Florian Maurer, M.Sc.

At LIS we want to use the Duckietown hardware and software ecosystem for experimenting with our reinforcement learning based learning classifier tables (LCT) as part of the control system of the Duckiebots: https://www.ce.cit.tum.de/lis/forschung/aktuelle-projekte/duckietown-lab/

More information on Duckietown can be found on https://www.duckietown.org/.

In this student work, we want to enable the use of the GPU in the Lane Detection.
Previous work already experimented with CuPy and CUDA on the NVIDIA Jetson Nano Platform and realized, that they are optimized for PCIe-attached GPUs. In the Jetson Nano, we have a shared memory model, where the GPU shares the main memory with the cpu. Hence, CuPy and co can't enable the complete potential of GPU processing, yet.

Goal of this work is to optimize the GPU usage to benefit from offloading parts of the Lane Detection Alogithm from the CPU and execute them accelerated on the GPU.

• Knowledge about GPU Programming
• Python

LCS, especially XCS, have been shown to be effective for design space exploration.

Recently they have been applied to control problems more often.

Hereby, it's important to consider if the learning is applied online / while execution or offline / before execution.

This seminar should investigate the challenges of employing RL to Real-Time Problems.

- save exploration
- inserting new rules

When we talk about "caches" is's clear, that we talk about dedicated hardware.

But there exist many other types of caching in the context of IT. Just have a look at the search results here: https://scholar.google.de/scholar?q=caching

This seminar should investigate in which contexts computer scientists talk about caching, which purpose it has and what are the HW and SW requirements.

RL is able to play games like Go (https://www.nature.com/articles/nature16961).

But how does it suceed in control?

This seminar should look into how RL engineers are trying to solve control problems: https://arxiv.org/pdf/1806.09460.pdf

At LIS we want to use the Duckietown hardware and software ecosystem for experimenting with our reinforcement learning based learning classifier tables (LCT) as part of the control system of the Duckiebots: https://www.ce.cit.tum.de/lis/forschung/aktuelle-projekte/duckietown-lab/

More information on Duckietown can be found on https://www.duckietown.org/.

In this student work, we want to enable the use of the FPGA in the Lane Detection.
Therefore, we need to port the xdma driver from xilinx from x86 to aarch64, as our Duckiebots run on the NVDIA Jetson Nano Platform (ARM64).
Further, this work should provide a Python wrapper for this driver to use it within Python.

• Knowledge about Linux drivers and PCIe

At LIS we want to use the Duckietown hardware and software ecosystem for experimenting with our reinforcement learning based learning classifier tables (LCT) as part of the control system of the Duckiebots: https://www.ce.cit.tum.de/lis/forschung/aktuelle-projekte/duckietown-lab/

More information on Duckietown can be found on https://www.duckietown.org/.

In this student work, we want to enable the use of the FPGA in the Lane Detection.
Therefore, the different stages of the Lande Detection Pipeline should be ported to FPGA.
In order to comunicate with the NVIDIA Jetson Nano Platform, the ported algorithm has to connect to the XILINX PCIE DMA IP-Core.

• Knowledge about VHDL and Xilinx IP-cores

At LIS we want to use the Duckietown hardware and software ecosystem for experimenting with our reinforcement learning based learning classifier tables (LCT) as part of the control system of the Duckiebots: https://www.ce.cit.tum.de/lis/forschung/aktuelle-projekte/duckietown-lab/

More information on Duckietown can be found on https://www.duckietown.org/.

In this student work, we want to enable the use of the GPU in the Lane Detection.
Previous work already experimented with CuPy and CUDA on the NVIDIA Jetson Nano Platform and realized, that they are optimized for PCIe-attached GPUs. In the Jetson Nano, we have a shared memory model, where the GPU shares the main memory with the cpu. Hence, CuPy and co can't enable the complete potential of GPU processing, yet.

Goal of this work is to optimize the GPU usage to benefit from offloading parts of the Lane Detection Alogithm from the CPU and execute them accelerated on the GPU.

• Knowledge about GPU Programming
• Python

At LIS we want to use the Duckietown hardware and software ecosystem for experimenting with our reinforcement learning based learning classifier tables (LCT) as part of the control system of the Duckiebots: https://www.ce.cit.tum.de/lis/forschung/aktuelle-projekte/duckietown-lab/

More information on Duckietown can be found on https://www.duckietown.org/.

Towards this goal, we need a (followup) working student who is improving the current infrastructure.

Towards this goal, the following three major tasks are necessary:

1. Developping an infrastructure to track and visualize measurement data of the platform (e.g. CPU utilization) as well as the executed application.
2. During this task also the source and periodicity of already provided data should be analyzed.
3. Setting up all Duckiebots incl. all their features and a pipeline to reflash them in case it's needed.
4. FPGA-Extension: Searching for a concept, as well as implementing it.
5. Final goal: demonstration of data exchange between NVIDIA Jetson and FPGA including protocol to specify the type of transfered data

At LIS, we want to use the Duckietown hardware and software ecosystem for experimenting with our reinforcement learning based learning classifier tables (LCTs) as part of the control system of the Duckiebots: https://www.ce.cit.tum.de/lis/forschung/aktuelle-projekte/duckietown-lab/

More information on Duckietown can be found on https://www.duckietown.org/.

Currently, we are developing the infrastructure for our LCT experiments.
While several students are improving on the autonomous driving abilities of the Duckiebots, this work's goal is to develop a system which provides insights into the bots' driving performance.
Therefore, we need objective measurements by a third party which allow us to compare the driving performance (average speed, deviation from optimal line, …) between bots which might run different SW.
To compare specific scenarios, these measurements shouldn't only be a time series, but be enhanced by the position of the respective bot at this point in time. Similar to the modern sports apps: https://www.outdooractive.com/de/route/wanderung/tegernsee-schliersee/auf-dem-prinzenweg-vom-schliersee-an-den-tegernsee/1374189/#dm=1.

Towards this goal it's required to develop a camera-based mechanism, which identifies bots in the field, extracts their concrete position and calculates certain metrics like direction, velocity, on / off lane, spinning, deviation from ideal line, ….
This data then should be logged to be analyzed + visualized later.

Depending on the type of work (BA/FP vs MA) this work might include to enhance these measurements with internal data of the bots to compare internal and external perception, and to develop tools for easy analysis.

• independent work style
• problem solving skills
• computer vision knowledge (openCV)
• programming skills (we are open which framework is used - Python, C++ (Qt), Matlab, ...
• Linux basics (permissions)

When we talk about "caches" is's clear, that we talk about dedicated hardware.

But there exist many other types of caching in the context of IT. Just have a look at the search results here: https://scholar.google.de/scholar?q=caching

This seminar should investigate in which contexts computer scientists talk about caching, which purpose it has and what are the HW and SW requirements.

Although its age, cache coherency is part of lots of ongoing research.

With the developement of Network on Chips (NoCs) to place more CPUs on a single compute node directory based coherency protocols got used more.

This seminar should look at coherency beyond the scope of single compute nodes (chips) using NOCs, but at interconnected compute nodes.
A first idea for coherency between connected compute nodes was developed already in the 90s: https://ieeexplore.ieee.org/document/6182605

Starting from there, we want to see which developement was in this topic and which types of architectures were targeted.

At LIS we want to use the Duckietown hardware and software ecosystem for experimenting with our reinforcement learning based learning classifier tables (LCT) as part of the control system of the Duckiebots: https://www.ce.cit.tum.de/lis/forschung/aktuelle-projekte/duckietown-lab/

More information on Duckietown can be found on https://www.duckietown.org/.

In this student work, we want to improve single stages of the image processing pipeline.
A first step is to analyse the image processing pipeline.
Afterwards the one with the biggest bottleneck in terms of functional accuracy or computation is selected to be optimized according to state of the art methods (literature research required).
Finally, the improvements should be measured and compared to before.