This guy makes cool stuff and releases the source code.
Ask HN: How do I learn robotics in 2025?
81–90 of 106 posts
Re: Ask HN: How do I learn robotics in 2025?
#82Robotics is a large multidisciplinary area, comprising of parts of ME, EE, and CS fields. Before you go down a particular path, it may be good to step back, and note down things which you actually enjoy doing, and how they might relate to one or more of these fields. After all the drama wears off and you are up late working on something .. it's important to enjoy what you are doing. Not just trying to catch some hype about the next big thing or the tech giants or AI or whatever (or something your friends or parents told you).
The top comment refers to a course around a small mobile robot. Maybe you could go through this, and try to build a bicycle which would balance itself and drive a 100 yards in an empty, safe parking lot. That will certainly involve ME, EE, and CS! Who knows where that might lead?
Re: Ask HN: How do I learn robotics in 2025?
#83Great, you know what you want to make. Go ahead, and do it. Look at projects previous folks have done, see how then can be adapted for your need. If you are interested in getting this One Amazing Thing working, great! You have the motivation and cranking through what you'll need to lean to succeed will be possible.
IF, on the other hand, you want to make 1e6 of these things ("tech giants seems to capture most of the conversation")-- that a completely different story. You're going to need a skilled team, ideally one that has been to a rodeo before. I can't help you there.
But if you're building one, for fun --- Just DO It. Ask friendly robotics club members when you get stuck. IF your problem is particularly and singularly unique, then whatever domain that entails, you will need to master; that's your Secret Sauce.
Ivan Sutherland, who was Thesis Advisor to CMU's first Robotics Institute PhD said something to the effect that after 4 years of a Robotics PhD program, you end up with the ability to solder and attach connectors with a high degree of confidence.
A True Roboticists requires deep knowledge in mathematics, software engineering, mechanical engineering, manufacturing small lots, reliability engineering, materials engineering, data collection & graphical evaluation methodologies..... What one might call a Systems Engineer's handbag. It also helps to be inspired by the wonders of nature that biology affords us.
The details? eh, they change. Whether you used some hot cpu, some hot language, some hot OS --- Marc Raibert's hopping & jumping robots used C and BSD4.3 Unix, with the kernel locks cleaned up (reduced) so a 1 kHz kernel interrupt stream could be supported on a 1 MIPS machine (Vax 780). Timesharing was never stopped, but the kernel did get quite a large percentage of CPU cycles.
I'll repeat: Just do it. Start. Move forward. The project will teach you the questions you must ask.
Re: Ask HN: How do I learn robotics in 2025?
#84If you’re an engineer, go volunteer for a First Robotics team, and advise high schoolers on your area of expertise.
I couldn't agree more. FIRST is an excellent organization to get involved with. Even if you don't have specialities which directly align with the needs of a team, most will not turn you away (especially if you demonstrate passion).
Just a few thoughts about starting a team and/or volunteering:
Starting a FIRST Robotics Competition (FRC) team is not for the feint-of-heart and requires significant time and money investment. This is the sort of endeavor you try when you're either retired or have a group of other dedicated volunteers willing to help you build the team over multiple seasons. If you spend a year or two mentoring/volunteering for a well-established team, you'll get a good sense of what you're getting into. FRC is a bit hardcore.
If no FRC teams exist nearby, FIRST Lego League (FLL) is a good entrypoint, but may not be technical enough for an adult interested in using FIRST to gain exposure to robotics. (It is plenty satisfying to mentor these teams, but Mindstorms can be somewhat limiting.) These are geared toward using Lego Mindstorms for learning robot concepts.
A good middle ground (for exposure to more practical robotics) would be volunteering with a FIRST Tech Challenge (FTC) team. It's the middle ground between FLL and FRC and is _doable_ for a single, dedicated, passionate adult to start (though I'd strongly recommend finding another volunteer to pursue this with).
If getting involved with a team is not an option, seek out nearby FIRST events that you can volunteer at. Many competition events need volunteers and you'll get a chance to interact with local teams and find plenty of opportunities to play with robots.
Re: Ask HN: How do I learn robotics in 2025?
#85Earlier quoted context omitted.
I would say for starting a first robotics lego league is going to be easier to access because they build a smaller robot out of legos, plus the "season" starts in the Fall vs. January for First robotics league. I've coached a First team that has qualified to go to worlds the last four years and been on the Einstein field once in that time. I think you'd learn a few things - robots are built to solve problems and the…
I was thinking I’d love to do that when my son gets older. Any tips for a first time coach?
FIRST and most of its teams are very open to collaborating and supporting rookies new to the org. I recommend reaching out to as many nearby teams as possible and see what support they can provide. Any serious teams are motivated to help as this directly contributes to their team's success during the competitive season. Competitions require a teams to have a pro-social aspect to their operations. Helping other teams is a strong signal in this area.
Additionally, find a nearby FRC competition and volunteer for at least one event (do more, if you can). Wander the robot pit and interact with the teams. There will be a lot of good intel for you there just wandering around and asking questions.
Source: Am volunteer judge for FRC.
Re: Ask HN: How do I learn robotics in 2025?
#86K-Scale Labs: Open-source humanoid robots, built for developers
- https://www.kscale.dev - https://news.ycombinator.com/item?id=44023680
A kernel developer plays with Home Assistant
- Part 1: https://lwn.net/SubscriberLink/1017720/7155ecb9602e9ef2/ - Part 2: https://lwn.net/SubscriberLink/1017945/93d12d28178b372e/ - https://news.ycombinator.com/item?id=44011381
Dutch ingenuity: A brainless soft robot running on air
- https://arstechnica.com/science/2025/05/dutch-scientists-bui... - https://news.ycombinator.com/item?id=43972689
Gemini Robotics
- https://deepmind.google/discover/blog/gemini-robotics-brings... - https://news.ycombinator.com/item?id=43344082
Morphing robot turns challenging terrain to its advantage
- https://actu.epfl.ch/news/morphing-robot-turns-challenging-t... - https://news.ycombinator.com/item?id=43194234
RoboPianist: Dexterous Piano Playing with Deep Reinforcement Learning (2023)
- https://kzakka.com/robopianist/#demo - https://news.ycombinator.com/item?id=43192751
Ask HN: Best way to learn robotics with a 10 year old?
- https://news.ycombinator.com/item?id=41070703
DARPA project reveals one person can control dozens of robots
- https://spectrum.ieee.org/darpa-robot - https://news.ycombinator.com/item?id=43209358
Re: Ask HN: How do I learn robotics in 2025?
#87I was just digging out this Roomba I modded with a Raspberry Pi and camera. I think the cost of that setup was like $40. I meant to get my kids into robotics but they lost interest ... so this cool platform is still sitting around...
Re: Ask HN: How do I learn robotics in 2025?
#88In all honesty I’d try and model a 2d 3-link arm in software with forward and inverse kinematics. Then I’d model the inertia of the bars, and model DC motors to apply a torque to the bar interconnects. I’d then model PID controllers for each motor to smoothly move the arm. I’d then move to 3D. Once the physics is modelled you’ll find speccing the motors, solidworks, motor drivers, and MCUs relatively straightforward…
Snoozefest for anyone looking to get hands-on. Arduino kits can be had for $50 and then 50 lines of c++ will have basic forward kinematics on a ~10 inch arm you can play with in the real world.
Re: Ask HN: How do I learn robotics in 2025?
#89I’ve been playing a bit with toy robots and vision models and I can’t shake the sense that somebody has got to be close to simplifying the control game with high fps cameras. Why are there so many systems to control motors and ground positioning … shouldn’t it all be cameras on the arm figuring out if the motors have positioned the arm correctly and updating to fix?
This is obviously naive and computationally wasteful but I really want to see vision first rebuilds of most control and feedback systems.
Re: Ask HN: How do I learn robotics in 2025?
#90I’ve been playing a bit with toy robots and vision models and I can’t shake the sense that somebody has got to be close to simplifying the control game with high fps cameras. Why are there so many systems to control motors and ground positioning … shouldn’t it all be cameras on the arm figuring out if the motors have positioned the arm correctly and updating to fix? This is obviously naive and computationally wastefu…
Biological analogies are always a bit dodgy, but biology hints that this doesn't work very well. Vision is important, particularly for path planning, but the immediate feedback of proprioception and touch is more important for stability. Think of how hard it is to walk normally when your leg has fallen asleep --- your visual cues remain unchanged, but you lose the immediate feedback loop from your leg. You can do it, but your gait is very unnatural and inefficient.