Portail HAL des publications du LIRMM
Not a member yet
13279 research outputs found
Sort by
sEMG-Based Motion Recognition for Robotic Surgery Training Using Machine Learning and Variable-Length Sliding Windows – A Preliminary Study
No full textInternational audienceThe advent of robotic surgery has brought about a paradigm shift in the medical field, necessitating the development of corresponding surgical skills training and assessment methods. These methods aim to enable surgeons to acquire the requisite skills for robotic surgery in the most efficient manner. Despite the progression from a master-apprentice system to manual objective assessment and then automated performance assessment methods, certain limitations have been observed. Our research aims to address these limitations by exploring muscle activity and state information during training via surface electromyography (sEMG) signals. This approach is intended to eventually provide interpretable information that can enhance the trainee's understanding of assessment feedback and facilitate skill improvement. Building on our first study that validated the feasibility of motion primitive recognition based on sEMG signals, this work compares the performance of various machine learning (ML) methods for motion primitive recognition. It also investigates the effect of different parameters of the sliding window on recognition accuracy. Our findings indicate that the deep neural network (DNN) when paired with optimal sliding window parameters, can achieve the best average accuracy of 61.76% in this study. The discoveries also provide a reference of parameter settings for variable-length sliding window approach and ML methods in recognition of robotic surgery motion based on sEMG data. By demonstrating the feasibility and exploring the most effective analysis method, this work lays down the first stone to address the research topic of integrating muscle information into multimodal surgical skill training and assessment
Walking in Mud: Modeling, Control, and Experiments of Quadruped Locomotion
No full textInternational audienceSoft wet grounds such as mud, sand, or forest soils, are difficult to navigate because it is hard to predict the response of the yielding ground and energy lost in deformation. In this paper, we address the control of quadruped robots' static gait in deep mud. We present and compare six controller versions with increasing complexity that use a combination of a creeping gait, a foot-substrate interaction detection, a model-based Center of Mass positioning, and a leg speed monitoring, along with their experimental validation in a tank filled with mud, and demonstrations in natural environments. We implement and test the controllers on a Go1 quadruped robot and also compare the performance to the commercially available dynamic gait controller of Go1. While the commercially available controller was only sporadically able to traverse in 12cm deep mud with a 0.35 water/solid matter ratio for a short time, all proposed controllers successfully traversed the test ground while using up to 4.42 times less energy. The results of this paper can be used to deploy quadruped robots on soft wet grounds, so far inaccessible to legged robots
Correction of non-traumatic extensor tendon dislocation and ulnar drift at the metacarpophalangeal joint by the modified Dell technique
No full textInternational audienceChronic ulnar extensor tendon dislocation at the metacarpophalangeal joint causes permanent extension deficit and ulnar drift. Several soft tissue procedures have been described for realignment of the extensor tendon in post-traumatic reducible instability or in combination with joint replacement in case of altered metacarpophalangeal joint in inflammatory conditions. However, no studies reported correction of both extension lag and ulnar deviation following isolated surgical treatment of ulnar extensor tendon dislocation at the metacarpophalangeal joint. The present study evaluated the clinical and functional results of isolated correction of chronic non-traumatic ulnar extensor tendon dislocation at metacarpophalangeal level using the modified Dell technique
3DSSDF: Underwater 3D Sonar Reconstruction Using Signed Distance Functions
No full textInternational audienceUnderwater autonomous robotic operations require online localization and 3D mapping. Because of the absence of absolute positioning underwater, these tasks strongly rely on embedded sensors, including proprioceptive or navigation sensors -which can be fused for an odometry, -and exteroceptive sensors. One of the most popular exteroceptive sensors for underwater is the imaging sonar, which emits a large fan-shaped acoustic signal and estimates the position of the surrounding obstacles from a measure of the reflected signal. This paper addresses underwater online localization and 3D mapping using a forward looking, wide-aperture imaging sonar and vehicle's intrinsic navigation estimates. We introduce 3DSSDF (3D Sonar Reconstruction Using Signed Distance Functions), a new localization and 3D mapping algorithm based on signed distance functions, which is evaluated in simulation and on real data, in man-made and natural environments. Comparisons to reference trajectories and maps demonstrate that, in our tests, 3DSSDF efficiently corrects navigation drift and that trajectory and map accuracy is always below 1 m and below 1% of the distanced travelled, which can be sufficient for the safe inspection of natural or artificial underwater structures
Seatizen Atlas: a collaborative dataset of underwater and aerial marine imagery
No full textPublisher: Nature Publishing GroupInternational audienceCitizen Science initiatives have a worldwide impact on environmental research by providing data at a global scale and high resolution. Mapping marine biodiversity remains a key challenge to which citizen initiatives can contribute. Here we describe a dataset made of both underwater and aerial imagery collected in shallow tropical coastal areas by using various low cost platforms operated either by citizens or researchers. This dataset is regularly updated and contains \textgreater1.6 M images from the Southwest Indian Ocean. Most of images are geolocated, and some are annotated with 51 distinct classes (e.g. fauna, and habitats) to train AI models. The quality of these photos taken by action cameras along the trajectories of different platforms, is highly heterogeneous (due to varying speed, depth, turbidity, and perspectives) and well reflects the challenges of underwater image recognition. Data discovery and access rely on DOI assignment while data interoperability and reuse is ensured by complying with widely used community standards. The open-source data workflow is provided to ease contributions from anyone collecting pictures
Combining constraint programming and a participatory approach to design agroecological cropping systems
No full textInternational audienceContext: Agroecology implementation around the world have shown that increasing the complexity of the agroecosystem leads to increased resilience, lower dependence on synthetic inputs, the provision of ecosystem services and improved performance. However, designing diversified agroecosystems is particularly complex because of the diverse factors to take into account for each specific local context and the range of possible spatiotemporal crop combinations. Objective: Here we propose an iterative agroecological design approach combining artificial intelligence with constraint programming and co-design workshops with farmers to explore and optimize spatiotemporal cropping arrangements in diversified cropping systems. Methods: Our iterative approach comprises a three-step loop for designing new cropping systems: 1) identifying problem data and spatiotemporal constraints; 2) applying a flexible constraint programming model, and refining/removing constraints iteratively with farmers' input until a solution is found; and 3) evaluating solutions through model assessment and workshops with farmers, leading to the design of a new scenario if necessary (repeating step 2). We applied our approach to a case study involving diversified mixed fruit tree–vegetable cropping systems in southern France, whereby farmers were involved in co-design workshops with an agronomist. Results and conclusions: The constraint programming model simulated most important farmers' constraints while adapting to the input of new information during the design process. The workshops facilitated knowledge elicitation, with progressive questioning of farming practices, while fostering a learning process through farmer-agronomist discussions. Meanwhile, the scope of the problem was iteratively outlined during the process, driven by the need to seek trade-offs between all of the constraints, and informed by model feedback. This approach allowed farmers to explore and assess disruptive scenarios, in turn facilitating informed decisions that jointly addressed agroecological and operational objectives on their farms. Significance: The framework presented and illustrated in this study provides a basis for exploring and optimizing spatiotemporal cropping arrangements in diversified cropping systems
On counting orientations for graph homomorphisms and for dually embedded graphs using the Tutte polynomial of matroid perspectives
No full textInternational audienceThe goal of this note is to highlight applications to graph orientations of some recent results in oriented matroid perspectives, by providing adapted settings and a detailed example. An (oriented) matroid perspective (or morphism, or strong map, or quotient) is an ordered pair of (oriented) matroids satisfying some structural relationship. In the case of graphs, two notable types of perspectives can be considered: graph homomorphisms, and dually embedded graphs on a surface. The Tutte polynomial of such a perspective is a classical polynomial (also called Las Vergnas polynomial in the case of dually embedded graphs), whose coefficients and (some) evaluations are known to count pairs of orientations of certain types. We show how coefficients and (other) evaluations of the polynomial also count pairs of orientations of certain types where some edge orientations are fixed, as well as some equivalence classes of pairs of orientations of certain types. These properties appear when the edge set is linearly ordered
Organotypic culture of human brain explants as a preclinical model for AI-driven antiviral studies
No full textInternational audienceViral neuroinfections represent a major health burden for which the development of antivirals is needed. Antiviral compounds that target the consequences of a brain infection (symptomatic treatment) rather than the cause (direct-acting antivirals) constitute a promising mitigation strategy that requires to be investigated in relevant models. However, physiological surrogates mimicking an adult human cortex are lacking, limiting our understanding of the mechanisms associated with viro-induced neurological disorders. Here, we optimized the Organotypic culture of Post-mortem Adult human cortical Brain explants (OPAB) as a preclinical platform for Artificial Intelligence (AI)-driven antiviral studies. OPAB shows robust viability over weeks, well-preserved 3D cytoarchitecture, viral permissiveness, and spontaneous local field potential (LFP). Using LFP as a surrogate for neurohealth, we developed a machine learning framework to predict with high confidence the infection status of OPAB. As a proof-of-concept, we showed that antiviral-treated OPAB could partially restore LFP-based electrical activity of infected OPAB in a donor-dependent manner. Together, we propose OPAB as a physiologically relevant and versatile model to study neuroinfections and beyond, providing a platform for preclinical drug discovery
Quadratic versus Polynomial Unconstrained Binary Models for Quantum Optimization illustrated on Railway Timetabling
No full textQuantum Approximate Optimization Algorithm (QAOA) is one of the most short-term promising quantum-classical algorithm to solve unconstrained combinatorial optimization problems. It alternates between the execution of a parametrized quantum circuit and a classical optimization. There are numerous levers for enhancing QAOA performances, such as the choice of quantum circuit meta-parameters or the choice of the classical optimizer. In this paper, we stress on the importance of the input problem formulation by illustrating it with the resolution of an industrial railway timetabling problem. Specifically, we present a generic method to reformulate any polynomial problem into a Polynomial Unconstrained Binary Optimization (PUBO) problem, with a specific formulation imposing penalty terms to take binary values when the constraints are linear. We also provide a generic reformulation into a Quadratic Unconstrained Binary Optimization (QUBO) problem. We then conduct a numerical comparison between the PUBO with binary penalty terms and the QUBO formulations proposed on a railway timetabling problem solved with QAOA. Our results illustrate that the PUBO reformulation outperforms the QUBO one for the problem at hand
Visual background information modulates motor contagions in humans
No full textInternational audienceMotor contagions refer to implicit effects induced by the observation of actions made by others on one’s own actions. A plethora of studies conducted over the last two decades have demonstrated that both observed and predicted actions can induce various kinds of motor contagions in a human observer. However, motor contagions have always been investigated with regard to different features of an observed action, and it remains unclear whether the background environment in which an observed action takes place modulates motor contagions as well. Here, we investigated participant movements in an empirical hand steering task during which the participants were required to move a cursor through a visual channel after being presented with videos of an actor performing the same task. We manipulated the congruency between the actions shown in the video and the background channels and examined whether and how they affected the participants’ own movements. We observed a clear interaction between the observed action and its background. The movement time of the participants’ actions tended to increase or decrease depending on whether they observed a faster or slower movement, respectively, and these changes were amplified if the background was not congruent with the action contained within it. These results suggest that background information can modulate motor contagions in humans