arXiv subjects

Kaian Chen

Publications and source records attributed to Kaian Chen.

7 recordsLinked to original sources

arXiv2025

Safe Data-Driven Predictive Control

In the realm of control systems, model predictive control (MPC) has exhibited remarkable potential; however, its reliance on accurate models and substantial computational resources has hindered its broader application, especially within real-time nonlinear systems. This study presents an innovative control framework to enhance the practical viability of the MPC. The developed safe data-driven predictive control aims to eliminate the requirement for precise models and alleviate computational burdens in the nonlinear MPC (NMPC). This is achieved by learning both the system dynamics and the control policy, enabling efficient data-driven predictive control while ensuring system safety. The methodology involves a spatial temporal filter (STF)-based concurrent learning for system identification, a robust control barrier function (RCBF) to ensure the system safety amid model uncertainties, and a RCBF-based NMPC policy approximation. An online policy correction mechanism is also introduced to counteract performance degradation caused by the existing model uncertainties. Demonstrated through simulations on two applications, the proposed approach offers comparable performance to existing benchmarks with significantly reduced computational costs.

eess.SY↗

arXiv2023

Privacy-Preserving Data-Enabled Predictive Leading Cruise Control in Mixed Traffic

Data-driven predictive control of connected and automated vehicles (CAVs) has received increasing attention as it can achieve safe and optimal control without relying on explicit dynamical models. However, employing the data-driven strategy involves the collection and sharing of privacy-sensitive vehicle information, which is vulnerable to privacy leakage and might further lead to malicious activities. In this paper, we develop a privacy-preserving data-enabled predictive control scheme for CAVs in a mixed traffic environment, where human-driven vehicles and CAVs coexist. We tackle external eavesdroppers and honest-but-curious central unit eavesdroppers who wiretap the communication channel of the mixed traffic system and intend to infer the CAVs' state and input information. An affine masking-based privacy protection method is designed to conceal the true state and input signals, and an extended form of the data-enabled predictive leading cruise control under different matrix structures is derived to achieve privacy-preserving optimal control for CAVs. Numerical simulations demonstrate that the proposed scheme can protect the privacy of CAVs against attackers without affecting control performance or incurring heavy computations.

eess.SY↗

arXiv2023

A Unified Framework for Online Data-Driven Predictive Control with Robust Safety Guarantees

Despite great successes, model predictive control (MPC) relies on an accurate dynamical model and requires high onboard computational power, impeding its wider adoption in engineering systems, especially for nonlinear real-time systems with limited computation power. These shortcomings of MPC motivate this work to make such a control framework more practically viable for real-world applications. Specifically, to remove the required accurate dynamical model and reduce the computational cost for nonlinear MPC (NMPC), this paper develops a unified online data-driven predictive control pipeline to efficiently control a system with guaranteed safety without incurring large computational complexity. The new aspect of this idea is learning not only the real system but also the control policy, which results in a reasonable computational cost for the data-driven predictive controllers. More specifically, we first develop a spatial temporal filter (STF)-based concurrent learning scheme to systematically identify system dynamics for general nonlinear systems. We then develop a robust control barrier function (RCBF) for safety guarantees in the presence of model uncertainties and learn the RCBF-based NMPC policy. Furthermore, to mitigate the performance degradation due to the existing model uncertainties, we propose an online policy correction scheme through perturbation analysis and design of an ancillary feedback controller. Finally, extensive simulations on two applications, cart-inverted pendulum and automotive powertrain control, are performed to demonstrate the efficacy of the proposed framework, which shows comparable performance with much lower computational cost in comparison with several benchmark algorithms.

eess.SY↗

arXiv2023

Data-Enabled Predictive Control for Fast Charging of Lithium-Ion Batteries with Constraint Handling

Fast charging of lithium-ion batteries has gained extensive research interests, but most of existing methods are either based on simple rule-based charging profiles or require explicit battery models that are non-trivial to identify accurately. In this paper, instead of relying on parametric battery models that are costly to derive and calibrate, we employ a novel data-enabled predictive control (DeePC) paradigm to perform safe and optimal fast charging for lithium-ion batteries. The developed DeePC methodology is based on behavioral system theory and directly utilizes the input-output measurements from the battery system to predict the future trajectory and compute the optimal control policy. Constraints on input current and battery states are incorporated in the DeePC formulation to ensure battery fast charging with safe operations. Furthermore, we propose a principal component analysis based scheme to reduce the dimension of the optimization variables in the DeePC algorithm, which significantly enhances the computation efficiency without compromising the charging performance. Numerical simulations are performed on a high-fidelity battery simulator to validate the efficacy of the proposed fast charging strategy.

eess.SY↗

arXiv2022

Deep Multi-agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic

On-ramp merging is a challenging task for autonomous vehicles (AVs), especially in mixed traffic where AVs coexist with human-driven vehicles (HDVs). In this paper, we formulate the mixed-traffic highway on-ramp merging problem as a multi-agent reinforcement learning (MARL) problem, where the AVs (on both merge lane and through lane) collaboratively learn a policy to adapt to HDVs to maximize the traffic throughput. We develop an efficient and scalable MARL framework that can be used in dynamic traffic where the communication topology could be time-varying. Parameter sharing and local rewards are exploited to foster inter-agent cooperation while achieving great scalability. An action masking scheme is employed to improve learning efficiency by filtering out invalid/unsafe actions at each step. In addition, a novel priority-based safety supervisor is developed to significantly reduce collision rate and greatly expedite the training process. A gym-like simulation environment is developed and open-sourced with three different levels of traffic densities. We exploit curriculum learning to efficiently learn harder tasks from trained models under simpler settings. Comprehensive experimental results show the proposed MARL framework consistently outperforms several state-of-the-art benchmarks.

eess.SY↗

arXiv2021

Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement

Reinforcement learning (RL) is a powerful data-driven control method that has been largely explored in autonomous driving tasks. However, conventional RL approaches learn control policies through trial-and-error interactions with the environment and therefore may cause disastrous consequences such as collisions when testing in real-world traffic. Offline RL has recently emerged as a promising framework to learn effective policies from previously-collected, static datasets without the requirement of active interactions, making it especially appealing for autonomous driving applications. Despite promising, existing offline RL algorithms such as Batch-Constrained deep Q-learning (BCQ) generally lead to rather conservative policies with limited exploration efficiency. To address such issues, this paper presents an enhanced BCQ algorithm by employing a learnable parameter noise scheme in the perturbation model to increase the diversity of observed actions. In addition, a Lyapunov-based safety enhancement strategy is incorporated to constrain the explorable state space within a safe region. Experimental results in highway and parking traffic scenarios show that our approach outperforms the conventional RL method, as well as state-of-the-art offline RL algorithms.

cs.RO↗

arXiv2020

MPC-based Vibration Control and Energy Harvesting Using an Electromagnetic Vibration Absorber With Inertia Nonlinearity

Simultaneous vibration control and energy harvesting of vehicle suspensions has attracted great research interests over the past decades. However, existing frameworks tradeoff suspension performance for energy recovery and are only responsive to narrow-bandwidth vibrations. In this paper, a new energy-regenerative vibration absorber (ERVA) using a ball-screw mechanism is investigated. The ERVA system is based on a rotary electromagnetic generator with adjustable nonlinear rotational inertia which passively increases the moment of inertia as the vibration amplitude increases. This structure is effective for energy harvesting and vibration control without increasing the suspension size. Furthermore, a nonlinear model predictive controller (NMPC) is applied to the system for further performance enhancement where we exploit road profile information as a preview. The performance of NMPC-based ERVA is demonstrated in a number of simulations and superior performance is demonstrated.

eess.SY↗