We show that the proposed strategy is able to reduce the computation time by one order of magnitude while achieving the same performance as our model-based control algorithm.

show abstract

Repetitive learning model predictive control: An autonomous racing example

Cited by 44 publications

References 12 publications

A survey of deep learning techniques for autonomous driving

A survey of deep learning techniques for autonomous driving

Learning How to Autonomously Race a Car: A Predictive Control Approach

Simple Policy Evaluation for Data-Rich Iterative Tasks

Contact Info

Product

Resources

About