Master Thesis - Reinforcement Learning for wheeled, bipedal robots

Advertisement for the field of study such as: automation technology, electrical engineering, computer science, cybernetics, aerospace engineering, mechanical engineering, mathematics, mechatronics, physics, control engineering, software design, software engineering, technical computer science or comparable. In the Professional Service Robots - Outdoor research group we develop autonomous, mobile robots for a variety of outdoor applications, such as agriculture, forestry and logistics. The focus is on the development of an autonomous outdoor navigation solution as well as the hardware of the robots. Wheeled, bipedal robots combine the advantages of dynamic walking with efficient wheeled locomotion. Controlling such systems in real-world environments is challenging due to the high-dimensional dynamics, non-linear contact interactions, and varying surface conditions. Reinforcement learning (RL) offers a promising approach to develop adaptive and robust control policies, but training on physical hardware is often impractical and unsafe. Realistic simulation environments are therefore essential. NVIDIA Isaac Sim with Isaac Lab enables high-fidelity physics simulation, sensor emulation, and RL-compatible environments for training and evaluating complex locomotion and navigation behaviours. Was Sie bei uns tun In this thesis, you will design and implement a simulation environment for a wheeled, bipedal robot in NVIDIA Isaac Sim, ensuring realistic physics for hybrid locomotion. You will develop and train RL algorithms for hybrid locomotion tasks, including transitioning between locomotion modes and balancing on uneven terrain. To assess the quality and limitations of the training, you will compare the simulated behaviour with the real-world performance of our internally developed bipedal robot.