Project

APRIL

Multipurpose robotics for mAniPulation of defoRmable materIaLs in manufacturing processes

Multipurpose robotics for mAniPulation of defoRmable materIaLs in manufacturing processes

The APRIL project aims at prototyping low cost and agile market-oriented multipurpose, and easy to repurpose, autonomous dexterous robots; which will manipulate, assemble or process different soft and flexible products/materials in a production line environment. This will enable new ways of automatization (semi- or fully-automatic tasks) in manufacturing lines that produce, assemble or handle different types of flexible or deformable materials (e.g., from pillows to delicate food products). Multi-sensor feedback will be used for robot interaction with their contextual environment, robot manipulation, motion planning, ergonomic enabled human work and safe performance. To underpin robots’ low set-up costs, reduced development effort and faster and scalable deployments, APRIL will transfer learning of many perceptive abilities and skills through easy robot training or repurposing in manufacturing processes at cross-domain level (e.g. food, appliances or passports manufacturing).

To reach this objective, APRIL will develop and build demonstrative robotic prototypes optimized for soft and deformable materials processing in the manufacturing environments; to be validated and tested in the lab, as well as in six different operational manufacturing environments and domains (appliances, food, textile, shoes, electronics and paper/passports), in five countries and in manufacturing industries of different: small (OSAI, ASIN), medium (INES, PEMU) and large (SLVR, INCM). These prototypes will be: (1) safe to deploy around people with no guarding; (2) more skilful and competent at handling different types of soft products while controlling their level of deformation; (3) more able to supervise all additional information of the product (colour, healthy state of food, etc.) during the handling; (4) more adaptable and able to learn in new interactive environments; as well as (5) more capable of being moved from line to line, and job to job, as needed. As a result, APRIL dexterous prototypes will be easily used by manufacturing organizations of any size, country and almost sector; while handling the materials with the minimum deformation; so that less distortion and higher accuracy of manipulation can be achieved. We also foresee these robots to be less expensive to purchase and deploy than pre-programmed caged robots’ setup for one specific task, which means a faster return on investment for their owners.

APRIL will validate and pilot through 6 demonstration use cases specific robotic challenging handling tasks, such pushing small cables, manipulation of highly deformable textiles, or packaging foodstuffs or insoles in transparent packaging materials – which are now mostly done by hand in many countries. The demonstration use cases will also approach the challenge of providing robots that come closer to matching people’s fine motor skills in manipulating materials and small parts, dealing with flexible and soft materials (such as paper or cloth), transparencies (such as packaging materials), specular materials (such as chrome-plated objects) and tiny objects (such as cables or thin flexible circuits).

Partners

  • Universidad Politécnica de Madrid
  • Shadow Robot Company
  • Prensilia s.r.l.
  • Tree Technology S. A.
  • Istituto Italiano di Tecnologia
  • Przemysłowy Instytut Automatyki i Pomiarów
  • Scuola Superiore di Studi Universitari e di Perfezionamento Sant’Anna
  • Asociación de investigación para las industrias del calzado y conexas
  • Kontor 46 s.a.s.
  • Silverline Endustri ve Ticaret A.S.
  • Asociación de Investigación de Industrias Cárnicas del Principado de Asturias
  • Pemu Muanyagipari Zartkoruen Mukodoreszvenytarsasag
  • Osai Automation System SpA
  • Imprensa Nacional - Casa de Moeda, S. A

Sponsors

European Union (EU) – Horizon 2020

European Union (EU) – Horizon 2020

Publications about the project

Alexander Fabisch

In: Journal of Open Source Software (JOSS) Journal of Open Source Software 6 62 Page 3054 6(62), 3054 The Open Journal 6/2021.

To the publication

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz