Expertise sportive et entraînement perceptivo-cognitif de l’athlète

Pour être performant au plus haut niveau, les athlètes doivent posséder une capacité perceptivo-cognitive supérieure à la moyenne. Cette faculté, reflétée sur le terrain par la vision et l’intelligence de jeu des sportifs, permet d’extraire l’information clé de la scène visuelle. La science du sport a depuis longtemps observé l’expertise perceptivo-cognitive au sein de l’environnement sportif propre aux athlètes. Récemment, des études ont rapporté que l’expertise pouvait également se refléter hors de ce contexte, lors d’activités du quotidien par exemple. De plus, les récentes théories entourant la capacité plastique du cerveau ont amené les chercheurs à développer des outils pour entraîner les capacités perceptivo-cognitives des athlètes afin de les rendre plus performants sur le terrain. Ces méthodes sont la plupart du temps contextuelles à la discipline visée. Cependant, un nouvel outil d’entraînement perceptivo-cognitif, nommé 3-Dimensional Multiple Object Tracking (3D-MOT) et dénué de contexte sportif, a récemment vu le jour et a fait l’objet de nos recherches. Un de nos objectifs visait à mettre en évidence l’expertise perceptivo-cognitive spécifique et non-spécifique chez des athlètes lors d’une même étude. Nous avons évalué la perception du mouvement biologique chez des joueurs de soccer et des non-athlètes dans une salle de réalité virtuelle. Les sportifs étaient systématiquement plus performants en termes d’efficacité et de temps de réaction que les novices pour discriminer la direction du mouvement biologique lors d’un exercice spécifique de soccer (tir) mais également lors d’une action issue du quotidien (marche). Ces résultats signifient que les athlètes possèdent une meilleure capacité à percevoir les mouvements biologiques humains effectués par les autres. La pratique du soccer semble donc conférer un avantage fondamental qui va au-delà des fonctions spécifiques à la pratique d’un sport. Ces découvertes sont à mettre en parallèle avec la performance exceptionnelle des athlètes dans le traitement de scènes visuelles dynamiques et également dénuées de contexte sportif. Des joueurs de soccer ont surpassé des novices dans le test de 3D-MOT qui consiste à suivre des cibles en mouvement et stimule les capacités perceptivo-cognitives. Leur vitesse de suivi visuel ainsi que leur faculté d’apprentissage étaient supérieures. Ces résultats confirmaient des données obtenues précédemment chez des sportifs. Le 3D-MOT est un test de poursuite attentionnelle qui stimule le traitement actif de l’information visuelle dynamique. En particulier, l’attention sélective, dynamique et soutenue ainsi que la mémoire de travail. Cet outil peut être utilisé pour entraîner les fonctions perceptivo-cognitives des athlètes. Des joueurs de soccer entraînés au 3D-MOT durant 30 sessions ont montré une amélioration de la prise de décision dans les passes de 15% sur le terrain comparés à des joueurs de groupes contrôles. Ces données démontrent pour la première fois un transfert perceptivo-cognitif du laboratoire au terrain suivant un entraînement perceptivo-cognitif non-contextuel au sport de l’athlète ciblé. Nos recherches aident à comprendre l’expertise des athlètes par l’approche spécifique et non-spécifique et présentent également les outils d’entraînements perceptivo-cognitifs, en particulier le 3D-MOT, pour améliorer la performance dans le sport de haut-niveau.

Grabbing Your Attention: The Impact of Finding a First Target in Multiple-Target Search

For over 50 years, the Satisfaction of Search effect, and more recently known as the Subsequent Search Miss (SSM) effect, has plagued the field of radiology. Defined as a decrease in additional target accuracy after detecting a prior target in a visual search, SSM errors are known to underlie both real-world search errors (e.g., a radiologist is more likely to miss a tumor if a different tumor was previously detected) and more simplified, lab-based search errors (e.g., an observer is more likely to miss a target ‘T’ if a different target ‘T’ was previously detected). Unfortunately, little was known about this phenomenon’s cognitive underpinnings and SSM errors have proven difficult to eliminate. However, more recently, experimental research has provided evidence for three different theories of SSM errors: the Satisfaction account, the Perceptual Set account, and the Resource Depletion account. A series of studies examined performance in a multiple-target visual search and aimed to provide support for the Resource Depletion account—a first target consumes cognitive resources leaving less available to process additional targets.

To assess a potential mechanism underlying SSM errors, eye movements were recorded in a multiple-target visual search and were used to explore whether a first target may result in an immediate decrease in second-target accuracy, which is known as an attentional blink. To determine whether other known attentional distractions amplified the effects of finding a first target has on second-target detection, distractors within the immediate vicinity of the targets (i.e., clutter) were measured and compared to accuracy for a second target. To better understand which characteristics of attention were impacted by detecting a first target, individual differences within four characteristics of attention were compared to second-target misses in a multiple-target visual search.

The results demonstrated that an attentional blink underlies SSM errors with a decrease in second-target accuracy from 135ms-405ms after detection or re-fixating a first target. The effects of clutter were exacerbated after finding a first target causing a greater decrease in second-target accuracy as clutter increased around a second-target. The attentional characteristics of modulation and vigilance were correlated with second- target misses and suggest that worse attentional modulation and vigilance are predictive of more second-target misses. Taken together, these result are used as the foundation to support a new theory of SSM errors, the Flux Capacitor theory. The Flux Capacitor theory predicts that once a target is found, it is maintained as an attentional template in working memory, which consumes attentional resources that could otherwise be used to detect additional targets. This theory not only proposes why attentional resources are consumed by a first target, but encompasses the research in support of all three SSM theories in an effort to establish a grand, unified theory of SSM errors.

Are stress and mixed urinary incontinence associated with impaired executive control in community-dwelling older women?

Objectives: To assess whether stress or mixed urinary incontinence (UI) is associated with deficits in executive functioning among community-dwelling women. Design: An observational study comparing the performance, using multivariate analyses of variance (MANOVAs) and Bonferroni post hoc test, of continent women and women with stress or mixed UI during executive control tasks. Setting: The research center of the Institut universitaire de gériatrie de Montréal. Participants: One hundred and fifty-five community-dwelling women aged 60 and older participated in the study. Measurements: Based on the Urogenital Distress Inventory (UDI), participants were split into three groups: 35 continent women, 43 women with stress UI, and 78 women with mixed UI. Participants completed a battery of neuropsychological tests and a computerized dual-task test. Results: Women with mixed UI showed poorer performances than continent and stress UI women in executive control functions. Deficits were specific to tests involving switching and sharing/dividing attention between two tasks. Conclusion: Results of this study suggest that mixed UI can be associated with executive control deficits in community-dwelling older women. Future intervention studies in the treatment of UI should take the higher risk of an executive control deficit in women with UI under consideration.

Magnetic susceptibility and particle size for the Shilou red clay section on the eastern Chinese Loess Plateau

The Chinese Loess Plateau red clay sequences display a continuous alternation of sedimentary cycles that represent recurrent climatic fluctuations from 2.58 Ma to the Miocene. Deciphering such a record can provide us with vital information on global and Asian climatic variations. Lack of fossils and failure of absolute dating methods made magnetostratigraphy a leading method to build age models for the red clay sequences. Here we test the magnetostratigraphic age model against cyclostratigraphy. For this purpose we investigate the climate cyclicity recorded in magnetic susceptibility and sedimentary grain size in a red clay section previously dated 11Myr old with magnetostratigraphy alone. Magnetostratigraphy dating based on only visual correlation could potentially lead to erroneous age model. In this study the correlation is executed through the iteration procedure until it is supported by cyclostratigraphy; i.e., Milankovitch cycles are resolved in the best possible manner. Our new age model provides an age of 5.2Ma for the Shilou profile. Based on the new age model, wavelet analysis reveals the well-preserved 400 kyr and possible 100 kyr eccentricity cycles on the eastern Chinese Loess Plateau. Further, paleomonsoon evolution during 2.58-5.2Ma is reconstructed and divided into three intervals (2.58-3.6Ma, 3.6-4.5Ma, and 4.5-5.2Ma). The upper part, the youngest stage, is characterized by a relatively intensified summer monsoon, the middle stage reflects an intensification of the winter monsoon and aridification in Asia, and the earliest stage indicates that summer and winter monsoon cycles may have rapidly altered. The use of cyclostratigraphy along withmagnetostratigraphy gives us an effectivemethod of dating red clay sequences, and our results imply that many presently published age models for the red clay deposits should be perhaps re-evaluated.

Understandings of transnational families in debates on Migration and development

International migration sets in motion a range of significant transnational processes that connect countries and people. How migration interacts with development and how policies might promote and enhance such interactions have, since the turn of the millennium, gained attention on the international agenda. The recognition that transnational practices connect migrants and their families across sending and receiving societies forms part of this debate. The ways in which policy debate employs and understands transnational family ties nevertheless remain underexplored. This article sets out to discern the understandings of the family in two (often intermingled) debates concerned with transnational interactions: The largely state and policydriven discourse on the potential benefits of migration on economic development, and the largely academic transnational family literature focusing on issues of care and the micro-politics of gender and generation. Emphasizing the relation between diverse migration-development dynamics and specific family positions, we ask whether an analytical point of departure in respective transnational motherhood, fatherhood or childhood is linked to emphasizing certain outcomes. We conclude by sketching important strands of inclusions and exclusions of family matters in policy discourse and suggest ways to better integrate a transnational family perspective in global migration-development policy.

Electrochemical RNA genosensors for toxic algal species: enhancing selectivity and sensitivity

Harmful algal blooms (HABs) are becoming more frequent as climate changes, with tropical species moving northward. Monitoring programs detecting the presence of toxic algae before they bloom are of paramount importance to protect aquatic ecosystems, aquaculture, human health and local economies. Rapid and reliable species identification methods using molecular barcodes coupled to biosensor detection tools have received increasing attention over the past decade as an alternative to the impractical standard microscopic counting-based techniques. This work reports on a PCR amplification-free electrochemical genosensor for the enhanced selective and sensitive detection of RNA from multiple Mediterranean toxic algal species. For a sandwich hybridization (SHA), we designed longer capture and signal probes for more specific target discrimination against a single base-pair mismatch from closely related species and for reproducible signals. We optimized experimental conditions, viz., minimal probe concentration in the SHA on a screen-printed gold electrode and selected the best electrochemical mediator. Probes from 13 Mediterranean dinoflagellate species were tested under optimized conditions and the format further tested for quantification of RNA from environmental samples. We not only enhanced the selectivity and sensitivity of the state-of-the-art toxic algal genosensors but also increased the repertoire of toxic algal biosensors in the Mediterranean, towards an integral and automatic monitoring system.

Electrochemical RNA genosensors for toxic algal species: enhancing selectivity and sensitivity

Harmful algal blooms (HABs) are becoming more frequent as climate changes, with tropical species moving northward. Monitoring programs detecting the presence of toxic algae before they bloom are of paramount importance to protect aquatic ecosystems, aquaculture, human health and local economies. Rapid and reliable species identification methods using molecular barcodes coupled to biosensor detection tools have received increasing attention over the past decade as an alternative to the impractical standard microscopic counting-based techniques. This work reports on a PCR amplification-free electrochemical genosensor for the enhanced selective and sensitive detection of RNA from multiple Mediterranean toxic algal species. For a sandwich hybridization (SHA), we designed longer capture and signal probes for more specific target discrimination against a single base-pair mismatch from closely related species and for reproducible signals. We optimized experimental conditions, viz., minimal probe concentration in the SHA on a screen-printed gold electrode and selected the best electrochemical mediator. Probes from 13 Mediterranean dinoflagellate species were tested under optimized conditions and the format further tested for quantification of RNA from environmental samples. We not only enhanced the selectivity and sensitivity of the state-of-the-art toxic algal genosensors but also increased the repertoire of toxic algal biosensors in the Mediterranean, towards an integral and automatic monitoring system.

Fast and robust face finding via local context

[EN]In visual surveillance face detection can be an important cue for initializing tracking algorithms. Recent work in psychophics hints at the importance of the local context of a face for robust detection, such as head contours and torso. This paper describes a detector that actively utilizes the idea of local context. The promise is to gain robustness that goes beyond the capabilities of traditional face detection making it particularly interesting for surveillance. The performance of the proposed detector in terms of accuracy and speed is evaluated on data sets from PETS 2000 and PETS 2003 and compared to the object-centered approach. Particular attention is paid to the role of available image resolution.

Anti-VEGF treatment of patients with diabetic macular edema : Studies of visual acuity, macular edema and patient-reported outcomes

The aim of this thesis was to describe and evaluate visual acuity, macular edema and patientreported outcomes (PRO) following anti-VEGF treatment of diabetic macular edema (DME) patients in a real-world setting. Using a longitudinal study design, a cohort of DME patients was followed from baseline to 1 year after treatment start. Data were collected from two eye clinics at two county hospitals. Social background characteristics, medical data and PRO were measured before treatment initiation, at four month and after 1 year. A total of 57 patients completed the study. Mean age was 69 years and the sample was equally distributed regarding sex. At baseline, the patients described their general health as low. One year after treatment initiation, 30 patients had improved visual acuity and 27 patients had no improvement in visual acuity. The patients whose visual acuity improved reported an improvement in several subscales in patient-reported outcome measures (PROM), which was in contrast to the group that experienced a decline in visual acuity, where there was no improvement in PROM. Outcomes from the study can be useful for developing and providing relevant information and support to patients undergoing this treatment.

Patient-reported outcomes and visual acuity after 12 months of anti-VEGF-treatment for sight-threatening diabetic macular edema in a real world setting

Aims To examine objective visual acuity measured with ETDRS, retinal thickness (OCT), patient reported outcome and describe levels of glycated hemoglobin and its association with the effects on visual acuity in patients treated with anti-VEGF for visual impairment due to diabetic macular edema (DME) during 12 months in a real world setting. Methods In this cross-sectional study, 58 patients (29 females and 29 males; mean age, 68 years) with type 1 and type 2 diabetes diagnosed with DME were included. Medical data and two questionnaires were collected; an eye-specific (NEI VFQ-25) and a generic health-related quality of life questionnaire (SF-36) were used. Results The total patient group had significantly improved visual acuity and reduced retinal thickness at 4 months and remains at 12 months follow up. Thirty patients had significantly improved visual acuity, and 27 patients had no improved visual acuity at 12 months. The patients with improved visual acuity had significantly improved scores for NEI VFQ-25 subscales including general health, general vision, near activities, distance activities, and composite score, but no significant changes in scores were found in the group without improvements in visual acuity. Conclusions Our study revealed that anti-VEGF treatment improved visual acuity and central retinal thickness as well as patient-reported outcome in real world 12 months after treatment start.

Vestibular and oculomotor influences on visual dependency

The degree to which a person relies on visual stimuli for spatial orientation is termed visual dependency (VD). VD is considered a perceptual trait or cognitive style influenced by psychological factors and mediated by central re-weighting of the sensory inputs involved in spatial orientation. VD is often measured using the rod-and-disk test, wherein participants align a central rod to the subjective visual vertical (SVV) in the presence of a background that is either stationary or rotating around the line of sight - dynamic SVV. Although this task has been employed to assess VD in health and vestibular disease, it is unknown what effect torsional nystagmic eye movements may have on individual performance. Using caloric ear irrigation, 3D video-oculography and the rod-and-disk test, we show that caloric torsional nystagmus modulates measures of visual dependency and demonstrate that increases in tilt after irrigation are positively correlated with changes in ocular torsional eye movements. When the direction of the slow phase of the torsional eye movement induced by the caloric is congruent with that induced by the rotating visual stimulus, there is a significant increase in tilt. When these two torsional components are in opposition there is a decrease. These findings show that measures of visual dependence can be influenced by oculomotor responses induced by caloric stimulation. The findings are of significance for clinical studies as they indicate that VD, which often increases in vestibular disorders, is not only modulated by changes in cognitive style but also by eye movements, in particular nystagmus.

A visual and contextual comparative study of the work of Picasso and Chanel towards an understanding of the overlaps between Modern Art and Fashion.

From the beginning of the twentieth century, ``Modernism`` impacted and transformed art and clothing. Pablo Picasso and Gabrielle ``Coco`` Chanel were two of the most central characters in Modernism working simultaneously in their disciplines. Picasso`s innovations, particularly in abstract art and Chanel`s fashion designs, that dramatically departed from the previous corseted and highly deco-rative styles, were so significant that they have left an influence on contemporary art and fashion. This study will compare their visual works and documented evidence of their motivations, within the context of their cultural backgrounds, to reveal meaning in the occurrences of overlaps. This approach has ex-amined the historical, cultural background of the artist and designer`s environment from different per-spectives, adding to previous research in this area. Through this research, outcomes of the analysis have shown similarities and divergences in the wider genres of art and fashion and the practice of the artist and fashion designer. The reference list to this text, used in the survey, gives a comprehensive overview of pertinent publications disseminating Picasso and Chanel`s visual works, oral perspectives and cultural impact.

Datasets, features, learning, and models in visual recognition

Visual recognition is a fundamental research topic in computer vision. This dissertation explores datasets, features, learning, and models used for visual recognition. In order to train visual models and evaluate different recognition algorithms, this dissertation develops an approach to collect object image datasets on web pages using an analysis of text around the image and of image appearance. This method exploits established online knowledge resources (Wikipedia pages for text; Flickr and Caltech data sets for images). The resources provide rich text and object appearance information. This dissertation describes results on two datasets. The first is Berg’s collection of 10 animal categories; on this dataset, we significantly outperform previous approaches. On an additional set of 5 categories, experimental results show the effectiveness of the method. Images are represented as features for visual recognition. This dissertation introduces a text-based image feature and demonstrates that it consistently improves performance on hard object classification problems. The feature is built using an auxiliary dataset of images annotated with tags, downloaded from the Internet. Image tags are noisy. The method obtains the text features of an unannotated image from the tags of its k-nearest neighbors in this auxiliary collection. A visual classifier presented with an object viewed under novel circumstances (say, a new viewing direction) must rely on its visual examples. This text feature may not change, because the auxiliary dataset likely contains a similar picture. While the tags associated with images are noisy, they are more stable when appearance changes. The performance of this feature is tested using PASCAL VOC 2006 and 2007 datasets. This feature performs well; it consistently improves the performance of visual object classifiers, and is particularly effective when the training dataset is small. With more and more collected training data, computational cost becomes a bottleneck, especially when training sophisticated classifiers such as kernelized SVM. This dissertation proposes a fast training algorithm called Stochastic Intersection Kernel Machine (SIKMA). This proposed training method will be useful for many vision problems, as it can produce a kernel classifier that is more accurate than a linear classifier, and can be trained on tens of thousands of examples in two minutes. It processes training examples one by one in a sequence, so memory cost is no longer the bottleneck to process large scale datasets. This dissertation applies this approach to train classifiers of Flickr groups with many group training examples. The resulting Flickr group prediction scores can be used to measure image similarity between two images. Experimental results on the Corel dataset and a PASCAL VOC dataset show the learned Flickr features perform better on image matching, retrieval, and classification than conventional visual features. Visual models are usually trained to best separate positive and negative training examples. However, when recognizing a large number of object categories, there may not be enough training examples for most objects, due to the intrinsic long-tailed distribution of objects in the real world. This dissertation proposes an approach to use comparative object similarity. The key insight is that, given a set of object categories which are similar and a set of categories which are dissimilar, a good object model should respond more strongly to examples from similar categories than to examples from dissimilar categories. This dissertation develops a regularized kernel machine algorithm to use this category dependent similarity regularization. Experiments on hundreds of categories show that our method can make significant improvement for categories with few or even no positive examples.

Expertise sportive et entraînement perceptivo-cognitif de l’athlète

Pour être performant au plus haut niveau, les athlètes doivent posséder une capacité perceptivo-cognitive supérieure à la moyenne. Cette faculté, reflétée sur le terrain par la vision et l’intelligence de jeu des sportifs, permet d’extraire l’information clé de la scène visuelle. La science du sport a depuis longtemps observé l’expertise perceptivo-cognitive au sein de l’environnement sportif propre aux athlètes. Récemment, des études ont rapporté que l’expertise pouvait également se refléter hors de ce contexte, lors d’activités du quotidien par exemple. De plus, les récentes théories entourant la capacité plastique du cerveau ont amené les chercheurs à développer des outils pour entraîner les capacités perceptivo-cognitives des athlètes afin de les rendre plus performants sur le terrain. Ces méthodes sont la plupart du temps contextuelles à la discipline visée. Cependant, un nouvel outil d’entraînement perceptivo-cognitif, nommé 3-Dimensional Multiple Object Tracking (3D-MOT) et dénué de contexte sportif, a récemment vu le jour et a fait l’objet de nos recherches. Un de nos objectifs visait à mettre en évidence l’expertise perceptivo-cognitive spécifique et non-spécifique chez des athlètes lors d’une même étude. Nous avons évalué la perception du mouvement biologique chez des joueurs de soccer et des non-athlètes dans une salle de réalité virtuelle. Les sportifs étaient systématiquement plus performants en termes d’efficacité et de temps de réaction que les novices pour discriminer la direction du mouvement biologique lors d’un exercice spécifique de soccer (tir) mais également lors d’une action issue du quotidien (marche). Ces résultats signifient que les athlètes possèdent une meilleure capacité à percevoir les mouvements biologiques humains effectués par les autres. La pratique du soccer semble donc conférer un avantage fondamental qui va au-delà des fonctions spécifiques à la pratique d’un sport. Ces découvertes sont à mettre en parallèle avec la performance exceptionnelle des athlètes dans le traitement de scènes visuelles dynamiques et également dénuées de contexte sportif. Des joueurs de soccer ont surpassé des novices dans le test de 3D-MOT qui consiste à suivre des cibles en mouvement et stimule les capacités perceptivo-cognitives. Leur vitesse de suivi visuel ainsi que leur faculté d’apprentissage étaient supérieures. Ces résultats confirmaient des données obtenues précédemment chez des sportifs. Le 3D-MOT est un test de poursuite attentionnelle qui stimule le traitement actif de l’information visuelle dynamique. En particulier, l’attention sélective, dynamique et soutenue ainsi que la mémoire de travail. Cet outil peut être utilisé pour entraîner les fonctions perceptivo-cognitives des athlètes. Des joueurs de soccer entraînés au 3D-MOT durant 30 sessions ont montré une amélioration de la prise de décision dans les passes de 15% sur le terrain comparés à des joueurs de groupes contrôles. Ces données démontrent pour la première fois un transfert perceptivo-cognitif du laboratoire au terrain suivant un entraînement perceptivo-cognitif non-contextuel au sport de l’athlète ciblé. Nos recherches aident à comprendre l’expertise des athlètes par l’approche spécifique et non-spécifique et présentent également les outils d’entraînements perceptivo-cognitifs, en particulier le 3D-MOT, pour améliorer la performance dans le sport de haut-niveau.

Integrated visual perception architecture for robotic clothes perception and manipulation

This thesis proposes a generic visual perception architecture for robotic clothes perception and manipulation. This proposed architecture is fully integrated with a stereo vision system and a dual-arm robot and is able to perform a number of autonomous laundering tasks. Clothes perception and manipulation is a novel research topic in robotics and has experienced rapid development in recent years. Compared to the task of perceiving and manipulating rigid objects, clothes perception and manipulation poses a greater challenge. This can be attributed to two reasons: firstly, deformable clothing requires precise (high-acuity) visual perception and dexterous manipulation; secondly, as clothing approximates a non-rigid 2-manifold in 3-space, that can adopt a quasi-infinite configuration space, the potential variability in the appearance of clothing items makes them difficult to understand, identify uniquely, and interact with by machine. From an applications perspective, and as part of EU CloPeMa project, the integrated visual perception architecture refines a pre-existing clothing manipulation pipeline by completing pre-wash clothes (category) sorting (using single-shot or interactive perception for garment categorisation and manipulation) and post-wash dual-arm flattening. To the best of the author’s knowledge, as investigated in this thesis, the autonomous clothing perception and manipulation solutions presented here were first proposed and reported by the author. All of the reported robot demonstrations in this work follow a perception-manipulation method- ology where visual and tactile feedback (in the form of surface wrinkledness captured by the high accuracy depth sensor i.e. CloPeMa stereo head or the predictive confidence modelled by Gaussian Processing) serve as the halting criteria in the flattening and sorting tasks, respectively. From scientific perspective, the proposed visual perception architecture addresses the above challenges by parsing and grouping 3D clothing configurations hierarchically from low-level curvatures, through mid-level surface shape representations (providing topological descriptions and 3D texture representations), to high-level semantic structures and statistical descriptions. A range of visual features such as Shape Index, Surface Topologies Analysis and Local Binary Patterns have been adapted within this work to parse clothing surfaces and textures and several novel features have been devised, including B-Spline Patches with Locality-Constrained Linear coding, and Topology Spatial Distance to describe and quantify generic landmarks (wrinkles and folds). The essence of this proposed architecture comprises 3D generic surface parsing and interpretation, which is critical to underpinning a number of laundering tasks and has the potential to be extended to other rigid and non-rigid object perception and manipulation tasks. The experimental results presented in this thesis demonstrate that: firstly, the proposed grasp- ing approach achieves on-average 84.7% accuracy; secondly, the proposed flattening approach is able to flatten towels, t-shirts and pants (shorts) within 9 iterations on-average; thirdly, the proposed clothes recognition pipeline can recognise clothes categories from highly wrinkled configurations and advances the state-of-the-art by 36% in terms of classification accuracy, achieving an 83.2% true-positive classification rate when discriminating between five categories of clothes; finally the Gaussian Process based interactive perception approach exhibits a substantial improvement over single-shot perception. Accordingly, this thesis has advanced the state-of-the-art of robot clothes perception and manipulation.