PhD position: Explainable Artificial Intelligence and Robotics

Application deadline:

"The core of this PhD thesis is the development of explainable machine learning processes at the different levels of a robotic system: decision making, perception and execution. Then, to develop a framework to integrate explanations at different layers into a human-understandable general explanation of the action decision taken during the execution of a manipulation task.

The applicant will work within the European CHIST-ERA project ""COHERENT: COllaborative HiErarchical Robotic ExplaNaTions"". Thanks to this, there will be possibilities to collaborate and even to do short research secondments with our project partners, King’s College London (KCL) in the UK and Università degli Studi di Napoli Federico II (UNINA) in Italy.

IRI is a Joint University Research Institute participated by the Spanish National Research Council (CSIC) and the Technical University of Catalonia (UPC) that conducts research in human-centered robotics and automatic control. The institute, is a key player in the Spanish robotics and automatic control scenes, and a valued participant in a large number of international collaborations including more than ten ongoing H2020 projects and an ERC Advanced Grant. It has been recognized as a Maria de Maeztu Excellence Unit, the main accreditation given by the Spanish Government to research units that stand out for the impact and international relevance of their results.

The position is linked to ""COHERENT: COllaborative HiErarchical Robotic ExplaNaTions"", a CHIST-ERA European project which seeks to improve trust and
reliability in robots by developing a framework capable of generating explanations during a robot action. The idea of the project is to synthesize an explanation from the different explainable machine learning methods that occur at the different robotic layers: decision making, perception and action execution.
XAI is becoming a trending research topic the more society comes to depend on machine learning-based dynamic systems. In the near future, clearer accountability will be required for decision making processes to ensure trust and transparency.  Female candidates are strongly encouraged to apply"