PhD – Hybrid and Geometric Optimization for Robotics
- Robert-Bosch-Campus 1, 71272 Renningen, Germany
- Legal Entity: Robert Bosch GmbH
Do you want beneficial technologies being shaped by your ideas? Whether in the areas of mobility solutions, consumer goods, industrial technology or energy and building technology – with us, you will have the chance to improve quality of life all across the globe. Welcome to Bosch.
The Robert Bosch GmbH s looking forward to your application!
Hybrid and geometric optimization refers to the general domain of optimization under hybrid and geometric constraints, where hybrid constraints refer to discrete decisions such as which machine to use and which object to manipulate and where geometric constraints refer to physical limitations that are inherent to the system such as machine models and robot dynamics. Such optimization problems have a broad range of potential applications such as automated assembly, bin packing/picking and coordination or scheduling of multi-robot systems. Nonetheless, most common solution is to treat each constraint separately and sequentially, which is not only sub-optimal but also often error-prone as the compatibility between these two constraints are not guaranteed. Instead, the joint and simultaneous optimization of these constraints can improve both aspects.
There are currently two directions to explore:
On the one hand, multi-bound tree search (MBTS) as proposed in , which can be potentially used to significantly reduce the search space by introducing simpler and faster pruning criteria. On the other hand, learning of search heuristic as proposed in , which trains a search policy by solving numerous problems offline thus improving online solution time. Both methods have shown great potential to various robotic applications. This PhD project aims to develop these concepts further and highlights their advantages in industrial settings.
During this project, you are expected to not only produce top-tier scientific publications but also implement high-quality software. Another strong flavor of research at Bosch is that scientific discoveries are tested rigorously through hardware experiments on robotic platforms at the Bosch research campus.
 M. Toussaint et. al. Differentiable Physics and Stable Modes for Tool-Use and Manipulation Planning. RSS2018.
 M Spies et. al. Bounded Suboptimal Search with Learned Heuristics for Multi-Agent Systems, AAAI2019.
- Education: Master’s degree in electric engineering or computer science or related subjects
- Personality and Working Practice: highly motivated, proactive, goal-oriented and ability to work independently as well as within a team
- Experience and Knowledge: Strong background in mathematic modelling of robotic physical systems, good knowledge in automatic control and electric engineering or computer science, experience in simulation of dynamic systems and excellent programming experience. Knowing Robot Operating System (ROS) is a plus
The final PhD topic is subject to your university. Duration: 3 years
Please submit all relevant documents (incl. cover letter, curriculum vitae, study transcripts, links to past projects such as codebase or publications).
Apply now in just 3 minutes!
Are you interested in working from home, or part-time? Please don't hesitate to ask us.
Need support during your application?
Kevin Heiner (Human Resources)
+49 711 811 48749
Need further information about the job?
Meng Guo (Functional Department)
+49 711 811 13815