Although the Automatic Train Operation (ATO) is consolidated in urban railways, its use on mainlines is still unexplored. Currently, the first prototypes of train with ATO capable of running on mainlines equipped with specific control systems (e.g., ETCS/ERTMS in Europe) have been realized. However, they require the active presence of staff on board. Recent research in innovative solutions for railway efficiency has opened to the possibility of extending the ATO concept to the Unattended Train Operation (UTO), i.e., the full automation of infrastructures and vehicles. In this context, a project based on synergistic collaboration between academia and the national railway industry has led to the definition of a new Vital Control module (VC). VC includes a PCB, managed by a reliable and safe hard Real-Time Operating System (RTOS). The hardware consists of a Eurocard-sized PCB that houses an Ultrazed-EG System on Module as computing core and embeds several communication interfaces to favor the inclusion in existing apparatus. The VC RTOS runs an application logic that acts as a real-time control core for the assessment of the on-cabin equipment operativity. VC is also responsible for detecting UTO-related hazardous situations by intervening with emergency braking. Both VC hardware and software are developed to be compliant with related safety standards. The proposed VC has been included in an automatic testbed to recreate real-time hazardous scenarios. In this context, VC system has proven to be able to mitigate these scenarios ~2 times faster than current ATO protection system.

In this live demonstration the RIDDANCE (distuRb-resIstant Dry electroDe-based brAiN Computer intErface) framework is presented. It is a Brain-Computer Interface (BCI) framework that characterizes and counteracts several factors that make difficult applying BCIs to real life contexts. RIDDANCE exploits data from an 8-channel dry EEG headset by g. Tec, Data collection for training/testing is typically carried out in not controlled environment (often disturbed) to improve the training and the classification robustness. For the purpose RIDDANCE embeds a user-tailored neural network (NN) topology selector that find the most robust model in terms of average validation loss. RIDDANCE is optimized for P300-based tasks and tested in a prototype car driving application.

Abstract Recent advances in technology and railway have led to the introduction of systems and infrastructures capable of driving trains automatically. The Automatic Train Operation (ATO) system has been optimized for active human supervision. The next challenge is to realize ATO systems capable of achieving unsupervised operations on the mainlines. However, at this aim, additional safety functionalities should be provided. In this paper, we propose a pioneer hardware/software Vital Control Module (VCM) architecture capable of expanding the control capabilities of the existing train control system. The VCM includes a Printed Circuit Board (PCB), to be integrated into the cabin equipment, managed by a reliable and safe hard Real-Time Operating System (RTOS). Both hardware and software are developed to be compliant with related safety standards. The VCM integrates an application logic that acts as an on-board equipment control core, assessing the overall operativity in real-time, and promptly issuing emergency brakes if hazardous situations occur. The application logic has been developed with a model-based approach via Simulink/Stateflow tool and implemented as a C-script on the Xilinx Ultrascale + core housed on the PCB. We have used two testbeds to evaluate the VCM performance. Experimental results showed that the Worst-Case Response Time (WCRT) by the application logic is 13.6 times smaller than the most limiting specification-related deadline. The achieved earliness (− 1.8 ms out of 2 ms of deadline) allows for the easy expansion of VCM’s train protection capabilities in the future. Results from the second testbed showed that the VCM can intervene to mitigate hazardous situations ~ 2 times faster than the current automatic train protection systems according to the related standard.

In this paper, we present a novel framework to realize an automatic “accuracy versus complexity” characterization for embeddable emotion recognition systems in healthcare applications. This framework is based on a series of grid searches able to identify highly descriptive features from the input signals, while taking into account implementation ease, memory usage, and classification performance. This paper is articulated on a proof of concept, in which the proposed framework is used to extract an emotion recognition architecture able to discriminate up to 8 emotions, by employing the users' cortical activity and a 3D model for the emotion characterization. The implemented series of grid searches lead to a final low-memory, low-resources and low-complexity emotions recognition processing chain suitable for embedded platforms. The processing chain extracted by the proposed framework has been implemented as a real-time task on a personal care robot processing core. The extracted emotion recognition system tested on cortical signals from a publicly available dataset, showed an accuracy of ~75 % (average) in discriminating 8 emotions and a memory reduction of 70% from a canonical implementation of the same feature extraction step.

In this paper, we propose an innovative architecture that merges the Personal Care Robots (PCRs) advantages with a novel Brain Computer Interface (BCI) to carry out assistive tasks, aiming to reduce the burdens of caregivers. The BCI is based on movement related potentials (MRPs) and exploits EEG from 8 smart wireless electrodes placed on the sensorimotor area. The collected data are firstly pre-processed and then sent to a novel Feature Extraction (FE) step. The FE stage is based on symbolization algorithm, the Local Binary Patterning, which adopts end-to-end binary operations. It strongly reduces the stage complexity, speeding the BCI up. The final user intentions discrimination is entrusted to a linear Support Vector Machine (SVM). The BCI performances have been evaluated on four healthy young subjects. Experimental results showed a user intention recognition accuracy of ~84 % with a timing of ~554 ms per decision. A proof of concept is presented, showing how the BCI-based binary decisions could be used to drive the PCR up to a requested object, expressing the will to keep it (delivering it to user) or to continue the research.

This paper describes the design, implementation and in vivo test of a novel Brain Computer Interface (BCI) for the mechatronic devices control. The method exploits electroencephalogram acquisitions (EEG), and specifically the Movement Related Potentials (MRPs) (i.e., μ and β rhythms), to actuate the user intention on the mechatronic device. The EEG data are collected by only five wireless smart electrodes positioned on the central and parietal cortex area. The acquired data are analyzed by an innovative single-trial classification algorithm that, with respect to the current state of the art, strongly reduces the training time (Minimum: ~1 h, reached: 10 min), as well as the acquisition time - after stimulus - for a reliable classification (Typical: 4-8 s reached: 2 s). As first step, the algorithm performs an EEG time-frequency analysis in the selected bands, making the data suitable for further computations. The implemented machine learning (ML) stage consists of: (i) dimensionality reduction; (ii) statistical inference-based features extraction (FE); (iii) classification model selection. It is also proposed a dedicated algorithm, the MLE-RIDE, for the dimensionality reduction that, jointly with statistical analyses, digitalize the μ and β rhythms, performing the features extraction. Finally, the best support vector machine (SVM) model is selected and used in the on-line classification. As proof of concept, two mechatronic devices have been brain-controlled by using the proposed BCI algorithm: a three-finger robotic hand and an acrylic prototype car. The experimental results, obtained with data from 3 subjects (aged 26±1), showed an accuracy on human will wireless detection of 87.4%, in the real-time binary discrimination, with 33.7ms of computation times.

This study presents a P300‐based brain‐computer interface (BCI) for mechatronic device driving, i.e. without the need for any physical control. The technique is based on a machine learning (ML) algorithm, which exploits a spatio‐temporal characterization of the P300, analyses all the discrimination scenarios through a multiclass classification problem. The BCI is composed of the acquisition unit, the processing unit and the navigation unit. The acquisition unit is a wireless 32‐channel electroencephalography headset collecting data from six electrodes. The processing unit is a dedicated µPC performing stimuli delivery, ML and classification, leading to the user intention interpretation. The ML stage is based on a custom algorithm (tuned residue iteration decomposition) which trains the classifier on the user‐tuned P300 features. The extracted features undergo a dimensionality reduction and are used to define decision boundaries for the real‐time classification. The real‐time classification performs a functional approach for the features extraction, reducing the amount of data to be analyzed. The Raspberry‐based navigation unit actuates the received commands, supporting the wheelchair motion. The experimental results, based on a dataset of seven subjects, demonstrate that the classification chain is performed in 8.16 ms with an accuracy of 84.28 ± 0.87%, allowing the real‐time control of the wheelchair.

A new mobile healthcare system for neuro-cognitive function monitoring and treatment is presented. The architecture of the system features sensors to measure the brain potential, localized data analysis and filtering, and in-cloud distribution to specialized medical personnel. As such, it presents tradeoffs typical of other cyber-physical systems, where hardware, algorithms, and software implementations have to come together in a coherent fashion. The system is based on spatio-temporal detection and characterization of a specific brain potential called P300. The diagnosis of cognitive deficit is achieved by analyzing the data collected by the system with a new algorithm called tuned-Residue Iteration Decomposition (t-RIDE). The system has been tested on 17 subjects ( n = 12 healthy, n = 3 mildly cognitive impaired, and n = 2 with Alzheimer's disease involved in three different cognitive tasks with increasing difficulty. The system allows fast diagnosis of cognitive deficit, including mild and heavy cognitive impairment: t-RIDE convergence is achieved in 79 iterations (i.e., 1.95s), yielding an 80% accuracy in P300 amplitude evaluation with only 13 trials on a single EEG channel.

In this paper we present a P300-hased Brain Computer Interface (BCI) for the remote control of a mechatronic actuator, such as wheelchair, or even a car, driven by EEG signals to be used hy tetraplegic and paralytic users or just for safe drive in case of car. The P300 signal, an Evoked Related Potential (ERP) devoted to the cognitive brain activity, is induced for purpose by visual stimulation. The EEG data are collected by 6 smart wireless electrodes from the parietal-cortex area and online classified by a linear threshold classifier, basing on a suitable stage of Machine Learning (ML). The ML is implemented on a μPC dedicated to the system and where the data acquisition and processing is performed. The main improvement in remote driving car by EEG, regards the approach used for the intentions recognition. In this work, the classification is based on the P300 and not just on the average of more not well identify potentials. This approach reduces the number of electrodes on the EEG helmet. The ML stage is based on a custom algorithm (t-RIDE) which tunes the following classification stage on the user's “cognitive chronometry”. The ML algorithm starts with a fast calibration phase (just ~190s for the first learning). Furthermore, the BCI presents a functional approach for time-domain features extraction, which reduces the amount of data to be analyzed, and then the system response times. In this paper, a proof of concept of the proposed BCI is shown using a prototype car, tested on 5 subjects (aged 26 ± 3). The experimental results show that the novel ML approach allows a complete P300 spatio-temporal characterization in 1.95s using 38 target brain visual stimuli (for each direction of the car path). In free-drive mode, the BCI classification reaches 80.5 ± 4.1% on single-trial detection accuracy while the worst-case computational time is 19.65ms ± 10.1. The BCI system here described can be also used on different mechatronic actuators, such as robots.