Publications | Qin Lin, 林勤

*: supervised students

2024

Distributed Perception Aware Safe Leader Follower System via Control Barrier Methods Richie Suganda*, Tony Tran, Miao Pan, Lei Fan, Qin Lin, and Bin Hu under review 2024
Disturbance Observer-based Control Barrier Functions with Residual Model Learning for Safe Reinforcement Learning Dvij Kalaria*, Qin Lin, and John M. Dolan under review 2024
Safety Augmentation for Volitional Human Locomotion via Lower-Limb Exoskeletons: A Case Study on Balance Control Miao Yu, Qin Lin, and Ge Lv IEEE Control Systems Letters (L-CSS) 2024
Viewpoints Planning for Active 3-D Reconstruction of Profiled Blades based on DDPG Jun Ye, Qiu Fang, Weixing Peng, Yaonan Wang, and Qin Lin under review 2024 [abstract]
Three-dimensional measurement plays a pivotal role in the aero-engine blade manufacturing process, with viewpoint planning serving as a crucial step in 3D reconstruction. However, most of the existing viewpoint planning methods often rely on discrete space, potentially resulting in missing details when directly employed on the complex surface structure of the blade. Additionally, conventional methods face challenges in controlling the overlap rate of the point cloud due to the thin-walled structure of the blade, which leads to a decrease in the accuracy of the point cloud alignment. This paper introduces a reinforcement learning framework for the viewpoint planning of profiled blades, utilizing the Deep Deterministic Policy Gradient (DDPG) algorithm to address optimal viewpoints in a continuous space. Effective control over the point cloud overlap rate is achieved through the design of a reward function. Furthermore, constraints related to the robot measurement equipment are formulated, enabling the application of obtained viewpoints on any conventional robot equipment. Through experimental testing, our method demonstrates a substantial improvement in point cloud overlap rate control accuracy, surpassing existing methods by an order of magnitude. Our approach achieves higher coverage using fewer viewpoints in comparison to other reinforcement learning-based viewpoint planning methods. Furthermore, it exhibits generalization capabilities and can assess models that have not been previously encountered.
Quadrotor Fault-Tolerant Control at High Speed: A Model-Based Extended State Observer for Mismatched Disturbance Rejection Approach Jinfeng Chen*, Fan Zhang, Bin Hu, Qiu Fang, and Qin Lin under review 2024
Add-on Safe Disturbance Compensation for High-Performance Control of Robotic Systems with Closed Architecture Fan Zhang*, Jinfeng Chen, Joseph Ahanda, Hanz Richter, Ge Lv, and Qin Lin under preparation 2024
Disturbance Rejection-Guarded Learning for Vibration Suppression of Two-Inertia Systems Fan Zhang*, Jinfeng Chen, Yu Hu, Zhiqiang Gao, Ge Lv, and Qin Lin IEEE International Conference on Automation Science and Engineering (CASE) 2024 [abstract] [link]
Model uncertainty presents significant challenges in vibration suppression of multi-inertia systems, as these systems often rely on inaccurate nominal mathematical models due to system identification errors or unmodeled dynamics. An observer, such as an extended state observer (ESO), can estimate the discrepancy between the inaccurate nominal model and the true model, thus improving control performance via disturbance rejection. The conventional observer design is memoryless in the sense that once its estimated disturbance is obtained and sent to the controller, the datum is discarded. In this research, we propose a seamless integration of ESO and machine learning. On one hand, the machine learning model attempts to model the disturbance. With the assistance of prior information about the disturbance, the observer is expected to achieve faster convergence in disturbance estimation. On the other hand, machine learning benefits from an additional assurance layer provided by the ESO, as any imperfections in the machine learning model can be compensated for by the ESO. We validated the effectiveness of this novel learning-for-control paradigm through simulation and physical tests on two-inertial motion control systems used for vibration studies.
Towards Optimal Head-to-head Autonomous Racing with Curriculum Reinforcement Learning Dvij Kalaria*, Qin Lin, and John M. Dolan 2024 [abstract] [link]
Autonomous head-to-head racing presents a formidable challenge, demanding vehicles to operate at the limits of friction and handling in pursuit of minimal lap times, all while strategically seeking to overtake or maintain the lead against opponents. In this work, we introduce a head-to-head racing environment tailored for reinforcement learning that models highly accurate vehicle dynamics. Some prior attempts have sought to directly learn a policy in the complex vehicle dynamics environment but have failed to learn an optimal policy. Our approach, however, centers on a curriculum learning-based framework, progressively transitioning from a simpler vehicle model to a more complex real environment for an approximated optimal policy. Additionally, we propose an innovative safe reinforcement learning algorithm grounded in control barrier functions, which ensures the agent’s safety without compromising optimality.
Adaptive Planning and Control with Time-Varying Tire Models for Autonomous Racing Using Extreme Learning Machine Dvij Kalaria*, Qin Lin, and John M. Dolan IEEE International Conference on Robotics and Automation, ICRA 2024 [abstract] [video] [link]
Autonomous racing is a challenging problem, as the vehicle needs to operate at the friction or handling limits in order to achieve minimum lap times. Autonomous race cars require highly accurate perception, state estimation, planning and precise application of controls. What makes it even more challenging is the accurate identification of vehicle model parameters that dictate the effects of the lateral tire slip, which may change over time, for example, due to wear and tear of the tires. Current works either propose model identification offline or need good parameters to start with (within 15-20% of actual vacdclue), which is not enough to account for major changes in tire model that occur during actual races when driving at the control limits. We propose a unified framework which learns the tire model online from the collected data, as well as adjusts the model based on environmental changes even if the model parameters change by a higher margin. We demonstrate our approach in numeric and high-fidelity simulators for a 1:43 scale race car and a full-size car.

2023

Queue Modeling and Simulation for a Large-scale Municipal Domestic Waste Transfer Station Jiakang Zhou, Qiu Fang, Han Zhu, Yaonan Wang, and Qin Lin under review 2023 [abstract]
A waste transfer station is a critical infrastructure for daily municipal domestic waste management. In this paper, we showcase the modeling and simulation for a complex, large-scale, and real domestic waste transfer station. Thanks to the actual operation situation and historical operation data, our work establishes a high-fidelity multi-step transfer station simulation model. First, the holistic simulation model consists of two sub-models as per the actual operation rules of the transfer station. Without knowing the exact distribution form, a time probability density distribution model is established based on kernel density estimation and incorporated into the two sub-models. Second, built on the simulation model, two operation schemes are proposed to improve the operation efficiency. The simulation results show that the proposed model can accurately capture the behaviors of the waste transfer system. Furthermore, the model carries out validation results and quantitatively analyzes the feasibility of given operation schemes in a real-time manner to assist in decision-making for system operators.
Towards Low-Barrier Cybersecurity Research and Education for Industrial Control Systems Colman McGuan*, Chansu Yu, and Qin Lin IEEE Intelligence and Security Informatics (ISI) 2023 [abstract] [video] [link]
The advent of Industry 4.0 exposes the vulnerability of traditional Industrial Control Systems (ICS) to cyber attacks due to essential cyber components. The protection of ICS that are employed in public critical infrastructures is of utmost importance due to catastrophic physical damages a potential attack may cause. The research community needs testbeds for validation and comparing various intrusion detection algorithms to protect ICS. However, there exist high barriers to entry for research and education in the ICS cybersecurity domain due to expensive hardware, software, and inherent dangers of manipulating real-world systems. To close the gap, built upon recently developed 3D high-fidelity simulators, we further showcase our integrated framework to automatically launch cyberattacks, collect data, train machine learning models, and evaluate for practical chemical and manufacturing processes. We present a novel intrusion detection model called Minimal Threshold and Window SVM (MinTWin SVM) that utilizes unsupervised machine learning via a one-class SVM in combination with a sliding window and classification threshold. The design of MinTWin SVM is driven by the desire to provide continuous and accurate monitoring of the ICS without erroneously identifying the system as under attack as well as to minimize the input to the classifier in the interest of lessening computational overhead. Results show that MinTWin SVM minimizes false positives and is responsive to physical process anomalies. Furthermore, we incorporate our framework with ICS cybersecurity education by using our dataset in an undergraduate machine learning course where students gain hands-on experience in practicing machine learning theory with a practical ICS dataset. All of our implementations have been open-sourced.
Towards Safety Assured End-to-End Vision-Based Control for Autonomous Racing Dvij Kalaria*, Qin Lin, and John M. Dolan IFAC World Congress 2023 [abstract] [video]
Autonomous car racing is a challenging task, as it requires precise applications of control while the vehicle is operating at cornering speeds. Traditional autonomous pipelines require accurate pre-mapping, localization, and planning which make the task computationally expensive and environment-dependent. Recent works propose use of imitation and reinforcement learning to train end-to-end deep neural networks and have shown promising results for high-speed racing. However, the end-to-end models may be dangerous to be deployed on real systems, as the neural networks are treated as black-box models devoid of any provable safety guarantees. In this work we propose a decoupled approach where an optimal end-to-end controller and a state prediction end-to-end model are learned together, and the predicted state of the vehicle is used to formulate a control barrier function for safeguarding the vehicle to stay within lane boundaries. We validate our algorithm both on a high-fidelity Carla driving simulator and a 1/10-scale RC car on a real track. The evaluation results suggest that using an explicit safety controller helps to learn the task safely with fewer iterations and makes it possible to safely navigate the vehicle on the track along the more challenging racing line.
Spatio-temporal Motion Planning for Autonomous Vehicles with Trapezoidal Prism Corridors and Bezier Curves Srujan Deolasee*, Qin Lin, Jialun Li, and John M. Dolan American Control Conference (ACC) 2023 [abstract] [link]
Safety-guaranteed motion planning is critical for self-driving cars to generate collision-free trajectories. A layered motion planning approach with decoupled path and speed planning is widely used for this purpose. This approach is prone to be suboptimal in the presence of dynamic obstacles. Spatial-temporal approaches deal with path planning and speed planning simultaneously; however, the existing methods only support simple-shaped corridors like cuboids, which restrict the search space for optimization in complex scenarios. We propose to use trapezoidal prism-shaped corridors for optimization, which significantly enlarges the solution space compared to the existing cuboidal corridors-based method. Finally, a piecewise Bézier curve optimization is conducted in our proposed corridors. This formulation theoretically guarantees the safety of the continuous-time trajectory. We validate the efficiency and effectiveness of the proposed approach in numerical and CommonRoad simulations.
Robust Control Barrier Functions for Safe Control Under Uncertainty Using Extended State Observer and Output Measurement Jinfeng Chen*, Zhiqiang Gao, and Qin Lin IEEE Conference on Decision and Control (CDC) 2023 [abstract] [link]
Control barrier functions-based quadratic programming (CBF-QP) method is gaining popularity as a controller synthesis tool for safe control owing to its appearing forward invariant set property. However, the provable safety is established on an accurate dynamic model and access to all states. To address such a vulnerability, this paper proposes a novel design combining an extended state observer (ESO) with a CBF for safe control of a system with model uncertainty and external disturbances only using output measurement. Unlike other disturbance observer-based CBFs, ESO is a more general approach to directly estimate the disturbances in the original system rather than the effect of the disturbance on CBF. As a result, our approach delivers a less conservative estimation error bound. Moreover, only output measurements are needed to estimate the disturbances instead of the full access to states. The bound of state estimation error and disturbance estimation error is derived in a unified manner and then used for robust safe control under uncertainty. We validate our approach?s efficacy in numerical simulations of an adaptive cruise control system and a Segway self-balancing scooter.
Delay-aware Robust Control for Safe Autonomous Driving and Racing Dvij Kalaria*, Qin Lin, and John M. Dolan IEEE Transactions on Intelligent Transportation Systems 2023 [abstract] [video] [link]
Delays endanger safety of autonomous systems operating in a rapidly changing environment, such as nondeterministic surrounding traffic participants in autonomous driving and high-speed racing. Unfortunately, delays are typically not considered during the conventional controller design or learning-enabled controller training phases prior to deployment in the physical world. In this paper, the computation delay from nonlinear optimization for motion planning and control, as well as other unavoidable delays caused by actuators, are addressed systematically and unifiedly. To deal with all these delays, in our framework: 1) we propose a new filtering approach with no prior knowledge of dynamics and disturbance distribution to adaptively and safely estimate the time-variant computation delay; 2) we model actuation dynamics for steering delay; 3) all the constrained optimization is realized in a robust tube model predictive controller. For the application merits, we demonstrate that our approach is suitable for both autonomous driving and autonomous racing. Our approach is a novel design for a standalone delay compensation controller. In addition, in the case that a learning-enabled controller assuming no delay works as a primary controller, our approach serves as the primary controller’s safety guard. The video demonstration is available online.

2022

Motion Planning by Search in Derivative Space and Convex Optimization with Enlarged Solution Space Jialun Li*, Xiaojia Xie, Qin Lin, Jianping He, and John M. Dolan IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022 [abstract] [video] [link]
To efficiently generate safe trajectories for an autonomous vehicle in dynamic environments, a layered motion planning method with decoupled path and speed planning is widely used. This paper studies speed planning, which mainly deals with dynamic obstacle avoidance given a planned path. The main challenges lie in the optimization in a non-convex space and the trade-off between safety, comfort, and efficiency. First, this work proposes to conduct a search in second-order derivative space for generating a comfort-optimal reference trajectory. Second, by combining abstraction and refinement, an algorithm is proposed to construct a convex feasible space for optimization. Finally, a piecewise B ́ezier polynomial optimization approach with trapezoidal corridors is presented, which theoretically guarantees safety and significantly enlarges the solution space compared with the existing rectangular corridors-based approach. We validate the efficiency and effectiveness of the proposed approach in simulations
Online Adaptive Compensation for Model Uncertainty Using Extreme Learning Machine-based Control Barrier Functions Emanuel Munoz Panduro*, Dvij Kalaria, Qin Lin, and John M. Dolan IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022 [abstract] [video] [link]
A control barrier functions-based quadratic programming (CBF-QP) method has emerged as a controller synthesis tool to assure safety of autonomous systems owing to the appealing safe forward invariant set. However, the provable safety relies on a precisely described dynamic model, which is not always available in practice. Recent works leverage learning to compensate model uncertainty for a CBF controller. However, these approaches based on reinforcement learning or episodic learning are limited to dealing with time-invariant uncertainty. Also, the reinforcement learning approach learns the uncertainty offline, while episodic learning only updates the controller after a batch of data is available by the end of an episode. Instead, we propose a novel tuning extreme learning machine (tELM)-based CBF controller that can compensate time-variant and time-invariant model uncertainty adaptively in an online manner. We validate our approach’s effectiveness in a simulation of an Adaptive Cruise Control (ACC) system.
Delay-aware Robust Control for Safe Autonomous Driving Dvij Kalaria*, Qin Lin, and John M Dolan IEEE Intelligent Vehicles Symposium (IV) oral, selection rate: 10%, 2022 [abstract] [video] [link]
With the advancement of affordable self-driving vehicles using complicated nonlinear optimization but limited computation resources, computation time becomes a matter of concern. Other factors such as actuator dynamics and actuator command processing cost also unavoidably cause delays. In high-speed scenarios, these delays are critical to the safety of a vehicle. Recent works consider these delays individually, but none unifies them all in the context of autonomous driving. Moreover, recent works inappropriately consider computation time as a constant or a large upper bound, which makes the control either less responsive or over-conservative. To deal with all these delays, we present a unified framework by 1) modeling actuation dynamics, 2) using robust tube model predictive control, and 3) using a novel adaptive Kalman filter without assuming a known process model and noise covariance, which makes the controller safe while minimizing conservativeness. On the one hand, our approach can serve as a standalone controller; on the other hand, our approach provides a safety guard for a high-level controller, which assumes no delay. This can be used for compensating the sim-to-real gap when deploying a black-box learning-enabled controller trained in a simplistic environment without considering delays for practical vehicle systems.

2021

Safe and resilient practical waypoint-following for autonomous vehicles Qin Lin, Stefan Mitsch, André Platzer, and John M. Dolan IEEE Control Systems Letters 2021 [abstract] [video] [link]
We combine theorem proving and reachability analysis for cyber-physical systems verification to arrive at a practical approach to safe waypoint-following for an autonomous mobile vehicle controlled by a learning-enabled controller. We propose a robust monitor verifying short-term and long-term safety simultaneously at runtime, thereby combining the benefits of both theorem proving and reachability analysis. The proposed novel monitor architecture allows temporary violation of long-term safety while maintaining short-term safety to recover to a state with long-term safety. The recovery is based on a fallback model predictive controller. The experiments conducted in a high-fidelity racing car simulator demonstrate that our framework is safe and resilient in path tracking scenarios, in which avoiding collision with the race track boundary and obstacles is required.
Safe planning and control under uncertainty for self-driving Shivesh Khaitan*, Qin Lin, and John M. Dolan IEEE Transactions on Vehicular Technology 2021 [abstract] [video] [link]
Motion planning under uncertainty is critical for safe self-driving. This paper proposes a unified obstacle avoidance framework that deals with 1) uncertainty in ego-vehicle motion; and 2) prediction uncertainty of dynamic obstacles from the environment. A two-stage traffic participant trajectory predictor comprising short-term and long-term prediction is used in the planning layer to generate safe but not over-conservative trajectories for the ego-vehicle. The prediction module cooperates well with existing planning approaches. Our work showcases its effectiveness in a Frenet frame planner. A robust controller using tube MPC guarantees safe execution of the trajectory in the presence of state noise and dynamic model uncertainty. A Gaussian process regression model is used for on-line identification of the uncertainty’s bound. We demonstrate the effectiveness, safety, and real-time performance of our framework in the CARLA simulator.
Jerk-Minimized CILQR for Human-Like Driving on Two-Lane Roadway Omid Jahanmahin, Qin Lin, Yanjun Pan, and John M. Dolan IEEE Intelligent Vehicles Symposium (IV) 2021 [abstract] [link]
This work proposes a novel framework for motion planning using trajectory optimization for autonomous driving. First, a two-phase behavioral policy maker (BPM) is proposed as a high-level decision maker to mimic human-like driving style by avoiding unnecessary tasks and early lane changes. Second, a comprehensive study on iterative adaptive weight tuning functions has been done to limit manual weight tuning in the Constrained Iterative Linear Quadratic Regulator (CILQR) motion planner. Third, a jerk-minimized CILQR is presented to ensure the comfort and safety of passengers by generating smooth trajectories. The simulation results show efficiency, safety, and comfort of generated trajectories.

2020

Measuring similarity of interactive driving behaviors using matrix profile Qin Lin, Wenshuoa Wang, Yihuan Zhang, and John M. Dolan American Control Conference (ACC) 2020 [abstract] [link]
Understanding multi-vehicle interactive behaviors with temporal sequential observations is crucial for autonomous vehicles to make appropriate decisions in an uncertain traffic environment. On-demand similarity measures are significant for autonomous vehicles to deal with massive interactive driving behaviors by clustering and classifying diverse scenarios. This paper proposes a general approach for measuring spatiotemporal similarity of interactive behaviors using a multivariate matrix profile technique. The key attractive features of the approach are its reduced space and time complexity, real-time online computing for streaming traffic data, and possible capability of leveraging hardware for parallel computation. The proposed approach is validated through automatically discovering similar interactive driving behaviors at intersections from sequential data.
Safe planning for self-driving via adaptive constrained ILQR Yanjun Pan*, Qin Lin, Het Shah, and John M. Dolan IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2020 [abstract] [link]
Constrained Iterative Linear Quadratic Regulator (CILQR), a variant of ILQR, has been recently proposed for motion planning problems of autonomous vehicles to deal with constraints such as obstacle avoidance and reference tracking. However, the previous work considers either deterministic trajectories or persistent prediction for target dynamical obstacles. The other drawback is lack of generality - it requires manual weight tuning for different scenarios. In this paper, two significant improvements are achieved. Firstly, a twostage uncertainty-aware prediction is proposed. The short-term prediction with safety guarantee based on reachability analysis is responsible for dealing with extreme maneuvers conducted by target vehicles. The long-term prediction leveraging an adaptive least square filter preserves the long-term optimality of the planned trajectory since using reachability only for long-term prediction is too pessimistic and makes the planner over-conservative. Secondly, to allow a wider coverage over different scenarios and to avoid tedious parameter tuning case by case, this paper designs a scenario-based analytical function taking the states from the ego vehicle and the target vehicle as input, and carrying weights of a cost function as output. It allows the ego vehicle to execute multiple behaviors (such as lane-keeping and overtaking) under a single planner. We demonstrate safety, effectiveness, and real-time performance of the proposed planner in simulations.
Reachflow: An online safety assurance framework for waypoint-following of self-driving cars Qin Lin, Xin Chen, Aman Khurana, and John M. Dolan IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2020 [abstract] [link]
Learning-enabled components have been widely deployed in autonomous systems. However, due to the weak interpretability and the prohibitively high complexity of large-scale machine learning models such as neural networks, reliability has been a crucial concern for safety-critical autonomous systems. This work proposes an online monitor called Reach-Flow for fault prevention of waypoint-following tasks for self-driving cars. It mainly consists of two components: (a) an online verification tool which conservatively checks the safety of the system behavior in the near future, and (b) a fallback controller which steers the system back to a desired state when the system is potentially unsafe. We implement ReachFlow in a self-driving racing car governed by a reinforcement learning-based controller. We demonstrate the effectiveness by rigorously verifying a safe waypoint-following control and providing a fallback control for an unsafe situation in which a large deviation from the planned path is predicted.
Safety verification of a data-driven adaptive cruise controller Qin Lin, Sicco Verwer, and John M. Dolan IEEE Intelligent Vehicles Symposium (IV) 2020 [abstract] [link]
Imitation learning provides a way to automatically construct a controller by mimicking human behavior from data. For safety-critical systems such as autonomous vehicles, it can be problematic to use controllers learned from data because they cannot be guaranteed to be collision-free. Recently, a method has been proposed for learning a multi-mode hybrid automaton cruise controller (MOHA). Besides being accurate, the logical nature of this model makes it suitable for formal verification. In this paper, we demonstrate this capability using the SpaceEx hybrid model checker as follows. We develop an automated tool to translate the automaton model into constraints and equations required by SpaceEx. We then verify that a pure MOHA controller is not collision-free. By adding a safety state based on headway in time, a rule that human drivers should follow anyway, we do obtain a provably safe cruise control. Moreover, the safe controller remains more humanlike than existing cruise controllers.

2019

Using datasets from industrial control systems for cyber security research and education Qin Lin, Sicco Verwer, Robert Kooij, and Aditya Mathur International Conference on Critical Information Infrastructures Security 2019 [abstract] [link]
The availability of high-quality benchmark datasets is an important prerequisite for research and education in the cyber security domain. Datasets from realistic systems offer a platform for researchers to develop and test novel models and algorithms. Such datasets also offer students opportunities for active and project-centric learning. In this paper, we describe six publicly available datasets from the domain of Industrial Control Systems (ICS). Five of these datasets are obtained through experiments conducted in the context of operational ICS while the sixth is obtained from a widely used simulation tool, namely EPANET, for large scale water distribution networks. This paper presents two studies on the use of the datasets. The first study uses the dataset from a live water treatment plant. This study leads to a novel and explainable anomaly detection method based upon Timed Automata and Bayesian Networks. The study conducted in the context of education made use of the water distribution network dataset in a graduate course on cyber data analytics. Through an assignment, students explored the effectiveness of various methods for anomaly detection. Research outcomes and the success of the course indicate an appreciation in the research community and positive learning experience in education.
Intelligent control systems: Learning, interpreting, verification
Ph.D. dissertation
Qin Lin 2019 [link]

2018

TABOR: A graphical model-based approach for anomaly detection in industrial control systems Qin Lin, Sridha Adepu, Sicco Verwer, and Aditya Mathur Asia conference on computer and communications security (AsiaCCS), acceptance rate: 62/320=20%, 2018 [abstract] [link] [slides]
Industrial Control Systems (ICS) such as water and power are critical to any society. Process anomaly detection mechanisms have been proposed to protect such systems to minimize the risk of damage or loss of resources. In this paper, a graphical model-based approach is proposed for profiling normal operational behavior of an operational ICS referred to as SWaT (Secure Water Treatment). Timed automata are learned as a model of regular behaviors shown in sensors signal like fluctuations of water level in tanks. Bayesian networks are learned to discover dependencies between sensors and actuators. The models are used as a one-class classifier for process anomaly detection, recognizing irregular behavioral patterns and dependencies. The detection results can be interpreted and the abnormal sensors or actuators localized due to the interpretability of the graphical models. This approach is applied to a dataset collected from SWaT. Experimental results demonstrate the model’s superior performance on both precision and run-time over methods including support vector machine and deep neural networks. The underlying idea is generic and applicable to other industrial control systems such as power and transportation.
Lane-change intention estimation for car-following control in autonomous driving Yihuan Zhang, Qin Lin, Jun Wang, Sicco Verwer, and John M. Dolan IEEE Transactions on Intelligent Vehicles 2018 [abstract] [link]
Car-following is the most general behavior in highway driving. It is crucial to recognize the cut-in intention of vehicles from an adjacent lane for safe and cooperative driving. In this paper, a method of behavior estimation is proposed to recognize and predict the lane change intentions based on the contextual traffic information. A model predictive controller is designed to optimize the acceleration sequences by incorporating the lane-change intentions of other vehicles. The public data set of next generation simulation is labeled and then published as a benchmarking platform for the research community. Experimental results demonstrate that the proposed method can accurately estimate vehicle behavior and therefore outperform the traditional car-following control.
MOHA: A multi-mode hybrid automaton model for learning car-following behaviors Qin Lin, Yihuan Zhang, Sicco Verwer, and Jun Wang IEEE Transactions on Intelligent Transportation Systems 2018 [abstract] [link]
This paper proposes a novel hybrid model for learning discrete and continuous dynamics of car-following behaviors. Multiple modes representing driving patterns are identified by partitioning the model into groups of states. The model is visualizable and interpretable for car-following behavior recognition, traffic simulation, and human-like cruise control. The experimental results using the next generation simulation datasets demonstrate its superior fitting accuracy over conventional models.

2017

A data-driven behavior generation algorithm in car-following scenarios Yihuan Zhang, Jun Wang, Qin Lin, Sicco Verwer, and John M. Dolan 2017 [abstract] [link]
The conventional Adaptive Cruise Control system lacks user-friendly design. In this paper, a novel method for learning a generative model from human drivers car-following data using an automaton learning algorithms is proposed. By partitioning the model using frequent common state sequences, human driving patterns are extracted and clustered. Then a cluster identification method is used to obtain the current driving pattern and generate a desired acceleration. The experiments validate that the simulated trajectories of the proposed method are more similarly to human drivers than those of conventional PID controller.
Car-following behavior model learning using timed automata Yihuan Zhang, Qin Lin, Jun Wang, and Sicco Verwer IFAC-PapersOnLine 2017 [abstract] [link]
Learning driving behavior is fundamental for autonomous vehicles to understand traffic situations. This paper proposes a novel method for learning a behavioral model of car-following using automata learning algorithms. The model is interpretable for car-following behavior analysis. Frequent common state sequences are extracted from the model and clustered as driving patterns. The Next Generation SIMulation dataset on the I-80 highway is used for learning and evaluating. The experimental results demonstrate high accuracy of car-following model fitting.
Anomaly Detection in a Digital Video Broadcasting System Using Timed Automata Xiaoran Liu*, Qin Lin, Sicco Verwer, and Dmitri Jarnikov Thirty-Second Annual ACM/IEEE Symposium on Logic in Computer Science (LICS) Workshop on Learning and Automata (LearnAut) 2017 [abstract] [link]
This paper focuses on detecting anomalies in a digital video broadcasting (DVB) system from providers’ perspective. We learn a probabilistic deterministic real timed automaton profiling benign behavior of encryption control in the DVB control access system. This profile is used as a one-class classifier. Anomalous items in a testing sequence are detected when the sequence is not accepted by the learned model.
Learning behavioral fingerprints from netflows using timed automata Gaetano Pellegrino, Qin Lin, Christian Hammerschmidt, and Sicco Verwer IFIP/IEEE Symposium on Integrated Network and Service Management (IM) 2017 [abstract] [link]
We present a novel way to detect infected hosts and identify malware in networks by analyzing network communication statistics with state-of-the-art automata learning algorithms. The automata encode patterns of short-term interactions in known malicious hosts, and are used to obtain small but effective fingerprints of machine behavior. We showcase the effectiveness of our system, named BASTA 1 (Behavioral Analytics System using Timed Automata), on a public dataset containing Netflow traces of real-world botnet malware. Compared to a deep packet inspection of communication content, Netflows are easy and cheap to collect and analyze, and preserve a greater degree of privacy. Even though the high level of abstraction in Netflow data makes it more difficult to utilize it, BASTA shows very impressive results achieving high accuracy in several settings while returning few false positives. It is also capable of detecting infections of previously unseen malware.
Learning deterministic finite automata from infinite alphabets Gaetano Pellegrino, Christian Hammerschmidt, Qin Lin, and Sicco Verwer International Conference on Grammatical Inference 2017 [abstract] [link]
We proposes an algorithm to learn automata infinite alphabets, or at least too large to enumerate. We apply it to define a generic model intended for regression, with transitions constrained by intervals over the alphabet. The algorithm is based on the Red & Blue framework for learning from an input sample. We show two small case studies where the alphabets are respectively the natural and real numbers, and show how nice properties of automata models like interpretability and graphical representation transfer to regression where typical models are hard to interpret.

2016

Interpreting Finite Automata for Sequential Data Christian Hammerschmidt, Verwer, and Qin Lin NIPS workshop proceedings 2016 [abstract] [link]
Automaton models are often seen as interpretable models. Interpretability itself is not well defined: it remains unclear what interpretability means without first explicitly specifying objectives or desired attributes. In this paper, we identify the key properties used to interpret automata and propose a modification of a state-merging approach to learn variants of finite state automata. We apply the approach to problems beyond typical grammar inference tasks. Additionally, we cover several use-cases for prediction, classification, and clustering on sequential data in both supervised and unsupervised scenarios to show how the identified key properties are applicable in a wide range of contexts.
Short-term Time Series Forecasting with Regression Automata Qin Lin, Christian Hammerschmidt, Gaetano Pellegrino, and Sicco Verwer Interpretable Machine Learning for Complex Systems: NIPS workshop proceedings 2016 [abstract] [video] [link]
We present regression automata (RA), which are novel type syntactic models for time series forecasting. Building on top of conventional state-merging algorithms for identifying automata, RA use numeric data in addition to symbolic values and make predictions based on this data in a regression fashion. We apply our model to the problem of hourly wind speed and wind power forecasting. Our results show that RA outperform other state-of-the-art approaches for predicting both wind speed and power generation. In both cases, short-term predictions are used for resource allocation and infrastructure load balancing. For those critical tasks, the ability to inspect and interpret the generative model RA provide is an additional benefit.

2014

Automatic contour-based road network design for optimized wind farm micrositing Huajie Gu, Jun Wang, Qin Lin, and Qi Gong IEEE Transactions on Sustainable Energy 2014 [abstract] [link]
Constructing the access roads between wind turbines requires a significant cost when a wind farm is built in hills or mountains. An optimized design of road network can substantially reduce construction costs and increase investment returns. In this paper, we consider a challenging problem of the road network design for a wind farm with complex topography. An automatic contour-based model is developed for road network design, and is incorporated into the optimization of wind farm micrositing to maximize investment returns of the wind farm. The directions of access roads are first deduced from a contour tree, the route projections are then designed by a gradient-bounded algorithm, and the most cost-effective road network is finally obtained by the minimum spanning tree algorithm. The topographic speedup, wind resource grid and Park wake model are incorporated to accurately evaluate the power production of the wind farm. Both the profit of wind energy sales and the cost of access roads are combined into a cost function called net present value, which is optimized using genetic algorithms. Simulation results illustrate that the length of access roads is decreased significantly while the locations of wind turbines are optimized. The proposed method simultaneously optimizes the turbine layout and road network of the wind farm, therefore achieving a more practical and profitable wind farm micrositing.
Vertically correlated echelon model for the interpolation of missing wind speed data Qin Lin, and Jun Wang IEEE Transactions on Sustainable Energy 2014 [abstract] [link]
The wind speeds of a wind farm are not always available or accurately measurable due to uncontrollable events such as anemometer failures or data transmission errors. However, the data are of great importance for wind resource assessment and wind speed prediction. In this paper, a vertically correlated echelon model (CEM) is proposed to interpolate the missing data of wind speeds by utilizing the correlation of wind speeds at different heights. First, the data of wind speed are checked according to a national standard. Second, the model based on the correlation of wind speeds at different heights is proposed for short interval of missing data. Third, the proposed method is compared with typical interpolation methods and its advantages and disadvantages are discussed. Finally, the uncertainty of the proposed method is analyzed for improved evaluation of interpolation errors.

2013

Denoising of wind speed data by wavelet thresholding Qin Lin, Jun Wang, and Weiting Qiao Chinese Automation Congress 2013 [abstract] [link]
Completeness and reasonableness test of wind farm data is a critical prerequisite for wind speed prediction, meanwhile it plays an important role on the reliability and safety of the grids. The key to dealing with the unreasonable data lies in eliminating the noise. In this work, we perform an analysis of the noise source of wind speed data observed in wind farm and highlight using the wavelet analysis to eliminate the noise. To test the denoising effect, the equivalent wind speed model is then established. Experiment results show that the effective preprocessing of the raw data yield good performance for attenuating the influence of noises.