Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLearning-Based Risk-Averse Model Predictive Control for Adaptive Cruise Control with Stochastic Driver Models
148
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
We propose a learning-based, distributionally robust model predictive control approach towards the design of adaptive cruise control (ACC) systems. We model the preceding vehicle as an autonomous stochastic system, using a hybrid model with continuous dynamics and discrete, Markovian inputs. We estimate the (unknown) transition probabilities of this model empirically using observed mode transitions and simultaneously determine sets of probability vectors (ambiguity sets) around these estimates, that contain the true transition probabilities with high confidence. We then solve a risk-averse optimal control problem that assumes the worst-case distributions in these sets. We furthermore derive a robust terminal constraint set and use it to establish recursive feasibility of the resulting MPC scheme. We validate the theoretical results and demonstrate desirable properties of the scheme through closed-loop simulations.
rate research
Read More
We study a risk-averse optimal control problem with a finite-horizon Borel model, where the cost is assessed via exponential utility. The setting permits non-linear dynamics, non-quadratic costs, and continuous spaces but is less general than the problem of optimizing an expected utility. Our contribution is to show the existence of an optimal risk-averse controller through the use of measure-theoretic first principles.
We propose Kernel Predictive Control (KPC), a learning-based predictive control strategy that enjoys deterministic guarantees of safety. Noise-corrupted samples of the unknown system dynamics are used to learn several models through the formalism of non-parametric kernel regression. By treating each prediction step individually, we dispense with the need of propagating sets through highly non-linear maps, a procedure that often involves multiple conservative approximation steps. Finite-sample error bounds are then used to enforce state-feasibility by employing an efficient robust formulation. We then present a relaxation strategy that exploits on-line data to weaken the optimization problem constraints while preserving safety. Two numerical examples are provided to illustrate the applicability of the proposed control method.
Accounting for more than 40% of global energy consumption, residential and commercial buildings will be key players in any future green energy systems. To fully exploit their potential while ensuring occupant comfort, a robust control scheme is required to handle various uncertainties, such as external weather and occupant behaviour. However, prominent patterns, especially periodicity, are widely seen in most sources of uncertainty. This paper incorporates this correlated structure into the learning model predictive control framework, in order to learn a global optimal robust control scheme for building operations.
This brief introduction to Model Predictive Control specifically addresses stochastic Model Predictive Control, where probabilistic constraints are considered. A simple linear system subject to uncertainty serves as an example. The Matlab code for this stochastic Model Predictive Control example is available online.
This paper investigates the accuracy and robustness of car-following (CF) and adaptive cruise control (ACC) models used to simulate measured driving behaviour of commercial ACCs. To this aim, a general modelling framework is proposed, in which ACC and CF models have been incrementally augmented with physics extensions; namely, perception delay, linear or nonlinear vehicle dynamics, and acceleration constraints. The framework has been applied to the Intelligent Driver Model (IDM), the Gipps model, and to three basic ACCs. These are a linear controller coupled with a constant time-headway spacing policy and with two other policies derived from the traffic flow theory, which are the IDM desired-distance function and the Gipps equilibrium distance-speed function. The ninety models resulting from the combination of the five base models and the aforementioned physics extensions, have been assessed and compared through a vast calibration and validation experiment against measured trajectory data of low-level automated vehicles. When a single extension has been applied, perception delay and linear dynamics have been the extensions to mostly increase modelling accuracy, whatsoever the base model considered. Concerning models, Gipps-based ones have outperformed all other CF and ACC models in calibration. Even among ACCs, the linear controllers coupled with a Gipps spacing policy have been the best performing. On the other hand, IDM-based models have been by far the most robust in validation, showing almost no crash when calibrated parameters have been used to simulate different trajectories. Overall, the paper shows the importance of cross-fertilization between traffic flow and vehicle studies.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
