Model predictive control (MPC) has become more
relevant to vehicle dynamics control due to its inherent capacity
of treating system constraints. However, online optimization
from MPC introduces an extensive computational burden for
today’s onboard microprocessors. To alleviate MPC
computational load, several methods have been proposed.
Among them, online successive system linearization and the
resulting linear time-varying model predictive controller
(LTVMPC) is one of the most popular options. Nevertheless,
such online successive linearization commonly approximates the
original (nonlinear) system by a linear one, which inevitably
introduces extra modeling errors and therefore reduces MPC
performance. Actually, if the controlled system possesses the
“differential flatness” property, then it can be exactly linearized
and an equivalent linear model will appear. This linear model
maintains all the nonlinear features of the original system and
can be utilized to design a flatness-based model predictive
controller (FMPC). CarSim-Simulink joint simulations
demonstrate that the proposed FMPC substantially outperforms
a classical LTVMPC in terms of the path-tracking performance
for autonomous vehicles.
more »
« less
Risk-Aware Model Predictive Path Integral Control Using Conditional Value-at-Risk
In this paper, we present a novel Model Predictive
Control method for autonomous robot planning and control
subject to arbitrary forms of uncertainty. The proposed Risk-
Aware Model Predictive Path Integral (RA-MPPI) control utilizes
the Conditional Value-at-Risk (CVaR) measure to generate
optimal control actions for safety-critical robotic applications.
Different from most existing Stochastic MPCs and CVaR
optimization methods that linearize the original dynamics and
formulate control tasks as convex programs, the proposed
method directly uses the original dynamics without restricting
the form of the cost functions or the noise. We apply the
novel RA-MPPI controller to an autonomous vehicle to perform
aggressive driving maneuvers in cluttered environments. Our
simulations and experiments show that the proposed RA-MPPI
controller can achieve similar lap times with the baseline MPPI
controller while encountering significantly fewer collisions. The
proposed controller performs online computation at an update
frequency of up to 80 Hz, utilizing modern Graphics Processing
Units (GPUs) to multi-thread the generation of trajectories as
well as the CVaR values.
more »
« less
- Award ID(s):
- 2219755
- NSF-PAR ID:
- 10499424
- Editor(s):
- risk-aware planning; Conditional Value-at-Risk; Model Predictive Control; Model Predictive Path Integral
- Publisher / Repository:
- IEEE
- Date Published:
- Journal Name:
- IEEE International Conference on Robotics and Automation
- ISSN:
- 2152-4092
- ISBN:
- 979-8-3503-2365-8
- Page Range / eLocation ID:
- 7937 to 7943
- Format(s):
- Medium: X
- Location:
- London, United Kingdom
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This paper proposes a novel robust reinforcement learning framework for discrete-time linear systems with model mismatch that may arise from the sim-to-real gap. A key strategy is to invoke advanced techniques from control theory. Using the formulation of the classical risk-sensitive linear quadratic Gaussian control, a dual-loop policy optimization algorithm is proposed to generate a robust optimal controller. The dual-loop policy optimization algorithm is shown to be globally and uniformly convergent, and robust against disturbances during the learning process. This robustness property is called small-disturbance input-to-state stability and guarantees that the proposed policy optimization algorithm converges to a small neighborhood of the optimal controller as long as the disturbance at each learning step is relatively small. In addition, when the system dynamics is unknown, a novel model-free off-policy policy optimization algorithm is proposed. Finally, numerical examples are provided to illustrate the proposed algorithm.more » « less
-
The performance of a model predictive controller depends on the accuracy of the objective and prediction model of the system. Although significant efforts have been dedicated to improving the robustness of model predictive control (MPC), they typically do not take a risk-averse perspective. In this paper, we propose a risk-aware MPC framework, which estimates the underlying parameter distribution using online Bayesian learning and derives a risk-aware control policy by reformulating classical MPC problems as Bayesian Risk Optimization (BRO) problems. The consistency of the Bayesian estimator and the convergence of the control policy are rigorously proved. Furthermore, we investigate the consistency requirement and propose a risk monitoring mechanism to guarantee the satisfaction of the consistency requirement. Simulation results demonstrate the effectiveness of the proposed approach.more » « less
-
We present a systematic framework for real-time risk-based optimization via multi-parametric programming. A dynamic risk indicator is utilized to monitor online process safety performance and provide model-based prediction of risk propagation, as a function of safety-critical process variables. Risk-based explicit/multi-parametric model predictive control is then developed to generate fit-for-purpose control strategies for proactive risk management. Given the probabilistic nature of risk, the controller design is extended to adapt a chance-constrained programming setting coupled with Bayesian inference for continuous risk updating along the rolling time horizon. A hierarchical dynamic optimization formulation is further developed to integrate risk control, operational optimization, and fault prognosis across multiple temporal scales in an integral but computationally efficient manner. If a potential fault is detected and cannot be prevented by adjusting operating actions, an alarm will be raised well ahead of time with the controller and optimizer continuously performing to attenuate the fault propagation speed and severity. The potential and efficacy of the proposed framework are demonstrated on three safety-critical case studies with increasing level of complexity: (i) Tank filling, (ii) Batch reactor at T2 Laboratories, and (iii) Cyber-physical hydrogen water electrolysis prototype.more » « less
-
In this paper, we consider a multi-objective control problem for stochastic systems that seeks to minimize a cost of interest while ensuring safety. We introduce a novel measure of safety risk using the conditional value-at-risk and a set distance to formulate a safety risk-constrained optimal control problem. Our reformulation method using an extremal representation of the safety risk measure provides a computationally tractable dynamic programming solution. A useful byproduct of the proposed solution is the notion of a risk-constrained safe set, which is a new stochastic safety verification tool. We also establish useful connections between the risk-constrained safe sets and the popular probabilistic safe sets. The tradeoff between the risk tolerance and the mean performance of our controller is examined through an inventory control problem.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ICRA48891.2023.10161100
