The last three years I gave a lecture series on "Motion Planning" together with Prof. Wolfgang Hönig ( at the @TUBerlin @LIS_TUBerlin. We designed this course almost entirely from scratch to really capture the state of the art in this field, both from a

Content.00:35 Research Goals.01:17 Motivation to do Robotics Research.01:58 Early Life in Dresden.03:20 First Programming Experiences.05:20 From Computer Science to Embedded Systems.06:36 Master Thesis with NVIDIA.07:38 Software Engineer at NVIDIA.09:11 Lessons Learned at NVIDIA.

The global drone market is projected to reach 260 billion USD by 2030. Are you curious about the technology driving this revolution?. I recently sat down with Wolfgang Hönig, professor for multi-robot coordination at the TU Berlin, for an in-depth discussion on the future of

Content.00:37 From Montana to Berlin.01:18 Born in Texas.02:26 First Contact with Computers.03:10 Chemical Engineering and Biotechnology.04:10 Interests in Bioinformatics.05:37 Reservoir Engineering .07:31 Challenges in Reservoir Engineering.11:12 PhD in Computer Science.13:05.

How do you build a robotics company? . Join me in my latest podcast episode, where I talk with Sean Murray, co-founder and director of robotics engineering at Realtime Robotics. Our topics include:. - His past as a chemical engineer.- Motion planning on a chip.- The challenges of

Imagine tiny robots moving through your bloodstream, breaking down blood clots, repairing damaged cells, or delivering targeted drugs to tumor sites. This isn't science fiction---it is the real-world potential of microrobotics, a field on the verge of revolutionizing robotics

Steve M. LaValle is one of the pioneers of robot motion planning. I got the rare opportunity to talk with him in my podcast series on robotics. Topics included his work on the Planning algorithms book, development of the rapidly-exploring random tree algorithm, minimal

Eventually, it was time to part and head back home. This was a really successful meetup and I am excited for the next one. Thank you for reading and consider subscribing to the event page on

Afterwards, @ASieverling presented @realtime_i's new flagship product Resolver Cloud, where you can just upload a robot workcell and get it optimized for collision free paths, optimal robot placements, and execution time. Read more about it here:

Finally, we dug into some delicious pizza from our local pizza joint and continued with some live robot demos. One of our senior application engineers showcased a demo of two robots moving between different welding spots inside of a cluttered box.

The resulting robot system can robustly handle physical puzzles which require longer reasoning into the future, while being robust against failures and interruptions. Check out more of his research here:

By having a more integrated system, he can solve complex physical puzzles with a robot, puzzles which were so far only solvable by animals like cuckoos.

Oussama believes interdisciplinary research is the answer. At the @scioi_cluster he works currently on a tighter integration of planning, control, and perception to push robotics forwards.

So why are we so far behind on those predictions? What is missing to overcome this bottleneck in robotics research to develop truly intelligent robots?

His talk started by listing some bad predictions about robotics of the past century, even by some famous people like Claude Shannon, Herbert Simon, or Marvin Minsky.

Our last speaker was Oussama Zenkri, who is a PhD candidate at @TUBerlin. He talked about some impressive physical puzzle solving abilities of the robots at the @rbolab.

Philipp finally showed some actual gameplay, but the lighting was too dark and he didn't have an adapter to display it on our display. So we mostly played it in our imagination. Still awesome work and a nice display of the FPGA wizardry of the folks over there at Synogate.

With this setup, however, they only got Doom II running with 2 frames per second (fps). To drive the frame rate up, they programmed several custom circuits on the FPGA, replacing slower code segments.

To make Doom II playable, they took the 1997 source code from id software and put it onto a field-programmable gate array (FPGA) circuit. The FPGA circuit is put into an old Gameboy cartridge and has access to the framebuffer of the Gameboy to insert pixels.

The next talk was by Philipp Keydel from the Berlin startup Synogate He presented some pretty crazy work using the @NintendoDE Gameboy to accomplish the age old dream of playing Doom II on it.

However, if you want to try out Rust, you should definitely look into two of Sergei's favorite libraries, cooper-rs and dora-rs. If you are interested in Sergei's other works, check out his website