• Emerging paradigms for robotic manipulation:
    from the lab to the productive world

    Previous Events

Full day Workshop at Robotics Science and Systems 2019, Freiburg

Abstract: Novel robotic developments are going hand in hand with the need for innovation in manufacturing and service applications. Large industries need increasingly fast adapting production lines, while SMEs are adopting collaborative robots to gain a competitive edge in global markets. Additionally, an increasing number of companies are producing and using service robots. In this emerging framework, robots should be able to grasp and manipulate different tools, and interact with fast changing or even unstructured environments involving human users or co-workers. Therefore, these new “real-world” scenarios require innovative grasping and manipulation paradigms that can cope with the needs of uncertain environments. Solutions are being proposed to deal with this challenge, including soft manipulation, AI-driven grasp planning, and human-robot collaborative manipulation. This workshop will bring together research experts as well as representatives of companies to discuss how new approaches in the field can efficiently be transferred from the research labs to the productive world.

Organizers:
Maria Pozzi, Virginia Ruiz Garate, Maximo Roa
Speakers:
  • Júlia Borràs Sol (CSIC-UPC) - Robot manipulation of textile objects
  • Robert Platt (Northeastern University) - Deictic action abstractions for robotic manipulation
  • Gionata Salvietti (University of Siena) - Design and modeling of novel robotic soft devices for grasping and manipulation
  • Hussein Mnyusiwalla (OCADO Technology) - Benchmarking for Next-Gen Warehouses: Evaluation of Soft Manipulation Solutions
  • Hilario Tomé (PAL Robotics) - Humanoid robots manipulating in domestic and industrial scenarios: PAL Robotics experience
  • Leonel Rozo (Bosch BCAI)
  • Dominik Bösl (Festo AG & Co. KG)
  • Accepted Posters:
  • Online Learning of Feed-Forward Models for Variable Impedance Control in Manipulation Tasks - Michael J Mathew [Winner of the Poster Award]
  • Effects of Coupled Parallel Compliance on Maximizing Achievable Controller Stiffness Range - Mincheol Kim
  • Inferring Occluded Geometry Improves Performance when Retrieving an Object from Dense Clutter - Andrew Price
  • Practical Robot Learning from Demonstrations using Deep End-to-End Training - Akansel Cosgun
  • Integrating Deep Learning and Hand Modelling for Grasp Planning with Robotic Soft Hands - Sara Marullo
  • Learning Precise Peg-in-hole Assembly from demonstration - Xiao Gao
  • IEEE RA-M Special Issue:
    Based on the workshop outcomes, we decided to propose a Special Issue to IEEE Robotics & Automation Magazine to collect works demonstrating how new technologies and results in robotic manipulation can be applied in real-world scenarios. More details on the SI can be found here.
    Acknowledgements:
    We gratefully acknowledge the funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 645599 (SoMa) and No. 688857 (SoftPro).