Emre Ugur

Ph.D.

NEW!

Funded full-time Msc/PhD and postdoc positions in CoLoRs Lab

Baxter
The Robotics Group in Computer Engineering Department, Bogazici University has openings for MSc/PhD students and postdoc researchers. Our group invites applications from students with or expecting BSc/MSc degrees in Computer Engineering or Electrical & Electronics Engineering. The accepted members will be supervised by Assoc. Prof. Dr. Emre Ugur, and funded by our new EU project "INVERSE": INteractive robots that intuitiVely lEarn to inVErt tasks by ReaSoning about their Execution.

The successful candidate will mainly work on

  • Data-driven extraction of neuro-symbolic representations and operators that connect reasoning and low-level perception and control.
The successful candidate will also contribute to the research on one of the following:
  • few-shot retraining for perceptual domain adaptation
  • interpretation of human actions
  • task learning from human observations
  • skill refinement via exploration,
  • planning and monitoring of direct and inverse tasks


The applicants should
  • fulfill the requirements for graduate school application in CMPE at Bogazici University (for MSc and PhD positions),
  • be highly-motivated, enthusiastic, and hard-working with good communication skills,
  • be proficient in programming languages, and also in oral and written English,
  • have strong interest in artificial intelligence, robotics, machine learning

Candidates should send a CV, transcript, and relevant supporting documents with title "[INVERSE Application] (Name) from (Department, University)" to emre[dot]ugur--AT--boun[dot]edu[dot]tr.

  • Duration of funding: 4 years
  • Deadline for application: As soon as possible
  • Start date: February 2024 and July 2024

The INVERSE project aims to provide robots with these essential cognitive abilities by adopting a continual learning approach. After an initial bootstrap phase, used to create initial knowledge from human-level specifications, the robot refines its repertoire by capitalising on its own experience and on human feedback. This experience-driven strategy permits to frame different problems, like performing a task in a different domain, as a problem of fault detection and recovery. Humans have a central role in INVERSE, since their supervision helps limit the complexity of the refinement loop, making the solution suitable for deployment in production scenarios. The effectiveness of developed solutions will be demonstrated in two complementary use cases designed to be a realistic instantiation of the actual work environments. The INVERSE project aims to provide robots with these essential cognitive abilities by adopting a continual learning approach. After an initial bootstrap phase, used to create initial knowledge from human-level specifications, the robot refines its repertoire by capitalising on its own experience and on human feedback. This experience-driven strategy permits to frame different problems, like performing a task in a different domain, as a problem of fault detection and recovery. Humans have a central role in INVERSE, since their supervision helps limit the complexity of the refinement loop, making the solution suitable for deployment in production scenarios. The effectiveness of developed solutions will be demonstrated in two complementary use cases designed to be a realistic instantiation of the actual work environments.