arXiv subjects

Anouck Girard

Publications and source records attributed to Anouck Girard.

At least 37 records · Page 2Linked to original sources

arXiv2023

Scheduling Dosage of Proton Pump Inhibitors Using Constrained Optimization With Gastric Acid Secretion Model

Dosage schedule of the Proton Pump Inhibitors (PPIs) is critical for gastric acid disorder treatment. In this paper, we develop a constrained optimization based approach for scheduling the PPIs dosage. In particular, we exploit a mathematical prediction model describing the gastric acid secretion, and use it within the optimization algorithm to predict the acid level. The dosage of the PPIs which is used to enforce acid level constraints is computed by solving a constrained optimization problem. Simulation results show that the proposed approach can successfully suppress the gastric acid level with less PPIs intake compared with the conventional fixed PPIs dosage regimen, which may reduce the long-term side effects of the PPIs.

eess.SY↗

arXiv2022

Set-theoretic Localization for Mobile Robots with Infrastructure-based Sensing

In this paper, we introduce a set-theoretic approach for mobile robot localization with infrastructure-based sensing. The proposed method computes sets that over-bound the robot body and orientation under an assumption of known noise bounds on the sensor and robot motion model. We establish theoretical properties and computational approaches for this set-theoretic localization approach and illustrate its application to an automated valet parking example in simulations and to omnidirectional robot localization problems in real-world experiments. We demonstrate that the set-theoretic localization method can perform robustly against uncertainty set initialization and sensor noises compared to the FastSLAM.

cs.RO↗

arXiv2022

Robust Action Governor for Uncertain Piecewise Affine Systems with Non-convex Constraints and Safe Reinforcement Learning

The action governor is an add-on scheme to a nominal control loop that monitors and adjusts the control actions to enforce safety specifications expressed as pointwise-in-time state and control constraints. In this paper, we introduce the Robust Action Governor (RAG) for systems the dynamics of which can be represented using discrete-time Piecewise Affine (PWA) models with both parametric and additive uncertainties and subject to non-convex constraints. We develop the theoretical properties and computational approaches for the RAG. After that, we introduce the use of the RAG for realizing safe Reinforcement Learning (RL), i.e., ensuring all-time constraint satisfaction during online RL exploration-and-exploitation process. This development enables safe real-time evolution of the control policy and adaptation to changes in the operating environment and system parameters (due to aging, damage, etc.). We illustrate the effectiveness of the RAG in constraint enforcement and safe RL using the RAG by considering their applications to a soft-landing problem of a mass-spring-damper system.

eess.SY↗

arXiv2021

Interaction-Aware Trajectory Prediction and Planning for Autonomous Vehicles in Forced Merge Scenarios

Merging is, in general, a challenging task for both human drivers and autonomous vehicles, especially in dense traffic, because the merging vehicle typically needs to interact with other vehicles to identify or create a gap and safely merge into. In this paper, we consider the problem of autonomous vehicle control for forced merge scenarios. We propose a novel game-theoretic controller, called the Leader-Follower Game Controller (LFGC), in which the interactions between the autonomous ego vehicle and other vehicles with a priori uncertain driving intentions is modeled as a partially observable leader-follower game. The LFGC estimates the other vehicles' intentions online based on observed trajectories, and then predicts their future trajectories and plans the ego vehicle's own trajectory using Model Predictive Control (MPC) to simultaneously achieve probabilistically guaranteed safety and merging objectives. To verify the performance of LFGC, we test it in simulations and with the NGSIM data, where the LFGC demonstrates a high success rate of 97.5% in merging.

eess.SY↗

arXiv2021

Energy-Efficient Autonomous Driving Using Cognitive Driver Behavioral Models and Reinforcement Learning

Autonomous driving technologies are expected to not only improve mobility and road safety but also bring energy efficiency benefits. In the foreseeable future, autonomous vehicles (AVs) will operate on roads shared with human-driven vehicles. To maintain safety and liveness while simultaneously minimizing energy consumption, the AV planning and decision-making process should account for interactions between the autonomous ego vehicle and surrounding human-driven vehicles. In this chapter, we describe a framework for developing energy-efficient autonomous driving policies on shared roads by exploiting human-driver behavior modeling based on cognitive hierarchy theory and reinforcement learning.

cs.RO↗

arXiv2021

Safe Learning Reference Governor: Theory and Application to Fuel Truck Rollover Avoidance

This paper proposes a learning reference governor (LRG) approach to enforce state and control constraints in systems for which an accurate model is unavailable, and this approach enables the reference governor to gradually improve command tracking performance through learning while enforcing the constraints during learning and after learning is completed. The learning can be performed either on a black-box type model of the system or directly on the hardware. After introducing the LRG algorithm and outlining its theoretical properties, this paper investigates LRG application to fuel truck (tank truck) rollover avoidance. Through simulations based on a fuel truck model that accounts for liquid fuel sloshing effects, we show that the proposed LRG can effectively protect fuel trucks from rollover accidents under various operating conditions.

eess.SY↗

arXiv2021

Safe Reinforcement Learning Using Robust Action Governor

Reinforcement Learning (RL) is essentially a trial-and-error learning procedure which may cause unsafe behavior during the exploration-and-exploitation process. This hinders the application of RL to real-world control problems, especially to those for safety-critical systems. In this paper, we introduce a framework for safe RL that is based on integration of a RL algorithm with an add-on safety supervision module, called the Robust Action Governor (RAG), which exploits set-theoretic techniques and online optimization to manage safety-related requirements during learning. We illustrate this proposed safe RL framework through an application to automotive adaptive cruise control.

cs.LG↗

arXiv2021

Coordinated Receding-Horizon Control of Battery Electric Vehicle Speed and Gearshift Using Relaxed Mixed Integer Nonlinear Programming

In this paper, we propose an approach to coordinated receding-horizon control of vehicle speed and transmission gearshift for automated battery electric vehicles (BEVs) to achieve improved energy efficiency. The introduction of multi-speed transmissions in BEVs creates an opportunity to manipulate the operating point of electric motors under given vehicle speed and acceleration command, thus providing the potential to further improve the energy efficiency. However, co-optimization of vehicle speed and transmission gearshift leads to a mixed integer nonlinear program (MINLP), solving which can be computationally very challenging. In this paper, we propose a novel continuous relaxation technique to treat such MINLPs that makes it possible to compute solutions with conventional nonlinear programming solvers. After analyzing its theoretical properties, we use it to solve the optimization problem involved in coordinated receding-horizon control of BEV speed and gearshift. Through simulation studies, we show that co-optimizing vehicle speed and transmission gearshift can achieve considerably greater energy efficiency than optimizing them sequentially, and the proposed relaxation technique can reduce the online computational cost to a level that is comparable to the time available for real-time implementation.

eess.SY↗

arXiv2021

Beating humans in a penny-matching game by leveraging cognitive hierarchy theory and Bayesian learning

It is a long-standing goal of artificial intelligence (AI) to be superior to human beings in decision making. Games are suitable for testing AI capabilities of making good decisions in non-numerical tasks. In this paper, we develop a new AI algorithm to play the penny-matching game considered in Shannon's "mind-reading machine" (1953) against human players. In particular, we exploit cognitive hierarchy theory and Bayesian learning techniques to continually evolve a model for predicting human player decisions, and let the AI player make decisions according to the model predictions to pursue the best chance of winning. Experimental results show that our AI algorithm beats 27 out of 30 volunteer human players.

cs.AI↗

arXiv2020

Chance-Constrained Controller State and Reference Governor

The controller state and reference governor (CSRG) is an add-on scheme for nominal closed-loop systems with dynamic controllers which supervises the controller internal state and the reference input to the closed-loop system to enforce pointwise-in-time constraints. By admitting both controller state and reference modifications, the CSRG can achieve an enlarged constrained domain of attraction compared to conventional reference governor schemes where only reference modification is permitted. This paper studies the CSRG for systems subject to stochastic disturbances and chance constraints. We describe the CSRG algorithm in such a stochastic setting and analyze its theoretical properties, including chance-constraint enforcement, finite-time reference convergence, and closed-loop stability. We also present examples illustrating the application of CSRG to constrained aircraft flight control.

eess.SY↗

arXiv2020

Suboptimal Nonlinear Model Predictive Control Strategies for Tracking Near Rectilinear Halo Orbits

Near Rectilinear Halo Orbits (NRHOs), a subclass of halo orbits around the L1 and L2 Lagrange points, are promising candidates for future lunar gateways in cis-lunar space and as staging orbits for lunar missions. Closed-loop control is beneficial to compensate orbital perturbations and potential instabilities while maintaining spacecraft on NRHOs and performing relative motion maneuvers. This paper investigates the use of nonlinear model predictive control (NMPC) coupled with low-thrust actuators for station-keeping on NRHOs. It is demonstrated through numerical simulations that NMPC is able to stabilize a spacecraft to a reference orbit and handle control constraints. Further, it is shown that the computational burden of NMPC can be managed using specialized optimization routines and suboptimal approaches without jeopardizing closed-loop performance.

eess.SY↗

arXiv2020

Game-theoretic Modeling of Traffic in Unsignalized Intersection Network for Autonomous Vehicle Control Verification and Validation

For a foreseeable future, autonomous vehicles (AVs) will operate in traffic together with human-driven vehicles. Their planning and control systems need extensive testing, including early-stage testing in simulations where the interactions among autonomous/human-driven vehicles are represented. Motivated by the need for such simulation tools, we propose a game-theoretic approach to modeling vehicle interactions, in particular, for urban traffic environments with unsignalized intersections. We develop traffic models with heterogeneous (in terms of their driving styles) and interactive vehicles based on our proposed approach, and use them for virtual testing, evaluation, and calibration of AV control systems. For illustration, we consider two AV control approaches, analyze their characteristics and performance based on the simulation results with our developed traffic models, and optimize the parameters of one of them.

cs.RO↗

arXiv2020

Action Governor for Discrete-Time Linear Systems with Non-Convex Constraints

This paper introduces an add-on, supervisory scheme, referred to as Action Governor (AG), for discrete-time linear systems to enforce exclusion-zone avoidance requirements. It does so by monitoring, and minimally modifying when necessary, the nominal control signal to a constraint-admissible one. The AG operates based on set-theoretic techniques and online optimization. This paper establishes its theoretical foundation, discusses its computational realization, and uses two simulation examples to illustrate its effectiveness.

eess.SY↗

arXiv2020

A Game Theoretic Approach for Parking Spot Search with Limited Parking Lot Information

We propose a game theoretic approach to address the problem of searching for available parking spots in a parking lot and picking the ``optimal'' one to park. The approach exploits limited information provided by the parking lot, i.e., its layout and the current number of cars in it. Considering the fact that such information is or can be easily made available for many structured parking lots, the proposed approach can be applicable without requiring major updates to existing parking facilities. For large parking lots, a sampling-based strategy is integrated with the proposed approach to overcome the associated computational challenge. The proposed approach is compared against a state-of-the-art heuristic-based parking spot search strategy in the literature through simulation studies and demonstrates its advantage in terms of achieving lower cost function values.

cs.RO↗

arXiv2020

Deep Reinforcement Learning with Enhanced Safety for Autonomous Highway Driving

In this paper, we present a safe deep reinforcement learning system for automated driving. The proposed framework leverages merits of both rule-based and learning-based approaches for safety assurance. Our safety system consists of two modules namely handcrafted safety and dynamically-learned safety. The handcrafted safety module is a heuristic safety rule based on common driving practice that ensure a minimum relative gap to a traffic vehicle. On the other hand, the dynamically-learned safety module is a data-driven safety rule that learns safety patterns from driving data. Specifically, the dynamically-leaned safety module incorporates a model lookahead beyond the immediate reward of reinforcement learning to predict safety longer into the future. If one of the future states leads to a near-miss or collision, then a negative reward will be assigned to the reward function to avoid collision and accelerate the learning process. We demonstrate the capability of the proposed framework in a simulation environment with varying traffic density. Our results show the superior capabilities of the policy enhanced with dynamically-learned safety module.

eess.SY↗

arXiv2020

Vision-Based Autonomous Driving: A Model Learning Approach

We present an integrated approach for perception and control for an autonomous vehicle and demonstrate this approach in a high-fidelity urban driving simulator. Our approach first builds a model for the environment, then trains a policy exploiting the learned model to identify the action to take at each time-step. To build a model for the environment, we leverage several deep learning algorithms. To that end, first we train a variational autoencoder to encode the input image into an abstract latent representation. We then utilize a recurrent neural network to predict the latent representation of the next frame and handle temporal information. Finally, we utilize an evolutionary-based reinforcement learning algorithm to train a controller based on these latent representations to identify the action to take. We evaluate our approach in CARLA, a high-fidelity urban driving simulator, and conduct an extensive generalization study. Our results demonstrate that our approach outperforms several previously reported approaches in terms of the percentage of successfully completed episodes for a lane keeping task.

eess.SY↗

arXiv2019

Rapid Uncertainty Propagation and Chance-Constrained Path Planning for Small Unmanned Aerial Vehicles

With the number of small Unmanned Aircraft Systems (sUAS) in the national airspace projected to increase in the next few years, there is growing interest in a traffic management system capable of handling the demands of this aviation sector. It is expected that such a system will involve trajectory prediction, uncertainty propagation, and path planning algorithms. In this work, we use linear covariance propagation in combination with a quadratic programming-based collision detection algorithm to rapidly validate declared flight plans. Additionally, these algorithms are combined with a Dynamic, Informed RRT* algorithm, resulting in a computationally efficient algorithm for chance-constrained path planning. Detailed numerical examples for both fixed-wing and quadrotor sUAS models are presented.

cs.RO↗

arXiv2019

A Novel Approach for Optimal Trajectory Design with Multiple Operation Modes of Propulsion System, Part 1

Efficient performance of a number of engineering systems is achieved through different modes of operation - yielding systems described as "hybrid", containing both real-valued and discrete decision variables. Prominent examples of such systems, in space applications, could be spacecraft equipped with 1) a variable-$I_{\text{sp}}$, variable-thrust engine or 2) multiple engines each capable of switching on/off independently. To alleviate the challenges that arise when an indirect optimization method is used, a new framework --- Composite Smooth Control (CSC) --- is proposed that seeks smoothness over the entire spectrum of distinct control inputs. A salient aftermath of the application of the CSC framework is that the original multi-point boundary-value problem can be treated as a two-point boundary-value problem with smooth, differentiable control inputs; the latter is notably easier to solve, yet can be made to accurately approximate the former hybrid problem. The utility of the CSC framework is demonstrated through a multi-year, multi-revolution heliocentric fuel-optimal trajectory for a spacecraft equipped with a variable-$I_{\text{sp}}$, variable-thrust engine.

math.OC↗