0 evaluări0% au considerat acest document util (0 voturi)
19 vizualizări4 pagini
This document discusses two research institutions and some of their projects. It provides information on projects from the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) related to humanoid robotics planning and object search. It also discusses projects from a Colombian software research institution (IDIS) focused on collaborative process improvement and monitoring collaborative processes using information technologies.
Descriere originală:
Metodologia Agil de Invetigación.
Empresas que desarrollan software.
This document discusses two research institutions and some of their projects. It provides information on projects from the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) related to humanoid robotics planning and object search. It also discusses projects from a Colombian software research institution (IDIS) focused on collaborative process improvement and monitoring collaborative processes using information technologies.
This document discusses two research institutions and some of their projects. It provides information on projects from the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) related to humanoid robotics planning and object search. It also discusses projects from a Colombian software research institution (IDIS) focused on collaborative process improvement and monitoring collaborative processes using information technologies.
Nombre Institucin /Nombre Grupos-Centros-Laboratorios
Dos proyectos de inters
Humanoid Manipulation Planning using Backward-Forward Search This paper explores combining task and manipulation planning for humanoid robots. Existing methods tend to either take prohibitively long to compute for humanoids or artificially limit the physical capabilities of the humanoid platform by restricting the robots actions to predetermined trajectories. We present a hybrid planning system which is able to scale well for complex tasks without relying on predetermined robot actions. Our system utilizes the hybrid backward- forward planning algorithm for high-level task planning combined with humanoid primitives for standing and walking motion planning. These primitives are designed to be efficiently computable during planning, despite the large amount of complexity present in humanoid robots, while still informing the task planner of the geometric constraints present in the problem. Our experiments apply our method to simulated pick-and-place problems with additional gate constraints impacting navigation using the DRC-HUBO1 robot. Our system is able to solve puzzle-like problems on a humanoid within a matter of minutes. Referencia: http://lis.csail.mit.edu/pubs/grey-iros16.pdf
Manipulation-based Active Search for Occluded Objects
Object search is an integral part of daily life, and in the quest for competent mobile manipulation robots it is an unavoidable problem. Previous approaches focus on cases where objects are in unknown rooms but lying out in the open, which transforms object search into active visual search. However, in real life, objects may be in the back of cupboards occluded by other objects, instead of conveniently on a table by themselves. Extending search to occluded objects requires a more precise model and tighter integration with manipulation. We present a novel generative model for representing container contents by using object co-occurrence information and spatial constraints. Given a target object, a planner uses the model to guide an agent to explore containers where the target is likely, potentially needing to move occluding objects to enable further perception. We demonstrate the model on simulated domains and a detailed simulation involving a PR2 robot. Referencia: http://lis.csail.mit.edu/pubs/tlp/ICRA13_1782_FI.pdf Dos publicaciones cientficas en revistas (de inters). Project-based, Collaborative, Algorithmic Robotics for High School Students: Programming Self-driving Race Cars at MIT We describe the pedagogy behind the MIT Beaver Works Summer Institute Robotics Program, a new high-school STEM program in robotics. The program utilizes state-of-the-art sensors and embedded computers for mobile robotics. These components are carried on an exciting 1/10-scale race-car platform. The program has three salient, distinguishing features: (i) it focuses on robotics software systems: the students design and build robotics software towards real- world applications, without being distracted by hardware issues; (ii) it champions project-based learning: the students learn through weekly project assignments and a final course challenge; (iii) the learning is implemented in a collaborative fashion: the students learn the basics of collaboration and technical communication in lectures, and they work in teams to design and implement their software systems. The program was offered as a fourweek residential program at MIT in the summer of 2016. In this paper, we provide the details of this new program, its teaching objectives, and its results. We also briefly discuss future directions and opportunities. Referencia: http://lis.csail.mit.edu/pubs/anders-isec-17.pdf
Searching for Physical Objects in Partially Known Environments
We address the problem of a mobile manipulation robot searching for an object in a cluttered domain that is populated with an unknown number of objects in an unknown arrangement. The robot must move around its environment, looking in containers, moving occluding objects to improve its view, and reasoning about collocation of objects of different types, all in service of finding a desired object. The key contribution in reasoning is a Markov-chain Monte Carlo (MCMC) method for drawing samples of the arrangements of objects in an occluded container, conditioned on previous observations of other objects as well as spatial constraints. The key contribution in planning is a receding-horizon forward search in the space of distributions over arrangements (including number and type) of objects in the domain; to maintain tractability the search is formulated in a model that abstracts both the observations and actions available to the robot. The strategy is shown empirically to improve upon a baseline systematic search strategy, and sometimes outperforms a method from previous work. Referencia: http://lis.csail.mit.edu/pubs/nie-icra2016-search.pdf Nombre Institucin /Nombre Grupos-Centros-Laboratorios
Dos proyectos de inters
Un Oleoducto para Generar Etiquetas de Verdad en Tierra para
Datos de RGB {RGBD} de Escenas Estorbadas
Se ha demostrado que las arquitecturas de redes neuronales
profundas (DNN) superan a las tuberas tradicionales para la segmentacin de objetos y plantean la estimacin utilizando datos RGBD, pero el rendimiento de estos oleoductos DNN est directamente relacionado con la representatividad de los datos de entrenamiento de los datos verdaderos. Por lo tanto, un requisito clave para emplear estos mtodos en la prctica es tener un conjunto grande de datos etiquetados para su tarea de manipulacin robtica especfica, requisito que generalmente no es satisfecho por conjuntos de datos existentes. En este artculo desarrollamos una tubera para generar rpidamente datos RGBD de alta calidad con etiquetas en forma de pxeles y poses de objetos. Utilizamos una cmara RGBD para recopilar vdeo de una escena desde mltiples puntos de vista y aprovechar las tcnicas de reconstruccin existentes para producir una reconstruccin 3D densa. Etiquetar la reconstruccin en 3D utilizando un humano asistido ICP-montaje de mallas de objetos. Al reprojectar los resultados del etiquetado de la escena 3D podemos producir etiquetas para cada imagen RGBD de la escena. Este oleoducto nos permiti recolectar ms de 1.000.000 de ejemplares de objetos etiquetados en pocos das. Utilizamos este conjunto de datos para responder a las preguntas relacionadas con la cantidad de datos de formacin que se requiere, y de qu calidad deben ser los datos, para lograr un alto rendimiento de una arquitectura DNN. NACIONALES
Nombre Institucin /Nombre Grupos-Centros-Laboratorios
Estrategia Digital SIMASCOACH Imaginatio, desarrolla una estrategia completa de posicionamiento digital, en la que se incluye el diseo e implementacin de un sitio web dinmico, moderno, claro y sencillo, adems de implementar una estrategia en redes sociales tales como; Twitter, Facebook, Youtube y LinkedIN, generando comunidad en cada una de ellas y posicionando los productos y servicios que Si+Coach presenta.
LOCALES
Nombre Institucin /Nombre Grupos-Centros-Laboratorios
Entorno Colaborativo de Apoyo a la Mejora de Procesos para la Industria de Software Colombiana Entorno Basado en Tecnologas de la Informacin y las Comunicaciones (TICs) para monotorizar y analizar los procesos colaborativos.
ChatGPT Money Machine 2024 - The Ultimate Chatbot Cheat Sheet to Go From Clueless Noob to Prompt Prodigy Fast! Complete AI Beginner’s Course to Catch the GPT Gold Rush Before It Leaves You Behind
ChatGPT Side Hustles 2024 - Unlock the Digital Goldmine and Get AI Working for You Fast with More Than 85 Side Hustle Ideas to Boost Passive Income, Create New Cash Flow, and Get Ahead of the Curve
ChatGPT Millionaire 2024 - Bot-Driven Side Hustles, Prompt Engineering Shortcut Secrets, and Automated Income Streams that Print Money While You Sleep. The Ultimate Beginner’s Guide for AI Business