Jobid=622636487615259534 (0.0198)
ppJoin TU Delft and the EU-funded OPERA consortium to develop long-term reasoning and adaptive learning methods for safe, human-aware robot autonomy. /p h3Job description /h3 pAutonomous robots working in human-centered environments must do more than react to immediate sensor input. They need to reason over longer time horizons, adapt to changing tasks and environmental conditions, and update their behavior when new observations become available. In the EU-funded OPERA project, TU Delft contributes to General-Purpose AI for robotics by developing methods that combine fast System 1‑style behavior with more deliberate System 2‑style reasoning, adaptation, and decision‑making. /p pIn this PhD position, you will develop methods for long‑term reasoning and adaptive robot behavior in human‑centered environments. Your research will focus on how robots can use learned models, memory, semantic information, task structure, and uncertainty estimates to make robust decisions over extended time horizons. This directly connects to OPERA’s task on long‑term reasoning in human‑centered environments, which combines adaptive learning, hierarchical reinforcement learning, semantic maps, predictive control, and deliberative planning to support long‑horizon mobile manipulation and human‑centered autonomy. /p pThis project will also address learning for adaptive and robust robot interaction. You will investigate how robots can adapt their behavior in response to human proximity, predicted intent, task context, environmental change, uncertainty, or model mismatch. This may involve reinforcement learning, imitation learning, adaptive control, model learning, state estimation, semantic reasoning, or self‑supervised learning. The focus is on enabling robots to remain safe and effective when operating conditions change, rather than learning policies that only work in a fixed training distribution. /p pYou will work in the Cognitive Robotics Department at TU Delft under the supervision of Prof. Robert Babuška and Dr. Laura Ferranti. You will be embedded in the Reliable Robot Control Lab and contribute to TU Delft’s OPERA work on reliable, adaptive, and trustworthy robot autonomy. /p h3Job requirements /h3 pThe ideal candidate for this PhD position has a strong technical background and is enthusiastic about contributing to safe, intelligent, and adaptive robot autonomy. We welcome applicants from all backgrounds who are motivated to work at the intersection of long term reasoning, learning, and human aware robotic behaviour. /p pYou have: /p ul liA MSc degree in Systems and Control, Computer Science, Applied Mathematics, Robotics, Mechanical Engineering, Artificial Intelligence, or a closely related field. /li liA strong interest in working across multiple research domains, including task level reasoning, control, perception, and machine learning. /li liExcellent programming skills, particularly in Python and/or C++, and experience with modern software development tools. /li liA passion for ground breaking theoretical research combined with an eagerness to test ideas on real robotic systems. /li liStrong analytical and mathematical abilities, enabling you to work confidently with algorithms, optimization, probability, or learning frameworks. /li liExcellent communication skills and proficiency in English (written and verbal), as required for academic publication and international collaboration. /li /ul pYou are particularly encouraged to apply if you have experience in one or more of the following areas: /p ul liReinforcement learning, model‑based RL, hierarchical RL, imitation learning. /li liAdaptive control, learning‑based control, nonlinear system identification, state estimation. /li liLong‑horizon planning, semantic reasoning, memory‑based decision‑making. /li liHuman‑aware robot behaviour, multi‑agent interaction, adaptive interaction strategies. /li liContinual/self‑supervised learning, uncertainty estimation, domain adaptation. /li liReal robot deployment and ROS/ROS2 as a strong plus. /li /ul pAs part of OPERA, you will travel to meet and collaborate with the project’s European partners and attend regular consortium meetings. /p h3Conditions of employment /h3 pDoctoral candidates will be offered a 4‑year period of employment in principle, but in the form of 2 employment contracts. An initial 1.5 year contract with an official go/no go progress assessment within 15 months, followed by an additional contract for the remaining 2.5 years assuming everything goes well and performance requirements are met. /p pAs a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline‑related and research skills. /p pTU Delft offers a customisable compensation package, discounts on health insurance, and a monthly work costs contribution. Flexible work schedules can be arranged. /p pAs part of knowledge security, TU Delft conducts a risk assessment during the recruitment of personnel to help prevent the unwanted transfer of sensitive knowledge and technology. The assessment takes place at the final stages of the selection process and is based on information provided by candidates, such as their motivation letter and CV. /p /p #J-18808-Ljbffr
Deel deze vacature: