1,721,036 research outputs found
Guest editorial: recent advances in reliable control and cost-effective engineering design for autonomous systems
No full textBrain-computer interface for robot control with eye artifacts for assistive applications
Full text linkHuman-robot interaction is a rapidly developing field and robots have been taking more active roles in our daily lives. Patient care is one of the fields in which robots are becoming more present, especially for people with disabilities. People with neurodegenerative disorders might not consciously or voluntarily produce movements other than those involving the eyes or eyelids. In this context, Brain-Computer Interface (BCI) systems present an alternative way to communicate or interact with the external world. In order to improve the lives of people with disabilities, this paper presents a novel BCI to control an assistive robot with user's eye artifacts. In this study, eye artifacts that contaminate the electroencephalogram (EEG) signals are considered a valuable source of information thanks to their high signal-to-noise ratio and intentional generation. The proposed methodology detects eye artifacts from EEG signals through characteristic shapes that occur during the events. The lateral movements are distinguished by their ordered peak and valley formation and the opposite phase of the signals measured at F7 and F8 channels. This work, as far as the authors' knowledge, is the first method that used this behavior to detect lateral eye movements. For the blinks detection, a double-thresholding method is proposed by the authors to catch both weak blinks as well as regular ones, differentiating itself from the other algorithms in the literature that normally use only one threshold. Real-time detected events with their virtual time stamps are fed into a second algorithm, to further distinguish between double and quadruple blinks from single blinks occurrence frequency. After testing the algorithm offline and in realtime, the algorithm is implemented on the device. The created BCI was used to control an assistive robot through a graphical user interface. The validation experiments including 5 participants prove that the developed BCI is able to control the robot
Vision-based robotic disassembly of aircraft engines with YOLO-SAM: a novel method for task orientation estimation
No full textThe growing demand for sustainable end-of-life management in aerospace has increased the need for robotic disassembly. This paper presents a novel pipeline for aircraft engine disassembly, operating in automatic and semi-automatic modes with state-of-the-art vision-based techniques. The key contributions are: (1) a method combining the Segment Anything Model (SAM) with YOLO for detecting removable bolts, independent of engine model and adaptable to various worn bolt types using vision-only perception; and (2) a SAM-based approach for estimating task orientation, ensuring precise tool alignment. Validated in simulations and real-world tests, the pipeline demonstrates high accuracy and adaptability for solutions in aerospace manufacturing
FLARE: Fine-tuned large LAnguage models for Resource-Efficient action generation in robotics
Full text linkDespite recent progress in robotic manipulation, robots still face difficulties generating actions across new tasks, objects, and environments. While foundation models such as Large Language Models (LLMs) show potential in robotic learning, they have several limitations with complex manipulation tasks. In addition, LLMs often depend on pre-trained actions or require reinforcement learning, and end-to-end robotic models demand vast amounts of data and computational power. Furthermore, building extensive multimodal datasets for real-world robotic applications is time-consuming, and training large foundation models is resource-intensive. This paper presents a framework that overcomes these challenges by employing an LLM model fine-tuned with a Parameter-Efficient Fine-Tuning (PEFT) technique to tailor them for robotic tasks. During the fine-tuning, our approach does not need real-world data because it is generated synthetically, without relying on images or multimodal inputs. This allows LLMs to directly produce generalized action plans in real-world settings, enabling the robot to perform seven tasks - including pick-and-place, stacking, lifting, and directional movements - after just a few hours of training on simulated data. By integrating a YOLO-based vision module for perception, our modular architecture achieves task success rates comparable to state-of-the-art robotic learning models on specific tasks. The primary advantages of our method are that it is trained entirely on synthetic data, provides exceptionally fast inference, and operates efficiently on a single commercial GPU for both training and inference. These features make this framework highly practical and accessible for industry use, offering a cost-effective solution in terms of time and resources
Experimental Validation of an Actor-Critic Model Predictive Force Controller for Robot-Environment Interaction Tasks
No full textImproved impedance/admittance switching controller for the interaction with a variable stiffness environment
Full text linkHybrid impedance/admittance control aims to provide an adaptive behavior to the manipulator in order to interact with the surrounding environment. In fact, impedance control is suitable for stiff environments, while admittance control is suitable for soft environments/free motion. Hybrid impedance/admittance control, indeed, allows modulating the control actions to exploit the combination of such behaviors. While some work has addressed the proposed topic, there are still some open issues to be solved. In particular, the proposed contribution aims: (i) to satisfy the continuity of the interaction force in the switching from impedance to admittance control when a feedforward velocity term is present; and (ii) to adapt the switching parameters to improve the performance of the hybrid control framework to better exploit the properties of both impedance and admittance controllers. The proposed approach was compared in simulation with the standard hybrid impedance/admittance control in order to show the improved performance. A Franka EMIKA panda robot was used as a reference robotic platform to provide a realistic simulation
Impedance Shaping Controller for Robotic Applications in Interaction with Compliant Environments
No full textThe impedance shaping control is presented in this paper, providing an extension of standard impedance controller. The method has been conceived to avoid force overshoots in applications where there is the need to track a force reference. Force tracking performance are obtained tuning on-line both the position setpoint and the stiffness and damping parameters, based on the force error and on the estimated stiffness of the interacting environment (an Extended Kalman Filter is used). The stability of the presented strategy has been studied through Lyapunov. To validate the performance of the control an assembly task is taken into account, considering the geometrical and mechanical properties of the environment (partially) unknown. Results are compared with constant stiffness and damping impedance controllers, which show force overshoots and instabilities
A framework for human–robot collaboration enhanced by preference learning and ergonomics
Full text linkIndustry 5.0 aims to prioritize human operators, focusing on their well-being and capabilities, while promoting collaboration between humans and robots to enhance efficiency and productivity. The integration of collaborative robots must ensure the health and well-being of human operators. Indeed, this paper addresses the need for a human -centered framework proposing a preference -based optimization algorithm in a human- robot collaboration (HRC) scenario with an ergonomics assessment to improve working conditions. The HRC application consists of optimizing a collaborative robot end -effector pose during an object -handling task. The following approach (AmPL-RULA) utilizes an Active multi -Preference Learning (AmPL) algorithm, a preferencebased optimization method, where the user is requested to iteratively provide qualitative feedback by expressing pairwise preferences between a couple of candidates. To address physical well-being, an ergonomic performance index, Rapid Upper Limb Assessment (RULA), is combined with the user's pairwise preferences, so that the optimal setting can be computed. Experimental tests have been conducted to validate the method, involving collaborative assembly during the object handling performed by the robot. Results illustrate that the proposed method can improve the physical workload of the operator while easing the collaborative task
BCI for robot control with eye artifacts
No full textLAUREA MAGISTRALEL'interazioni tra uomo e robot sono un argomento in rapida espansione e i robot stanno sempre piu’ acquisendo un ruolo importante nella nostra quotidianeita’. Il supporto ai pazienti e’ uno degli ambiti in cui i robot stanno diventando sempre piu presenti, specialmente per le persone disabili. Le persone con disturbi neurodegenerativi non possono effettuare consapevolmente o volontariamente movimenti diversi da quelli che coinvolgono gli occhi o le palpebre. In questo contesto, i sistemi BCI rappresentano una via alternativa di comunicazione o interazione con il mondo esterno. Per migliorare la vita delle persone disabili, questo paper presenta una nuova interfaccia computer/cervello per controllare un robot di assistenza attraverso l’uso degli artefatti oculari dell’utente. In questo studio, gli artefatti oculari che contaminano i segnali EEG sono considerati una preziosa fonte di informazione grazie al loro alto signal-to-noise ratio e alla generazione intenzionale dei segnali. La metodologia proposta rileva gli artefatti oculari dai segnali EEG attraverso le forme caratteristiche che occorrono durante gli eventi dei battiti di ciglia. I movimenti laterali vengono distinti dai picchi ordinari e dalle valle formazione e dalla fase opposta dei segnali misurati dai canali F7 e F8. Questo lavoro, per quanto ne risulti all’autore, e’ la prima applicazione che utilizza questa metodologia di rilevazione del movimento laterale degli occhi. Per la rilevazione dei battiti, un metodo a doppia soglia viene proposto dagli autori per catturare sia i battiti deboli che quelli regolari, differenziandosi dagli altri algoritmi proposti in letteratura che normalmente tendono ad utilizzare una sola soglia. Gli eventi real-time con i relativi timestamp vengono poi forniti come input ad un secondo algoritmo, per differenziare ancora di piu tra i battiti doppi e quadrupli dalla frequenza di occorrenza dei battiti singoli. Dopo aver testato l’algoritmo sia offline che in real time, l’algoritmo e’ stato successivamente implementato nel dispositivo. Il BCI creato e’ stato in grado di controllare un robot di assistenza attraverso l’utilizzo di una GUI. Gli esperimenti di validazione provano che il BCI e’ in grado di controllare il robot.Human-robot interaction is a rapidly developing field and robots have been taking more active roles in our daily lives. Patient care is one of the fields in which robots are becoming more present, especially for disabled people. Neurodegenerative disordered people cannot consciously or voluntarily produce movements other than those involving the eyes or eyelids. In this context, BCI systems present an alternative way to communicate or interact with the external world. In order to improve the lives of disabled people, this paper presents a novel brain-computer interface to control an assistive robot with user's eye artifacts. In this study, eye artifacts that contaminate the EEG signals are considered a valuable source of information thanks to their high signal-to-noise ratio and intentional generation. The proposed methodology detects eye artifacts from EEG signals through characteristic shapes that occur during the events. The lateral movements are distinguished by their ordered peak and valley formation and the opposite phase of the signals measured at F7 and F8 channels. This work, as far as the author's knowledge is the first method that used this behavior to detect lateral eye movements. For the blinks detection, a double-thresholding method is proposed by the author to catch both weak blinks as well as regular ones, differentiating itself from the other algorithms in the literature that normally uses only one threshold. Real-time detected events with their virtual time stamps are fed into a second algorithm, to further distinguish between double and quadruple blinks from single blinks occurrence frequency. After testing the algorithm offline and in real-time, the algorithm is implemented on the device. The created BCI was able to control an assistive robot through a graphical user interface. The validation experiment proves that the developed BCI is able to control the robot
- …
