13 research outputs found
Modular ROS-based software architecture for reconfigurable, Industry 4.0 compatible robotic workcells
No full textIncremental Policy Refinement by Recursive Regression and Kinesthetic Guidance
No full textFast deployment of robot tasks requires appropriate
tools that enable efficient reuse of existing robot control
policies. Learning from Demonstration (LfD) is a popular tool
for the intuitive generation of robot policies, but the issue of
how to address the adaptation of existing policies has not been
properly addressed yet. In this work, we propose an incremental
LfD framework that efficiently solves the above-mentioned
issue. It has been implemented and tested on a number of
popular collaborative robots, including Franka Emika Panda,
Universal Robot UR10, and KUKA LWR 4
Learning of Exception Strategies in Assembly Tasks
No full textAssembly tasks performed with a robot often fail due to unforeseen situations, regardless of the fact that we carefully learned and optimized the assembly policy. This problem is even more present in humanoid robots acting in an unstructured environment where it is not possible to anticipate all factors that might lead to the failure of the given task. In this work, we propose a concurrent LfD framework, which associates demonstrated exception strategies to the given context. Whenever a failure occurs, the proposed algorithm generalizes past experience regarding the current context and generates an appropriate policy that solves the assembly issue. For this purpose, we applied PCA on force/torque data, which generates low dimensional descriptor of the current context. The proposed framework was validated in a peg-in-hole (PiH) task using Franka-Emika Panda robot.This is the author submitted version to ICRA 2020. For the publisher version, please access 10.1109/ICRA40945.2020.9197480
Enhancing the performance of adaptive iterative learning control with reinforcement learning
No full text
Autonomous Learning of Assembly Tasks from the Corresponding Disassembly Tasks
No full textAn assembly task is in many cases just a reverse
execution of the corresponding disassembly task. During the
assembly, the object being assembled passes consecutively from
state to state until completed, and the set of possible movements
becomes more and more constrained. Based on the observation
that autonomous learning of physically constrained tasks can
be advantageous, we use information obtained during learning
of disassembly in assembly. For autonomous learning of a
disassembly policy we propose to use hierarchical reinforcement
learning, where learning is decomposed into a highlevel
decision-making and underlying lower-level intelligent
compliant controller, which exploits the natural motion in
a constrained environment. During the reverse execution of
disassembly policy, the motion is further optimized by means
of an iterative learning controller. The proposed approach was
verified on two challenging tasks - a maze learning problem and
autonomous learning of inserting a car bulb into the casing
The search for tourette syndrome genes : a conceptual and experimental approach
No full textDissertation (PhD) -- University of Stellenbosch, 1999.ENGLISH SUMMARY: Tourette syndrome has been reported in most populations throughout the world.
Overall, there appears to be similar clinical phenomenology and psychopathology,
which may serve as an indication of the biological nature for the condition.
The diagnosis of Tourette syndrome represents a challenge for physicians because of
clinical heterogeneity and often-present comorbidity with other known
neurobehavioural conditions. Due to these clinical overlaps Tourette syndrome may
serve as a model disorder for investigating the relationship between various
neurological and behavioral domains of childhood reflecting either the expression of a
common biological pathway or a common genetic background. The understanding of
the genetic basis of Tourette syndrome is therefore of special importance, because it
may provide useful insights for the study of other developmental disorders. However,
the lack of objective biological markers of clinical manifestation together with a
possible high phenocopy rate, unclear mode of inheritance, incomplete penetrance,
and frequent bilinear transmission of predisposing genes represent major obstacles for
those attempting to elucidate the genetic basis of Tourette syndrome.
The research presented in this document is a result of six years' effort of the author
and her collaborators to generate cytogenetic and molecular genetic data contributing
to a better understanding of genetic and environmental factors affecting the
phenotypic expression of Tourette syndrome. Theoretical and experimental results of
this collaborative effort are assembled in seven articles (four published, three
currently submitted for a publication) and a general introductory section relating to
the problems, methods and methodology described and utilized in data collection for
the individual papers.
Taken as a whole, while the study of chromosome fragile site expression in Tourette
syndrome probands yielded equivocal results leading to a number of rather speculative but interesting interpretations, the results of subsequent molecular genetic
studies are far clearer.
The three most valuable outcomes of these studies for future genetic investigations in
Tourette syndrome gene-mapping efforts in the Afrikaner population, and complex
genetic traits in general, are:
I. The evidence for association/linkage of at least three genomic regions with
Tourette syndrome in the Afrikaner population, with two of the regions (11q23
and 8q22) being suggestively linked to Tourette syndrome by others in different
populations and employing different analytical methods.
2. The evidence for extended background linkage disequilibrium in the general
Afrikaner population (> 5 cM) which further strengthens existing experimental
data demonstrating the suitability of this population for gene-mapping efforts
involving complex traits.
3. The proof based on real rather than computer-simulated data that sequential and
semiparametric methods of analysis could be sufficiently powerful to generate
cumulative evidence for positive linkage with the trait in the regions which
repeatedly yielded both highly significant as well as suggestively significant
disease-marker associations in the initial set of samples.AFRIKAANSE OPSOMMING: Tourettesindroom is 'n algemene oorerflike neurobiologiese probleem wat in verskeie
bevolkingsgroepe vanoor die wereld beskryf is. As gevolg van identiese
fenomenologie en psigopatologie ten spyte van omgewingsverskille, is dit aanduidend
van 'n sterk biologiese grondslag vir die toe stand.
Die teenwoordigheid van kliniese meersoortigheid en die verhoogde voorkoms van 'n
verskeidenheid komorbiede probleme by 'n subgroep van individue met
Tourettesindroom, veroorsaak dikwels probleme met die akkurate identifisering
hiervan. Dit skep egter ook geleenthede vir die bestudering by kinders, van verskeie
neurologiese en gedragsmanifestasies gebaseer op 'n gemene genetiese substraat.
Insig in die genetiese-omgewings wisselwerking by Tourettesindroom baan dus die
weg vir begrip van ander ontwikkelingsprobleme wat ook by kinders aangetref word.
Die afwesigheid van 'n betroubare biologiese merker of merkers vir hierdie kliniese
entiteit, die algemene voorkoms van fenokopiee, komplekse oorerwingspatroon,
onvolledige penetrasie en algemene verskynsel van oorerwing vanaf beide ouers,
verteenwoordig 'n aantal formidabele struikelblokke ten opsigte van die analise van
die genetiese basis van Tourettesindroom.
TS word as een van die komplekse oorerflike toestande beskou, wat beteken dat daar
duidelike oorerflike faktore by betrokke is, maar dat die oorerwing nie-mendelies van
aard is. Die gebruiklike reduksionistiese benaderings wat so suksesvol was vir die
analise van die enkelgeentoestande, werk nie meer onder hierdie omstandighedenie,
en vir die rede word verskeie nie-parametriese of semiparametriese modelle ingespan.
Die gedokumenteerde resultate verteenwoordig die navorsing uitgevoer tesame met
plaaslike en oorsese medewerkers op hierdie gebied gedurende die laaste ses jaar. Die
teoretiese en eksperimentele resultate word weergegee in sewe publikasies.
Hiertydens is sitogenetiese en molekulere gegewens versamel in 'n poging om die
genetiese en omgewingsfaktore onderliggend tot die ekspressie van Tourettesindroom te bepaal. Die teoretiese en eksperimentele resultate van hierdie poging word
weergegee in sewe publikasies, waarvan vier reeds gepubliseer is, en 'n algemene
inleidende afdeling wat die probleme en metodes bespreek soos tydens die
versameling en analise van die data ervaar is.
Die resultate word in twee afdelings aangebied: eerstens is daar die teoretisering ten
opsigte van die bevinding van chromosomale breekbaarheid, wat aangedui is om
verhoog te wees in die Tourette groep. Die betekenis van hierdie bevinding is tans
nog onduidelik, en as gevolg van resolusieverskille nie direk met die DNA bevindings
korreleerbaar nie. Hierdie merkerareas moet egter deurgaans in gedagte gehou word
as moontlik aanwysend van die ligging van kandidaatgene vir Tourettesindroom.
Die belangrikste gedeelte behandel egter die benadering tot die totale genoomsifiing,
sowel as die veilgheidsmaatreels ingebou deur die heranalise van verskeie subgroepe
en gevolglike replisering van resultate.
Die mees waardevolle implikasies van hierdie navorsing ten opsigte van die
uitstippeling van die pad vorentoe vir Tourettesindroom geenkartering by die
Afrikaner, en komplekse oorerflike toestande in die algemeen, sluit die volgende in:
1. Die bewyse gevind vir die bevestiging van 3 genomiese streke soos
oorspronklik deur die eerste fase assosiasiestudies aangetoon by die
manifestering van Tourettesindroom in die Afrikaner, en waar ten minste twee
van die gebiede (11q23 en 8q22) ook deur ander navorsers in ander
bevolkingsgroepe met hierdie toestand gekoppel is;
2. Die kwantifisering van die stand van koppelings-disekwilibrium by 'n aantal
lokusse in die Afrikaner genepoel van < 5cM. Hierdie gegewens versterk die
gedagtes met betrekking tot die geskiktheid van hierdie bevolkingsgroep vir
geenkarteringspogings vir komplekse toestande;
3. Die bewys, gebaseer op reele in stede van gemodelleerde data, dat
opeenvolgende, semiparametriese analisemetodes oor voldoende statistiese
krag beskik om kumulatiewe getuienis te verskaf vir positiewe koppeling van
TS met streke wat ook in die oorspronkilke siektemerker assosiasiestudies
betekenisvolle resultate gelewer het.Doctora
Recommended from our members
Is it Living? Insights from Modeling Event-Oriented, Self-Motivated, Acting,Learning and Conversing Game Agents
No full textA cognitive architecture is presented, which combines insights from artificial intelligence with cognitive psychology,biology, and linguistics. Using a Super Mario clone, we equipped the simulated agents with (i) motivational behavioral systems,(ii) reasoning and planning capabilities, (iii) event-based schema learning and sensorimotor exploration, and (iv) speech com-prehension and generation mechanisms. The motivational system activates goal events to maintain internal homeostasis. Toinvoke selected events, hierarchical action planning and control unfolds both on an event-schematic and a sensorimotor level.Schema learning is based on the detection of event changes, which are not predicted by the basic sensorimotor forward model.Language is comprehended and generated using context-free grammars linked to the schema-based knowledge structure. Thework offers an approach to develop and thus to ground conceptual, semantic world knowledge in sensorimotor interactions andto couple this knowledge with a language to generate and comprehend language about the agent’s virtual world meaningfully
Author Correction: CHD3 helicase domain mutations cause a neurodevelopmental syndrome with macrocephaly and impaired speech and language (Nature Communications, (2018), 9, 1, (4619), 10.1038/s41467-018-06014-6)
No full text\ua9 2019, The Author(s).The HTML and PDF versions of this Article were updated after publication to remove images of one individual from Figure 1
Evidence for 28 genetic disorders discovered by combining healthcare and research data
No full text\ua9 2020, The Author(s), under exclusive licence to Springer Nature Limited.De novo mutations in protein-coding genes are a well-established cause of developmental disorders1. However, genes known to be associated with developmental disorders account for only a minority of the observed excess of such de novo mutations1,2. Here, to identify previously undescribed genes associated with developmental disorders, we integrate healthcare and research exome-sequence data from 31,058 parent–offspring trios of individuals with developmental disorders, and develop a simulation-based statistical test to identify gene-specific enrichment of de novo mutations. We identified 285 genes that were significantly associated with developmental disorders, including 28 that had not previously been robustly associated with developmental disorders. Although we detected more genes associated with developmental disorders, much of the excess of de novo mutations in protein-coding genes remains unaccounted for. Modelling suggests that more than 1,000 genes associated with developmental disorders have not yet been described, many of which are likely to be less penetrant than the currently known genes. Research access to clinical diagnostic datasets will be critical for completing the map of genes associated with developmental disorders
