Stud. Assistant (m/f/d) - Learning contact-rich tasks in simulation with GenAI/Foundation models/RL

Job description

Advertisement for the field of study such as: Automation Engineering, Electrical Engineering, Computer Science, Cybernetics, Mechanical Engineering, Mechatronics, Control Engineering, Software Design, Software Engineering, Computer Engineering, Robotics, Autonomous Systems or comparable. Contact-rich tasks in assembly often involve complex physical interactions and high sensitivity to parameter settings. With a large number of product variants, it is not feasible to manually tune or validate process parameters for every possible variant, which limits scalability and flexibility in industrial applications. Simulation environments offer a promising approach to address this challenge. By accurately modeling the underlying physics of assembly operations, it becomes possible to learn generalized representations of these processes. NVIDIA Isaac Sim and other simulation engines like MuJoCo enables high-fidelity physics simulation, sensor emulation for accurately simulating these assembly processes. Reinforcement learning (RL) and modern foundational models can then be leveraged to learn policies and predictive models that capture the dynamics of contact-rich interactions. Be part of change Setup and configuration of physics-based simulation environments (e.g., different simulators and robot models) Modeling and implementation of contact-rich handling and assembly operations in simulation Exploration of generative AI approaches to automatically generate sequences of skills for assembly tasks Investigation of state-of-the-art foundation models for modeling and generalizing assembly operations Design and training of RL-based approaches to learn assembly processes and policies Documentation and presentation of the developed methods and findings What you contribute Valid enrollment at a German university in robotics, computer science, artificial intelligence, or a related field (Required) Practical experience modelling contact-rich interactions with robotics simulation environments such as Isaac Sim, MuJoCo or Bullet (Required) Practical experience working with Retrieval-Augmented Generation (RAG) and generation pipelines, particularly in the context of Large Language Models (LLMs) Experience with robotic manipulators is beneficial Strong programming skills in Python, C++ and experience with ROS (Robot Operating System) Experience with machine learning frameworks in particular PyTorch and reinforcement learning methods Fluent in English What we offer Cutting-edge technology in the field of robotic manipulators Practical work with our robots in Stuttgart Responsibility and freedom to implement your own ideas Collaboration with the best students in their field We value and promote the diversity of our employees' skills and therefore welcome all applications – regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity. Severely disabled persons are given preference in the event of equal suitability. Our tasks are diverse and adaptable – for applicants with disabilities, we work together to find solutions that best promote their abilities. Remuneration according to the general works agreement for employing assistant staff. With its focus on developing key technologies that are vital for the future and enabling the commercial utilization of this work by business and industry, Fraunhofer plays a central role in the innovation process. As a pioneer and catalyst for groundbreaking developments and scientific excellence, Fraunhofer helps shape society now and in the future. Ready for a change? Then apply now and make a difference! Once we have received your online application, you will receive an automatic confirmation of receipt. We will then get back to you as soon as possible and let you know what happens next. Ms. Jennifer Leppich Recruiting Tel. +49 711 970-1415 Fraunhofer Institute for Manufacturing Engineering and Automation IPA Requisition Number: 84165 Application Deadline: