Silvia Strada | Politecnico di Milano (original) (raw)

Papers by Silvia Strada

Research paper thumbnail of Sliding mode control for LPV systems

LPV models are extremely appealing, as they allow describing the dynamics of many physical system... more LPV models are extremely appealing, as they allow describing the dynamics of many physical systems that are of interest in various engineering applications. For such systems, dedicated control approaches have been proposed, which rely on the measurement of the scheduling variables and exploit such information for improving the closed-loop performance with respect to fixed-structure, possibly robust, solutions. Unfortunately, such control techniques are often not so simple to tune and design, especially when also parametric uncertainties affect the system, thus requiring LPV-robust control techniques. In this work we explore the advantages offered by sliding mode (SM) algorithms for the control of LPV systems, showing that a fixed-structure SM approach can outperform genuine LPV solutions in the case of parametric uncertainties on the system model without additional tuning and design needs. A case study considering the control of lateral vehicle dynamics is used to investigate the performance of the different approaches, showing promising results for extending SM controllers to cope with additional uncertainties affecting LPV systems, that may be difficult to act upon with traditional methods.

Research paper thumbnail of MIRACLE: MInd ReAding CLassification Engine

IEEE Transactions on Neural Systems and Rehabilitation Engineering

Brain-computer interfaces (BCIs) have revolutionized the way humans interact with machines, parti... more Brain-computer interfaces (BCIs) have revolutionized the way humans interact with machines, particularly for patients with severe motor impairments. EEG-based BCIs have limited functionality due to the restricted pool of stimuli that they can distinguish, while those elaborating event-related potentials up to now employ paradigms that require the patient's perception of the eliciting stimulus. In this work, we propose MIRACLE: a novel BCI system that combines functional data analysis and machine-learning techniques to decode patients' minds from the elicited potentials. MIRACLE relies on a hierarchical ensemble classifier recognizing 10 different semantic categories of imagined stimuli. We validated MIRACLE on an extensive dataset collected from 20 volunteers, with both imagined and perceived stimuli, to compare the system performance on the two. Furthermore, we quantify the importance of each EEG channel in the decision-making process of the classifier, which can help reduce the number of electrodes required for data acquisition, enhancing patients' comfort.

Research paper thumbnail of Real Time Passenger Mass Estimation for e-scooters

2023 American Control Conference (ACC)

Research paper thumbnail of Driving electric vehicles’ mass adoption: An architecture for the design of human-centric policies to meet climate and societal goals

Transportation Research Part A: Policy and Practice

Research paper thumbnail of Social network analysis of electric vehicles adoption: a data-based approach

2020 IEEE International Conference on Human-Machine Systems (ICHMS), 2020

Mobility is undergoing dramatic transformations. Especially in the context of urban areas, severa... more Mobility is undergoing dramatic transformations. Especially in the context of urban areas, several significant changes are underway, driven by both new mobility needs and environmental concerns. The most mature one, which still is struggling to affirm itself is the process of the adoption of Electric Vehicles (EVs), thus switching from fuel-based to batterypowered propulsion technologies. Many social and economic barriers have proved to play a crucial role in this process, ranging from level of education, environmental awareness, age and census. This work aims at contributing to the study of this adoption process through a data-based lens, using real mobility patterns to setup a social-network analysis to model the spread of consensus among neighboring people that can enable the switch to EVs. In particular, we build the network topology using proximity measures that emerge from the analysis of real trips, and the initial disposition of the single agents towards the EV technology is inferred from their real mobility patterns. Based on this network, a cascade adoption model is simulated to investigate the dynamics of the adoption process, and an incentive scheme is designed to show how different policies can contribute to the opinion diffusion over time on the network.

Research paper thumbnail of Automatic detection of human's falls from heights for airbag deployment via inertial measurements

Automation in Construction, 2020

Workers in different industrial sectors, mainly in the construction and energy areas, face the da... more Workers in different industrial sectors, mainly in the construction and energy areas, face the daily risky situation of falling from the height accidentally, even wearing safety harnesses. To actively protect workers, a safety jacket is proposed. The jacket is equipped with an airbag cushion and an inertial measurement unit, located on the back, to sense the body motion hl. An algorithm deploys the airbag automatically for falls from heights greater than 1 m, leaving enough time for the airbag to be fully inflated. The proposed algorithm is tested and validated against experimental data collected during real falls performed by a professional stuntman, and during months of daily routine workers' life. Particular attention is devoted to the calibration of the tuning parameters, with the aim of the best trade-off between false positives' minimization, reactiveness, and robustness.

Research paper thumbnail of fierClass: A multi-signal, cepstrum-based, time series classifier

Engineering Applications of Artificial Intelligence, 2020

The task of learning behaviors of dynamical systems heavily involves time series analysis. Most o... more The task of learning behaviors of dynamical systems heavily involves time series analysis. Most often, to set up a classification problem, the analysis in time is seen as the main and most natural option. In general, working in the time domain entails a manual, time-consuming phase dealing with signal processing, features engineering and selection processes. Extracted features may also lead to a final result that is heavily dependent of subjective choices, making it hard to state whether the current solution is optimal under any perspective. In this work, leveraging a recent proposal to use the cepstrum as a frequency-based learning framework for time series analysis, we show how such an approach can handle classification with multiple input signals, combining them to yield very accurate results. Notably, the approach makes the whole design flow automatic, freeing it from the cumbersome and subjective step of handcrafting and selecting the most effective features. The method is validated on experimental data addressing the automatic classification of whether a car driver is using the smartphone while driving.

Research paper thumbnail of Automatic crash detection system for two-wheeled vehicles: design and experimental validation

IFAC-PapersOnLine, 2019

In the insurance telematics context, four-wheeled vehicles are being equipped with e-Boxes instal... more In the insurance telematics context, four-wheeled vehicles are being equipped with e-Boxes installed on the battery, allowing an online monitoring of the vehicle motion thanks to an inertial measurement unit and a GPS unit. The main service that the e-Box enables is the automatic reconstruction of the real crash dynamics, and the detection of potentially dangerous situations, with the subsequent automatic activation of rescue operations, both for driver and passengers and for the vehicle itself. How to design such system for two-wheeled vehicles is far from trivial, as the dynamics of two-wheelers is much different, and so are the ways in which accidents may occur. In this work, a novel crash detection algorithm for two-wheeled vehicles is presented, and its validity is proved against experimental data.

Research paper thumbnail of Switched adaptation strategies for integral sliding mode control: Theory and application

International Journal of Robust and Nonlinear Control, 2019

SummaryIntegral sliding mode (SM) control is an interesting approach, as it can maintain the good... more SummaryIntegral sliding mode (SM) control is an interesting approach, as it can maintain the good chattering alleviation property of higher‐order SMs while making the reaching phase less critical and keeping the controlled system trajectory on a suitably selected sliding manifold since the initial time instant. In order to make such a method more robust and to improve its flexibility by the adaptation of its parameters to the current system condition, in this paper, a switched strategy is proposed. Specifically, the suboptimal Second‐order SM algorithm is considered as a basis in its integral formulation, and the switching strategy is designed by partitioning the so‐called auxiliary system state space in a finite number of regions. The proposed method allows one to improve the transient performance by adapting the gains through these regions, thus implying an energy saving capability. The proposal is theoretically analyzed and, in order to test its performance, the control of the la...

Research paper thumbnail of Sliding mode control for LPV systems

2016 American Control Conference (ACC), 2016

LPV models are extremely appealing, as they allow describing the dynamics of many physical system... more LPV models are extremely appealing, as they allow describing the dynamics of many physical systems that are of interest in various engineering applications. For such systems, dedicated control approaches have been proposed, which rely on the measurement of the scheduling variables and exploit such information for improving the closed-loop performance with respect to fixed-structure, possibly robust, solutions. Unfortunately, such control techniques are often not so simple to tune and design, especially when also parametric uncertainties affect the system, thus requiring LPV-robust control techniques. In this work we explore the advantages offered by sliding mode (SM) algorithms for the control of LPV systems, showing that a fixed-structure SM approach can outperform genuine LPV solutions in the case of parametric uncertainties on the system model without additional tuning and design needs. A case study considering the control of lateral vehicle dynamics is used to investigate the performance of the different approaches, showing promising results for extending SM controllers to cope with additional uncertainties affecting LPV systems, that may be difficult to act upon with traditional methods.

Research paper thumbnail of Fostering the Mass Adoption of Electric Vehicles: A Network-Based Approach

IEEE Transactions on Control of Network Systems

Mobility will surely be at the core of the smart cities of the future. As such, it must be planne... more Mobility will surely be at the core of the smart cities of the future. As such, it must be planned based on novel mobility models, smart enough to answer the multifaceted needs of users, while being sustainable and energy efficient. In this evolution, electric vehicles (EVs) will be crucial, as confirmed by the fact that many governments are already actively sustaining their spread in place of common internal combustion engine (ICE) ones. Nonetheless, for their adoption to be actually widespread, one must be able to govern the mass adoption mechanisms, by designing policies that are cost-effective and successful in making the mobility transition a reality in due time. In this work, we propose a novel framework that can represent a valuable control-oriented tool to serve this ambitious goal. Our framework lays its foundation on a quantitative description of the inclination of traditional car owners toward EVs, which is retrieved by relying on data-driven insights on their mobility habits only. This information is further exploited to construct a proximity-based network, that is combined with the individual characterization into a cascade model describing the adoption dynamics. To show the potential of the introduced framework, we exploit it to assess the unforced spread of EVs starting from a set of known EV owners, and to test and quantitatively evaluate the cost and benefits of policies enacted to foster adoption.

Research paper thumbnail of Sistema e Metodo Per Il Rilevamento Dello Stato DI Fermo Diun Veicolo

Research paper thumbnail of A Data-Driven, Vehicle-Independent Usage Monitoring System for Shared Fleets: Assessing Vertical and Longitudinal Wear

IEEE Vehicular Technology Magazine

Research paper thumbnail of A Novel Crash Detection Algorithm for Two-Wheeled Vehicles

IEEE Transactions on Intelligent Vehicles, 2021

This paper presents a crash detection strategy for motorcycles, using GPS/GNSS and inertial measu... more This paper presents a crash detection strategy for motorcycles, using GPS/GNSS and inertial measurements collected by telematic e-Boxes. The primary goal is to jointly minimize the access time of the emergency services and to accurately store the event dynamics for further investigation on accident's responsibilities. For motorcycles, unlike for cars, crash events cannot always be detected by monitoring abnormal longitudinal decelerations solely. Thus, this work proposes a novel method that detects and classifies the severity of crash-like situations. The proposed approach follows a new paradigm that improves the detection performance, better generalizing the motorcycle dynamics with respect to the specific vehicle and the driving style. The proposed approach has been tested and validated with experimental data, covering both motorsport and naturalistic scenarions, involving several riders, different road conditions and vehicles.

Research paper thumbnail of Dross attachment estimation in the laser-cutting process via Convolutional Neural Networks (CNN)

2020 28th Mediterranean Conference on Control and Automation (MED), 2020

Laser cutting of metals offers the advantage of high precision and accuracy. Dross attachment, me... more Laser cutting of metals offers the advantage of high precision and accuracy. Dross attachment, measured as the length of the re-solidified material perpendicular to the surface, has definitely the highest impact on the overall process quality. Dross attachment is commonly judged by skilled technicians that evaluate the cut quality. Process parameters are optimized to maximize the cutting speed while keeping an acceptable level of dross attachment. However, in practice, increased levels of dross may occur due to different processing conditions. In this framework, a real-time dross attachment monitoring system is desired. Within the stream of vision based monitoring systems, in this work we use high frequency images generated by a precision camera, mounted on the laser head, to capture the cutting process light emission. A CNN-based classification system is developed, where captured images are fed into the trained network with the aim of automatically recognize if a predetermined dros...

Research paper thumbnail of Vehicle Vertical Wearing Index (V2 WI): active monitoring of wearing and aging of vertical-dynamics components in four-wheeled vehicles

2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), 2020

Being able to assess the state-of-health of a vehicle opens of course many possible applications.... more Being able to assess the state-of-health of a vehicle opens of course many possible applications. All the more so if the ongoing degradation of the monitored components can be provided continuously as the vehicle life extends over time. In modern shared mobility systems, thanks to which migration from ownership to usership models should eventually take place, developing means to actively monitor the state of the vehicle fleet is crucial to improve business models and feasible and predictive maintenance plans. Within this challenging context, the present paper focuses on the monitoring of the vehicle vertical dynamics, to understand, from the analysis of measured data, which is the combined effect of driving-style and introduce road pavement roughness in determining the usage profile of the vertical-dynamics-related components of the vehicle, mostly the suspensions system. The proposed cost function concisely represents such wearing process, with the advantage of not requiring detail...

Research paper thumbnail of Leveraging walking inertial pattern for terrain classification

2020 International Conferences on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics), 2020

The goal of this work is to illustrate how measurements collected during walking by inertial sens... more The goal of this work is to illustrate how measurements collected during walking by inertial sensors embedded in the shoes' sole can be used to reveal the underlying terrain type. The final aim is to enable the automatic, real time adaptation of the actuated bottom cushioning of the innovative Wahu shoe for the sake of safety and comfort. For this purpose, the gait patterns of the normal walk of different healthy subjects on four different surface types, with different hardness and friction, are collected offline and represented through the three accelerations' time history. These signals are pre-processed and segmented into two different “elementary” items, a “walk” object, made of a sequence of subsequent steps, and a “mean step” object. In both cases, time and frequency attributes are computed and the most explicative selected through a principal component analysis. A cubic SVM classifier is then trained with the experimental data from multiple walking trials and its perf...

Research paper thumbnail of Learning the min-max gait comfort region when wearing shoes

2020 International Conferences on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics), 2020

Shoe-embedded sensors are a recent, common and convenient choice for devices intended for locomot... more Shoe-embedded sensors are a recent, common and convenient choice for devices intended for locomotion-related applications. They are advantageous, compared to other wearable devices, since they allow performing gait assessment in real-world environments, recognizing the user walking pattern in real-time and directly on the feet level. However, shoe with embedded sensors, while providing affore-mentioned advantages, must in no way disturb the walk. In this paper, we present a simple, reliable and cheap method to check whether, and in which manner, the shoe affects the gait. The ultimate goal of the developed methodology is to provide a way to assess the performance of an innovative sole adaptable to changes in the external environment and in the dynamic state of the user. The proposed method is based on using a 2D camera to monitor three geometrical angles (knee, ankle, shoe) which reflect, in a simple but exhaustive manner, the lower limb behavior during the gait cycle. The ability o...

Research paper thumbnail of Control-oriented modelling of proof-of-work blockchains

2019 18th European Control Conference (ECC), 2019

Blockchain (BC) technology is a rather new conception of a mixed hardware and software platform t... more Blockchain (BC) technology is a rather new conception of a mixed hardware and software platform to achieve distributed consensus among peers. Its diffusion is related to cryptocurrency, the most widespread of which is Bitcoin. The protocol on which BCs operate sees the interaction between users, interested in performing their transactions, and miners, who certify the trust behind the transactions by putting some form of effort that allows acknowledging their trustfulness, obtaining Bitcoins in reward for their work. In the so-called proof-of-work implementation of the BC, such effort is the computational power needed to find a specific string of bits called nonce. The resulting game-theoretic setting has subtle dynamics, and its functioning could be strongly improved using closed-loop control. This work is an attempt to define a control-oriented description of the agent-based BC dynamics and offer a redesign of the difficulty control system that regulates the amount of work needed t...

Research paper thumbnail of Mining the electrification potential of fuel-based vehicles mobility patterns: a data-based approach

2020 IEEE International Conference on Human-Machine Systems (ICHMS), 2020

Electric Vehicles (EVs) are quickly becoming a very important segment of the automotive industry.... more Electric Vehicles (EVs) are quickly becoming a very important segment of the automotive industry. However, the so-called range anxiety, i.e., the fear that a vehicle has insufficient range to reach its destination, the experience anxiety, i.e.,the fear of the hassle of public charging and the high selling price are still major barriers to a widespread adoption of electric cars. In this paper, we use real-world data from vehicle telematics devices to quantitatively assess whether range anxiety is a justified threat. Specifically, we evaluate the vehicles electrification potential based on their real driving patterns, showing that a significant percentage of traditional Internal Combustion Engine (ICE) Vehicles could be effortlessly replaced by EVs, without any impact on the owners’ driving habits and with the current public charging infrastructure, only ensuring an overnight recharging.

Research paper thumbnail of Sliding mode control for LPV systems

LPV models are extremely appealing, as they allow describing the dynamics of many physical system... more LPV models are extremely appealing, as they allow describing the dynamics of many physical systems that are of interest in various engineering applications. For such systems, dedicated control approaches have been proposed, which rely on the measurement of the scheduling variables and exploit such information for improving the closed-loop performance with respect to fixed-structure, possibly robust, solutions. Unfortunately, such control techniques are often not so simple to tune and design, especially when also parametric uncertainties affect the system, thus requiring LPV-robust control techniques. In this work we explore the advantages offered by sliding mode (SM) algorithms for the control of LPV systems, showing that a fixed-structure SM approach can outperform genuine LPV solutions in the case of parametric uncertainties on the system model without additional tuning and design needs. A case study considering the control of lateral vehicle dynamics is used to investigate the performance of the different approaches, showing promising results for extending SM controllers to cope with additional uncertainties affecting LPV systems, that may be difficult to act upon with traditional methods.

Research paper thumbnail of MIRACLE: MInd ReAding CLassification Engine

IEEE Transactions on Neural Systems and Rehabilitation Engineering

Brain-computer interfaces (BCIs) have revolutionized the way humans interact with machines, parti... more Brain-computer interfaces (BCIs) have revolutionized the way humans interact with machines, particularly for patients with severe motor impairments. EEG-based BCIs have limited functionality due to the restricted pool of stimuli that they can distinguish, while those elaborating event-related potentials up to now employ paradigms that require the patient's perception of the eliciting stimulus. In this work, we propose MIRACLE: a novel BCI system that combines functional data analysis and machine-learning techniques to decode patients' minds from the elicited potentials. MIRACLE relies on a hierarchical ensemble classifier recognizing 10 different semantic categories of imagined stimuli. We validated MIRACLE on an extensive dataset collected from 20 volunteers, with both imagined and perceived stimuli, to compare the system performance on the two. Furthermore, we quantify the importance of each EEG channel in the decision-making process of the classifier, which can help reduce the number of electrodes required for data acquisition, enhancing patients' comfort.

Research paper thumbnail of Real Time Passenger Mass Estimation for e-scooters

2023 American Control Conference (ACC)

Research paper thumbnail of Driving electric vehicles’ mass adoption: An architecture for the design of human-centric policies to meet climate and societal goals

Transportation Research Part A: Policy and Practice

Research paper thumbnail of Social network analysis of electric vehicles adoption: a data-based approach

2020 IEEE International Conference on Human-Machine Systems (ICHMS), 2020

Mobility is undergoing dramatic transformations. Especially in the context of urban areas, severa... more Mobility is undergoing dramatic transformations. Especially in the context of urban areas, several significant changes are underway, driven by both new mobility needs and environmental concerns. The most mature one, which still is struggling to affirm itself is the process of the adoption of Electric Vehicles (EVs), thus switching from fuel-based to batterypowered propulsion technologies. Many social and economic barriers have proved to play a crucial role in this process, ranging from level of education, environmental awareness, age and census. This work aims at contributing to the study of this adoption process through a data-based lens, using real mobility patterns to setup a social-network analysis to model the spread of consensus among neighboring people that can enable the switch to EVs. In particular, we build the network topology using proximity measures that emerge from the analysis of real trips, and the initial disposition of the single agents towards the EV technology is inferred from their real mobility patterns. Based on this network, a cascade adoption model is simulated to investigate the dynamics of the adoption process, and an incentive scheme is designed to show how different policies can contribute to the opinion diffusion over time on the network.

Research paper thumbnail of Automatic detection of human's falls from heights for airbag deployment via inertial measurements

Automation in Construction, 2020

Workers in different industrial sectors, mainly in the construction and energy areas, face the da... more Workers in different industrial sectors, mainly in the construction and energy areas, face the daily risky situation of falling from the height accidentally, even wearing safety harnesses. To actively protect workers, a safety jacket is proposed. The jacket is equipped with an airbag cushion and an inertial measurement unit, located on the back, to sense the body motion hl. An algorithm deploys the airbag automatically for falls from heights greater than 1 m, leaving enough time for the airbag to be fully inflated. The proposed algorithm is tested and validated against experimental data collected during real falls performed by a professional stuntman, and during months of daily routine workers' life. Particular attention is devoted to the calibration of the tuning parameters, with the aim of the best trade-off between false positives' minimization, reactiveness, and robustness.

Research paper thumbnail of fierClass: A multi-signal, cepstrum-based, time series classifier

Engineering Applications of Artificial Intelligence, 2020

The task of learning behaviors of dynamical systems heavily involves time series analysis. Most o... more The task of learning behaviors of dynamical systems heavily involves time series analysis. Most often, to set up a classification problem, the analysis in time is seen as the main and most natural option. In general, working in the time domain entails a manual, time-consuming phase dealing with signal processing, features engineering and selection processes. Extracted features may also lead to a final result that is heavily dependent of subjective choices, making it hard to state whether the current solution is optimal under any perspective. In this work, leveraging a recent proposal to use the cepstrum as a frequency-based learning framework for time series analysis, we show how such an approach can handle classification with multiple input signals, combining them to yield very accurate results. Notably, the approach makes the whole design flow automatic, freeing it from the cumbersome and subjective step of handcrafting and selecting the most effective features. The method is validated on experimental data addressing the automatic classification of whether a car driver is using the smartphone while driving.

Research paper thumbnail of Automatic crash detection system for two-wheeled vehicles: design and experimental validation

IFAC-PapersOnLine, 2019

In the insurance telematics context, four-wheeled vehicles are being equipped with e-Boxes instal... more In the insurance telematics context, four-wheeled vehicles are being equipped with e-Boxes installed on the battery, allowing an online monitoring of the vehicle motion thanks to an inertial measurement unit and a GPS unit. The main service that the e-Box enables is the automatic reconstruction of the real crash dynamics, and the detection of potentially dangerous situations, with the subsequent automatic activation of rescue operations, both for driver and passengers and for the vehicle itself. How to design such system for two-wheeled vehicles is far from trivial, as the dynamics of two-wheelers is much different, and so are the ways in which accidents may occur. In this work, a novel crash detection algorithm for two-wheeled vehicles is presented, and its validity is proved against experimental data.

Research paper thumbnail of Switched adaptation strategies for integral sliding mode control: Theory and application

International Journal of Robust and Nonlinear Control, 2019

SummaryIntegral sliding mode (SM) control is an interesting approach, as it can maintain the good... more SummaryIntegral sliding mode (SM) control is an interesting approach, as it can maintain the good chattering alleviation property of higher‐order SMs while making the reaching phase less critical and keeping the controlled system trajectory on a suitably selected sliding manifold since the initial time instant. In order to make such a method more robust and to improve its flexibility by the adaptation of its parameters to the current system condition, in this paper, a switched strategy is proposed. Specifically, the suboptimal Second‐order SM algorithm is considered as a basis in its integral formulation, and the switching strategy is designed by partitioning the so‐called auxiliary system state space in a finite number of regions. The proposed method allows one to improve the transient performance by adapting the gains through these regions, thus implying an energy saving capability. The proposal is theoretically analyzed and, in order to test its performance, the control of the la...

Research paper thumbnail of Sliding mode control for LPV systems

2016 American Control Conference (ACC), 2016

LPV models are extremely appealing, as they allow describing the dynamics of many physical system... more LPV models are extremely appealing, as they allow describing the dynamics of many physical systems that are of interest in various engineering applications. For such systems, dedicated control approaches have been proposed, which rely on the measurement of the scheduling variables and exploit such information for improving the closed-loop performance with respect to fixed-structure, possibly robust, solutions. Unfortunately, such control techniques are often not so simple to tune and design, especially when also parametric uncertainties affect the system, thus requiring LPV-robust control techniques. In this work we explore the advantages offered by sliding mode (SM) algorithms for the control of LPV systems, showing that a fixed-structure SM approach can outperform genuine LPV solutions in the case of parametric uncertainties on the system model without additional tuning and design needs. A case study considering the control of lateral vehicle dynamics is used to investigate the performance of the different approaches, showing promising results for extending SM controllers to cope with additional uncertainties affecting LPV systems, that may be difficult to act upon with traditional methods.

Research paper thumbnail of Fostering the Mass Adoption of Electric Vehicles: A Network-Based Approach

IEEE Transactions on Control of Network Systems

Mobility will surely be at the core of the smart cities of the future. As such, it must be planne... more Mobility will surely be at the core of the smart cities of the future. As such, it must be planned based on novel mobility models, smart enough to answer the multifaceted needs of users, while being sustainable and energy efficient. In this evolution, electric vehicles (EVs) will be crucial, as confirmed by the fact that many governments are already actively sustaining their spread in place of common internal combustion engine (ICE) ones. Nonetheless, for their adoption to be actually widespread, one must be able to govern the mass adoption mechanisms, by designing policies that are cost-effective and successful in making the mobility transition a reality in due time. In this work, we propose a novel framework that can represent a valuable control-oriented tool to serve this ambitious goal. Our framework lays its foundation on a quantitative description of the inclination of traditional car owners toward EVs, which is retrieved by relying on data-driven insights on their mobility habits only. This information is further exploited to construct a proximity-based network, that is combined with the individual characterization into a cascade model describing the adoption dynamics. To show the potential of the introduced framework, we exploit it to assess the unforced spread of EVs starting from a set of known EV owners, and to test and quantitatively evaluate the cost and benefits of policies enacted to foster adoption.

Research paper thumbnail of Sistema e Metodo Per Il Rilevamento Dello Stato DI Fermo Diun Veicolo

Research paper thumbnail of A Data-Driven, Vehicle-Independent Usage Monitoring System for Shared Fleets: Assessing Vertical and Longitudinal Wear

IEEE Vehicular Technology Magazine

Research paper thumbnail of A Novel Crash Detection Algorithm for Two-Wheeled Vehicles

IEEE Transactions on Intelligent Vehicles, 2021

This paper presents a crash detection strategy for motorcycles, using GPS/GNSS and inertial measu... more This paper presents a crash detection strategy for motorcycles, using GPS/GNSS and inertial measurements collected by telematic e-Boxes. The primary goal is to jointly minimize the access time of the emergency services and to accurately store the event dynamics for further investigation on accident's responsibilities. For motorcycles, unlike for cars, crash events cannot always be detected by monitoring abnormal longitudinal decelerations solely. Thus, this work proposes a novel method that detects and classifies the severity of crash-like situations. The proposed approach follows a new paradigm that improves the detection performance, better generalizing the motorcycle dynamics with respect to the specific vehicle and the driving style. The proposed approach has been tested and validated with experimental data, covering both motorsport and naturalistic scenarions, involving several riders, different road conditions and vehicles.

Research paper thumbnail of Dross attachment estimation in the laser-cutting process via Convolutional Neural Networks (CNN)

2020 28th Mediterranean Conference on Control and Automation (MED), 2020

Laser cutting of metals offers the advantage of high precision and accuracy. Dross attachment, me... more Laser cutting of metals offers the advantage of high precision and accuracy. Dross attachment, measured as the length of the re-solidified material perpendicular to the surface, has definitely the highest impact on the overall process quality. Dross attachment is commonly judged by skilled technicians that evaluate the cut quality. Process parameters are optimized to maximize the cutting speed while keeping an acceptable level of dross attachment. However, in practice, increased levels of dross may occur due to different processing conditions. In this framework, a real-time dross attachment monitoring system is desired. Within the stream of vision based monitoring systems, in this work we use high frequency images generated by a precision camera, mounted on the laser head, to capture the cutting process light emission. A CNN-based classification system is developed, where captured images are fed into the trained network with the aim of automatically recognize if a predetermined dros...

Research paper thumbnail of Vehicle Vertical Wearing Index (V2 WI): active monitoring of wearing and aging of vertical-dynamics components in four-wheeled vehicles

2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), 2020

Being able to assess the state-of-health of a vehicle opens of course many possible applications.... more Being able to assess the state-of-health of a vehicle opens of course many possible applications. All the more so if the ongoing degradation of the monitored components can be provided continuously as the vehicle life extends over time. In modern shared mobility systems, thanks to which migration from ownership to usership models should eventually take place, developing means to actively monitor the state of the vehicle fleet is crucial to improve business models and feasible and predictive maintenance plans. Within this challenging context, the present paper focuses on the monitoring of the vehicle vertical dynamics, to understand, from the analysis of measured data, which is the combined effect of driving-style and introduce road pavement roughness in determining the usage profile of the vertical-dynamics-related components of the vehicle, mostly the suspensions system. The proposed cost function concisely represents such wearing process, with the advantage of not requiring detail...

Research paper thumbnail of Leveraging walking inertial pattern for terrain classification

2020 International Conferences on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics), 2020

The goal of this work is to illustrate how measurements collected during walking by inertial sens... more The goal of this work is to illustrate how measurements collected during walking by inertial sensors embedded in the shoes' sole can be used to reveal the underlying terrain type. The final aim is to enable the automatic, real time adaptation of the actuated bottom cushioning of the innovative Wahu shoe for the sake of safety and comfort. For this purpose, the gait patterns of the normal walk of different healthy subjects on four different surface types, with different hardness and friction, are collected offline and represented through the three accelerations' time history. These signals are pre-processed and segmented into two different “elementary” items, a “walk” object, made of a sequence of subsequent steps, and a “mean step” object. In both cases, time and frequency attributes are computed and the most explicative selected through a principal component analysis. A cubic SVM classifier is then trained with the experimental data from multiple walking trials and its perf...

Research paper thumbnail of Learning the min-max gait comfort region when wearing shoes

2020 International Conferences on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics), 2020

Shoe-embedded sensors are a recent, common and convenient choice for devices intended for locomot... more Shoe-embedded sensors are a recent, common and convenient choice for devices intended for locomotion-related applications. They are advantageous, compared to other wearable devices, since they allow performing gait assessment in real-world environments, recognizing the user walking pattern in real-time and directly on the feet level. However, shoe with embedded sensors, while providing affore-mentioned advantages, must in no way disturb the walk. In this paper, we present a simple, reliable and cheap method to check whether, and in which manner, the shoe affects the gait. The ultimate goal of the developed methodology is to provide a way to assess the performance of an innovative sole adaptable to changes in the external environment and in the dynamic state of the user. The proposed method is based on using a 2D camera to monitor three geometrical angles (knee, ankle, shoe) which reflect, in a simple but exhaustive manner, the lower limb behavior during the gait cycle. The ability o...

Research paper thumbnail of Control-oriented modelling of proof-of-work blockchains

2019 18th European Control Conference (ECC), 2019

Blockchain (BC) technology is a rather new conception of a mixed hardware and software platform t... more Blockchain (BC) technology is a rather new conception of a mixed hardware and software platform to achieve distributed consensus among peers. Its diffusion is related to cryptocurrency, the most widespread of which is Bitcoin. The protocol on which BCs operate sees the interaction between users, interested in performing their transactions, and miners, who certify the trust behind the transactions by putting some form of effort that allows acknowledging their trustfulness, obtaining Bitcoins in reward for their work. In the so-called proof-of-work implementation of the BC, such effort is the computational power needed to find a specific string of bits called nonce. The resulting game-theoretic setting has subtle dynamics, and its functioning could be strongly improved using closed-loop control. This work is an attempt to define a control-oriented description of the agent-based BC dynamics and offer a redesign of the difficulty control system that regulates the amount of work needed t...

Research paper thumbnail of Mining the electrification potential of fuel-based vehicles mobility patterns: a data-based approach

2020 IEEE International Conference on Human-Machine Systems (ICHMS), 2020

Electric Vehicles (EVs) are quickly becoming a very important segment of the automotive industry.... more Electric Vehicles (EVs) are quickly becoming a very important segment of the automotive industry. However, the so-called range anxiety, i.e., the fear that a vehicle has insufficient range to reach its destination, the experience anxiety, i.e.,the fear of the hassle of public charging and the high selling price are still major barriers to a widespread adoption of electric cars. In this paper, we use real-world data from vehicle telematics devices to quantitatively assess whether range anxiety is a justified threat. Specifically, we evaluate the vehicles electrification potential based on their real driving patterns, showing that a significant percentage of traditional Internal Combustion Engine (ICE) Vehicles could be effortlessly replaced by EVs, without any impact on the owners’ driving habits and with the current public charging infrastructure, only ensuring an overnight recharging.