Topics & Keywords - CHIST-ERA Conference 2017
Topics of Call 2017
In the Call 2017, to be published in October 2017, two new and hot topics are addressed, namely Object recognition and manipulation by robots and Industrial big data and process modelling for smart factories .
The following topic keywords are given as illustration only. The CHIST-ERA Conference 2017 in Kraków, June 21-23, brings together scientists and CHIST-ERA representatives in order to identify and formulate promising scientific and technological challenges at the frontier of research with a view to refine the scientific content of the call. The conference is open to the research community. The conference website will be open soon.
To register to the CHIST-ERA Conference 2017: http://conference2017.chistera.eu
The short topic descriptions below are provided in view of the conference. The full topic descriptions, to appear in the call text, will result from the conference.
1. Object recognition and manipulation by robots: Data sharing and experiment reproducibility
The ability of recognising objects and manipulating them is central to robotics. Robots should for example be able to recognise objects mentioned by a user and fetch them, or to visually determine if and how an object can be safely grasped. However, despite decades of research, such abilities remain limited in practice. Limiting factors are the lack of large data sets for training robust models for the tasks under study and of objective evaluation protocols to test these models in a reproducible way. A new approach is needed, going beyond the organisation of robotics competitions, whereby robotic perceptions about the surrounding environment and internal states are recorded, annotated with reference information usable to evaluate models, and shared across researchers working on the same task.
Application sectors: Industrial and service robotics
Keywords: Robotics, object recognition, image recognition, artificial vision, visual servoing, grasping, object manipulation, perception through interaction, embodied cognition, machine learning, benchmarking, performance evaluation, experiment reproducibility
2. Industrial big data and process modelling for smart factories
Industry and its production plants are increasingly digitized and the production processes generate increasing amounts of heterogeneous data, from simple sensor data to complex 3D video streams. This opens the way for new intelligent, flexible, network-centric production approaches where parts, products and machines are interconnected across plants, companies and value chains. This evolution is often referred to as the fourth industrial revolution. Most industrial sectors are concerned, including aeronautics, energy, chemical industry, dairy farming and 3D industry, among others.
The goal is to enable production at higher yield, higher quality, lower costs, lower environmental footprint and increased flexibility. For that purpose, intelligent context-aware automation systems should be developed. Such systems should be generic enough to be reusable in various settings. One of the research challenges is to combine a priori knowledge about the processes with learning from data.
Application sectors: Industry, manufacturing, maintenance.
Keywords: Smart industry, cognitive plants, advanced manufacturing, predictive maintenance, process modelling, big data, machine learning
Anticipated Participation of Funding Organisations
The definitive list of the participating funding organisations will be published in the call text in October 2017. The table below provides indications only.
Note that the CHIST-ERA network of funding organisations is open to new members and is growing over time. Only funding organisations belonging to the current CHIST-ERA consortium appear in the table below. Interested researchers in countries not listed below are encouraged to contact their national funding organisation to express their interest.
|The Netherlands||NWO||To be firstname.lastname@example.org|
|Sweden||VR||To be email@example.com|
||EPSRC||To be firstname.lastname@example.org|