1,720,956 research outputs found
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
Byzantine fault-tolerant Swarm-SLAM through blockchain-based smart contracts
Full text linkLAUREA MAGISTRALEAl fine di navigare ed esplorare ambienti sconosciuti senza l'ausilio di sistemi esterni di localizzazione, i sistemi robotici autonomi devono essere in grado di eseguire la localizzazione e mappatura simultanea, abbreviato in SLAM. Attraverso le tecniche SLAM, i robot possono costruire una mappa dell'ambiente e localizzarsi al suo interno in tempo reale.
Decenni di ricerca intensiva hanno portato a soluzioni efficienti nel campo dello SLAM per robot singoli, tuttavia, recentemente, l'attenzione si è spostata al design di sistemi SLAM multi-robot, in cui gruppi di robot costituiscono in cooperazione una mappa e migliorano le stime di localizzazione attraverso lo scambio di informazioni locali. Lo SLAM multi-robot offre opportunità uniche per migliorare l'efficienza, la robustezza e la parallelizzazione, affrontando tuttavia le sfide di scalabilità e di aggregazione coerente di dati potenzialmente in conflitto.
Mentre la robustezza è spesso indicata come una caratteristica intrinseca dei sistemi multi-robot grazie alla presenza di molti robot, ricerche recenti hanno dimostrato che la ridondanza e la parallelizzazione delle operazioni non sono sufficienti per ottenere robustezza del sistema contro robot malfunzionanti. È ragionevole presumere che un sottoinsieme di robot possa comportarsi in modo errato, deviando dall'algoritmo progettato, a causa di errori interni o di manomissioni esterne. In accordo con la letteratura sui sistemi decentralizzati, chiamo tali robot malfunzionanti ''robot bizantini''.
Questa tesi studia la robustezza del framework allo stato dell'arte per lo SLAM multi-robot in sciami di robot decentralizzati, chiamato Swarm-SLAM. Mostro che Swarm-SLAM è vulnerabile alla presenza di robot bizantini, anche solo uno di essi è sufficiente per compromettere l'intero sistema. Pertanto, ispirato dalle recenti ricerche sulla robotica degli sciami che utilizza la tecnologia blockchain, ho sviluppato un applicativo di sicurezza per Swarm-SLAM che sfrutta contratti intelligenti, che sono algoritmi distribuiti in esecuzione sulla blockchain. Testo la mia soluzione con un insieme di simulazioni di gruppi di otto robot che eseguono algoritmi codificati in ROS2 e un framework blockchain personalizzato. I risultati mostrano che la soluzione proposta rende Swarm-SLAM tollerante a guasti bizantini significativi.
La mia analisi mostra anche che l'aumento della tolleranza ai guasti bizantini è correlato a una diminuzione dell'efficienza del sistema. Questa tesi discute tale compromesso tra robustezza ed efficienza e affronta in modo completo le problematiche di sicurezza che Swarm-SLAM, in particolare, e lo SLAM multi-robot, in generale, affrontano e come potrebbero essere potenzialmente affrontate attraverso future ricerche in soluzioni basate su blockchain per la robotica.In order to navigate and explore unknown environments without external localisation systems, autonomous robotics systems must be able to perform Simultaneous Localisation And Mapping, SLAM for short.
Through SLAM techniques, robots can build a map of the environment and localise themselves in it in real time.
Decades of intensive research have led to efficient solutions in single-robot SLAM, however recent attention has shifted to the design of multi-robot SLAM systems where groups of robots cooperatively build a map and improve localisation estimates through exchange of local information. Multi-robot SLAM offers unique opportunities for improved efficiency, robustness, and parallelisation, however facing the challenges of scalability and consistent data aggregation of potentially conflicting pieces of information.
While robustness is often indicated as an intrinsic characteristic of multi-robot systems thanks to the presence of many robots, recent research has shown that robot redundancy and parallelisation of operations are not sufficient to achieve system robustness against misbehaving robots. It is reasonable to assume that a subset of robots may misbehave, deviating from the designed algorithm, due to internal errors or to external malicious tampering. In agreement with decentralised system literature, I name such misbehaving robots as Byzantine robots.
This thesis studies the robustness of the state-of-the-art framework for multi-robot SLAM in decentralised robot swarms, which is called Swarm-SLAM. I show that Swarm-SLAM is vulnerable to the presence of Byzantine robots: even one of them is sufficient to jeopardise the entire system. Therefore, inspired by recent research on blockchain-based swarm robotics, I built a security layer for Swarm-SLAM through blockchain-based smart contracts, which are distributed algorithms running on the blockchain. I test my solution with a set of physics-driven simulations of groups of eight robots running algorithms coded in ROS2 and a custom blockchain framework. The results show that the proposed blockchain-based solution makes Swarm-SLAM tolerant to relatively large Byzantine faults.
My analysis also shows that the increase in Byzantine fault tolerance is compensated by a decrease in system efficiency. This thesis discusses such a robustness-efficiency trade-off and also comprehensively discusses the security issues that Swarm-SLAM, in the specific, and multi-robot SLAM, in general, face and how they could be potentially addressed through future research in blockchain-based solutions for robotics
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
koamabayili/VECTRON-author-checklist: VECTRON author checklist
No full textWe have done our best to complete the author checklist relating to the use of animals in the hut study. Note that the objective for the hut study was to evaluate the IRS treatment applications for residual efficacy against Anopheles mosquitoes, including the local An. coluzzii mosquito population. Cows were only used to attract mosquitoes into the huts and no tests were carried out directly on the cows. The author checklist is intended for use with studies where experiments are carried out on animals, which is why we have had such difficulty in completing this for the hut study, as many of the questions do not relate to how the cows were used
- …
