H2020Индивидуална стипендия2016–2018

LEACON · LEArning-CONtrol tight interaction: a novel approach to robust execution of mobile manipulation tasks

„Хоризонт 2020“ — Действия „Мария Склодовска-Кюри“

Период: 2016-03-07 → 2018-03-06
Финансиране от ЕС: 159 461 €
Участници: 1
Схема: MSCA-IF

Линиите свързват координатора с партньорите.

Накратко на български

Роботите за мобилно манипулиране се обучават да разпознават човешки действия и да използват сензори за допир и зрение, за да се движат в неочаквана среда. Това помага за по-бързото им внедряване в болници, домове и гъвкави производствени линии.

Този кратък обзор е генериран от изкуствен интелект

Кратко обяснение, генерирано от езиков модел по текста на CORDIS. Оригиналът е по-долу.

Резултати накратко

LEArning-CONtrol tight interaction: a novel approach to robust execution of mobile manipulation tasks

One of the main challenges of roboticists in both academia and industry is to take robots out of the factories and let them enter into unstructured environments, such as houses, hospitals, small manufacturers and dangerous area. The scientific objective of the project is to take a step towards the presence of robots in such environments. Currently, there are still important obstacles to the massive diffusion of robotic systems in the fields described above. First of all, programming robots with the classical methods is still too expensive and time-consuming due to intrinsic complexity of manipulation tasks. A second limitation is that planning the robot motion completely off-line may likely bring to a failure of the assigned task, since a high degree of uncertainty is present. Moreover, robots that work in anthropic environments should be able to understand and classify human actions and behaviour for an effective human-robot interaction. In order to tackle these limitations, the LEACON project has the objective to develop a framework that: -allows combining learning and perception-based control to achieve higher robustness -exploits multimodal and crossmodal perception (tactile, proximity, visual, force sensors) to increase the robustness to unforeseen events -allows the robot to recognize human actions A first, shorter-term benefit of having robots with learning capabilities is in agile manufacturing. In such applications, we need flexible production processes and low programming costs. With those technologies, process experts with very limited robot programming skills could re-adapt the assembly line in an faster and much cheaper way. Also, machine laerning for robotics is an enabling technology for applications of the future, such as hospital automation, home automation, automous farming, operations dangerous for humans and human-robot collaboration.

Текст от CORDIS, на английски · Данни: CORDIS, © Европейски съюз

Цел на проекта

One of the main challenges of roboticists is to take robots out of the factories and let them enter into unstructured environments, such as houses, hospitals, small manufacturers and dangerous area.The objective of the project is to take a step towards the presence of robots in such environments.Currently, there are still important obstacles to the massive diffusion of advanced mobile manipulation systems in the fields described above. First of all, programming mobile manipulators with the classical methods is still too expensive and time-consuming due to intrinsic complexity of mobile manipulation tasks.A second limitation is that planning the robot motion completely off-line, as often happens in classical industrial applications, may likely bring to a failure of the assigned task, since a high degree of uncertainty is present and the environment can dynamically change. Such features may cause safety issues for humans potentially present in the workspace and for the external environment itself.In order to tackle these limitations, the LEACON project has the objective to develop a framework that: - allows robots to learn in a real world scenario manipulation skills from human demonstration -exploits multimodal perception (tactile, proximity, visual, force sensors) to increase the robustness to unforeseen events and safety when manipulation tasks are executed. To fulfill such objectives, a multidisciplinary approach that combines machine learning and perception-based control is proposed. The core of the proposed framework will provide two planning levels tightly connected: the high-level and low-level cognitive system.To show the effectiveness of the developed architecture, the main use cases will be constituted by a robot that performs picking, manipulation, and placing operations in a dynamic, unstructured environment in presence of humans in its workspace. At the end of the project, the developed software will be released as open source code.

Оригинален текст от CORDIS (на английски).

Участници

TECHNISCHE UNIVERSITAET MUENCHEN · MuenchenКоординаторГермания