TransLearn 2019: Workshop on Robot Skill Transfer from Simulation to Real World Deployment in Manufacturing Industries and Warehouses

Индия, Нью-Дели

14 октября18 октября 2019

Форма участия: Очная

Срок подачи заявок: 15.07.2019

Организаторы: KUKA

Контактное лицо: Daniel Braun, KUKA

emal: [email protected]

Повысить рейтинг

Повышение рейтинга дает возможность оставаться объявлению в топе на главной странице, а также на страницах городов, тематик, связанных с объявлением.

Текущее значение: 0

Industry 4.0 will be driven by two main technologies: AI and Robotics — and especially the combination of both — allowing robots to learn skills and tasks without explicitly programming them. Data-driven machine learning (particularly, Reinforcement Learning) algorithms offer untapped potential for significantly reducing robot programming cost, optimizing robot movements and the making new robot applications viable. Current reinforcement learning algorithms, however, require a lot of data to learn complex industrial tasks. The generation of this data by real robots is very cost-intensive and time-consuming. Simulations are attractive environments for training robots as they provide an abundant source of cheap, scalable and safe data. On the other hand, behaviors developed by agents in the simulation are often specific to the characteristics of the simulator, and physics simulators do not reflect the physical world sufficiently well. Due to modeling errors strategies that are successful in the simulation may not transfer to their real-world counterparts («reality gap»).

This workshop is named after an Indo-German research project ‘TransLearn’ which addresses the above-mentioned theme. We invite authors to submit papers relevant to this theme. The aim of this workshop is to discuss and share ideas in relation to the ‘TransLearn’ project and transfer learning in general, between robot and machine learning researchers on the one hand and manufacturing and warehouse automation practitioners on the other. Particular objectives of this workshop are to:

  • Develop a community of researchers working on learning robot skills and tasks in industrial applications
  • Discuss the current state of the art and future directions of bridging the gap between simulation and reality in robotic manipulation
  • Provide for collaboration opportunities

Смотреть похожие мероприятия

Shopping Cart