SoftGrip Project News & Media

The University of Essex brought SoftGrip to MED 2023

Med2023 2

The 31st Mediterranean Conference on Control and Automation (MED2023) was hosted at the Grand Resort in Limassol, Cyprus, from June 26 – 29, 2023. It included a series of tutorials, workshops and presentations on topics like automation, robotics, control, and intelligent systems. The University of Essex prepared one of the research presentations accepted by the conference about the SoftGrip project. Antonis Porichis, as the principal author, presented the paper “Visual Imitation Learning for robotic fresh mushroom harvesting”. The publication was made possible with contributions from Essex researchers Konstantinos Vasios, Myrto Iglezou, Vishwanathan Mohan and Panagiotis Chatzakos.

The paper and subsequent presentation focused on imitation learning and its potential benefits in enabling complex robotic manipulation tasks like mushroom harvesting. Then, specialised training and long periods of time to master the respective skills could become necessities of the past. The publication presents an end-to-end Imitation Learning pipeline that can be taught how to perform a spectrum of motions from reaching, grasping, twisting, and pulling the mushroom directly from pixel-level information. The approach is tested in a simulated environment.

For the full paper, check the link below:


Website Logo

Scuola Superiore Sant'Anna (SSSA),
The BioRobotics Institute
V.Le R. Piaggio, 34
56025 Pontedera,


Project Management

Project Coordinator
Matteo Cianchetti
Scuola Superiore Sant'Anna (SSSA), The BioRobotics Institute

Project Manager
Martina Maselli
Scuola Superiore Sant'Anna (SSSA), The BioRobotics Institute

Dissemination & Exploitation Manager
Marianna Vari
Twi Ellas Astiki Mi Kerdoskopiki Etaireia

Project Info

Starting date: January 2021
Duration: 36 months
Funding: ~ 3 M€
Coordinator: Scuola Superiore Sant'Anna (SSSA),
The BioRobotics Institute
Partners: 6 from 5 EU countries

Website Logo


This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement N° 101017054