Community Research and Development Information Service - CORDIS

H2020

SoMa Report Summary

Project ID: 645599
Funded under: H2020-EU.2.1.1.5.

Periodic Reporting for period 1 - SoMa (Soft-bodied intelligence for Manipulation)

Reporting period: 2015-05-01 to 2016-10-31

Summary of the context and overall objectives of the project

Soma explores a new avenue of robotic manipulation with the environment, as opposed to manipulation of or in the environment.
In our approach, the physical constraints imposed by objects in the environment and the manipulandum itself are not regarded as obstacles, but rather as opportunities to guide functional hand pre-shaping, adaptive grasping, and affordance-guided manipulation of objects. The exploitation of these opportunities, which we refer to as environmental constraints (EC), enables robust grasping and manipulation in dynamic, open, and highly variable environments.

The key ingredient for the exploitation of EC is softness of hands, i.e. their embodied ability to comply and adapt to features of the environment.
The traditional paradigm for robotic manipulation is in complete disarray in front of this shift of focus: state-of-the-art grasp planners are targeted towards rigid hands and objects, and attempt to find algorithmic solutions to inherently complex, often ill-posed problems.
Further complicating matters, the requirement of planning for soft, uncertain interactions between hand and environment is entirely beyond the state of the art. However, this is how humans most often use their hands, and how we plan to change robotic manipulation.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

WP1 Human Grasping and Manipulation:
We created a taxonomy based on human grasping trials and the idea of environmental constraint exploitation. We gathered preliminary evidence on the existence of coordinated stiffening patterns in the human hand.

WP2 Hand Design: We developed simulation infrastructure to speed up the hand design and enable automated optimization of soft hands design and ECE primitives.
We designed several new hands and fingers, among which the Pisa/IIT SoftHand 2 that won the Best Paper Award at Humanoids 2015.

WP3 Hand Control: We developed a new modeling framework that takes into account underactuation and compliance at different levels. We developed a haptically guided reflex controller to regulate the motion and stiffness of the Pisa/IIT hand during grasping.

WP4 Grasp and Manipulation Planning:
We developed a preliminary planner to sequence environmental constraint exploitation from visual input. We designed grasp reflex primitives based on human grasping experiments.

WP5 Use Case in Commercial Food Handling:
We analyzed the requirements for the design of soft hands for handling fruit and vegetables.
We performed first automated grasping experiments with the Soma hands and two different robotic arms feeding back results.

WP6 Use Case in Human/Robot Co-Working Environment:
We have developed test metrics and evaluated \soma hands both with quantitative tests and in a user study. Design feedback has been provided to project partners, which has led to the development of the first Disney-RBO hand.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

Scientific and Industrial Objectives: Soma will design capable soft hands for the versatile and competent exploitation of EC. Soma will develop control methodology tailored to these hands. And Soma will devise approaches for perception and planning Soft Manipulation in dynamic, real-world environments. Taken together, these components deliver versatile, robust, cost-effective, and safe robotic grasping and manipulation capabilities.
Soma will apply the developed technologies to an open manipulation problem in the food and agriculture industry: the handling of irregularly shaped, flexible, and easily damageable goods, such as fruit and vegetables.

Related information

Record Number: 198117 / Last updated on: 2017-05-17
Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top