Thesis in Optimizing Robotic Bin-Picking – Pushing and Grasping with Deep Reinforcement Learning

Stellenbezeichnung: Thesis in Optimizing Robotic Bin-Picking – Pushing and Grasping with Deep Reinforcement Learning

Firma: Bosch

Arbeitsort / Location: Tübingen, Baden-Württemberg

Job Beschreibung: Company Description

At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other. Join in and feel the difference.

The Robert Bosch GmbH is looking forward to your application!

Job Description

This Master thesis project proposes a cutting-edge approach to revolutionize robotic bin-picking by combining model-based reinforcement learning with 3D scene rendering techniques. In the realm of industrial automation, robotic bin-picking plays a crucial role in streamlining various processes. However, traditional methods often struggle in dealing with complex and cluttered environments, leading to decreased efficiency. To address these challenges, this thesis project aims to develop an intelligent robotic system that can optimize pushing and grasping actions through model-based reinforcement learning, utilizing 3D scene rendering to enhance perception and decision-making capabilities in dynamic and unpredictable bin-picking scenarios.

  • The primary objective of this Master thesis project is to design and implement a model-based reinforcement learning framework supported by 3D scene rendering techniques for optimal pushing and grasping in robotic bin-picking.
  • The specific goals include a model-based reinforcement learning, to develop a model-based approach that utilizes simulated environments for training. By leveraging learned models of the environment, the robot can plan and optimize its actions more efficiently, even in challenging and unseen scenarios.
  • Evaluate the developed algorithm and compare with baselines on a physical Franka Panda robot. These metrics will measure the success rate, efficiency, and robustness of the robotic bin-picking system.

Qualifications

  • Education: studies in the field of Computer Science, Cybernetics, Mechanical Engineering, Mechatronics, Mathematics or comparable
  • Experience and Knowledge: experience in Python, knowledge in ROS and strong background in AI, machine learning or mathematics are advantages
  • Enthusiasm: motivation for learning and experimenting on physical systems, i.e. robots
  • Languages: fluent in English

Additional Information

Start: according to prior agreement

Duration: 6 months

Requirement for this thesis is the enrollment at university. Please attach your CV, transcript of records, examination regulations and if indicated a valid work and residence permit.

Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore, we welcome all applications, regardless of gender, age, disability, religion, ethnic origin or sexual identity.

Need further information about the job?

Anh Vien Ngo (Business Department)

+49 173 207 7375

#LI-DNI

Gehalts Budget:

Bewerbung:Auf diesen Job bewerben.

Oder lassen Sie sich von Arbeitgebern finden.

Hier Lebenslauf als Gesuch eintragen!