ERC Advanced Grant

WhiteMech: White-box Self Programming Mechanisms 

Giuseppe De Giacomo

 

Nov. 1, 2019 - Oct. 31, 2024

 

 

Context. We are witnessing an increasing availability of mechanisms that offer form of programmability. These mechanisms are currently being revolutionized by advancements in sensing (vision, language understanding) and actuation components (autonomous mobile manipulators, automated storage and retrieval systems). However, such mechanisms are held back by the fact that their logic is still based on hard-wired rules encoded in hand-crafted programs.

 

What. WhiteMech aims at developing the science and the tools for mechanisms that are able to program themselves, automatically tailor their behavior so as to achieve desired goals, maintain themselves within safe boundaries in a changing environment, and follow regulations and conventions that evolve over time. Crucially, empowering mechanisms with self-programming carries significant risks and therefore we must be able to balance power with safety. For this reason WhiteMech intends to realize mechanisms that are white-box, that is, whose behavior is at any moment fully analyzable and comprehensible in human terms, and guarded by human oversight. 

 

How. Recent discoveries in Knowledge Representation, Reasoning about Action and Planning, and Reinforcement Learning in Artificial Intelligence, and their connections to Verification and Synthesis in Formal Methods, and Data-Aware Processes in Databases, chart an novel path to produce a breakthrough.

 

Driving Applications. WhiteMech will ground its scientific results upon three driving applications: smart manufacturing (Industry 4.0), smart spaces (IoT) and business process management systems (BPM).

 

 

Positions available as Senior Postdoc, Junior Postdocs and PhD students. Candidates must have strong mathematical and computational skills. Specific topics of interest include but are not limited to:

  • Knowledge Representation
  • Planning
  • Autonomous Agents
  • Reinforcement Learning
  • Logics in AI
  • Temporal Logics
  • Automata
  • Synthesis
  • Logics and Games
  • Monitoring and Verification
  • Data-aware processes
  • Service Composition and Business Process Management
  • Interest in applications in Smart Spaces (IoT) and Smart Manufacturing

 

All the research activities will be carried out at the University of Rome "La Sapienza" (the largest university in Rome). Salaries vary depending on experience and are commensurate to international standards. Moreover generous funds for traveling and visiting scholars are available for the entire project team.

 

Perspective candidates are invited to make an expression of interest by sending an e-mail including a CV and the name of two references to degiacomo@diag.uniroma1.it.