41–50 of 106 posts
If you want to make something, have a look at https://huggingface.co/lerobot For hardware check: https://github.com/TheRobotStudio/SO-ARM100 There will be a world wide hackathon in two weeks time, no better way to get started and get to know some people: https://huggingface.co/LeRobot-worldwide-hackathon
It may sound silly, but I asked Gemini to recommend a learning plan and it came up with a detailed plan along with time estimates in months. The first step is reading and going through all the exercises in Make Electronics (third edition) which is very hands on.
Do this course https://github.com/henki-robotics/robotics_essentials_ros2 Totally free, don't need to buy anything just a computer. I've been designing electrical hardware for robots for the last 4 years for a big corporation and I can tell you, the fun and money is in the software but having another skill is awesome. Robotics is a place where multiple fields converge and if you find a good team they will help you to…
Robotics is a compound discipline which pairs mechanical and electrical engineering knowledge with mathematics and software development. In order to get meaningful practice in all of these areas, I would recommend re-implementing a robot vacuum from 'scratch'.
The actual vacuum part is non-essential, as you're really trying to implement the famous 'turtle' robot and experience all the design steps/compromises/challenges first hand. As a goal, aim for autonomous navigation around your home that works equivalently to a cheap 'throwaway' robo-vac.
Keep in mind you are surrounded by robotics. Most passenger vehicles, consumer drones, micro-mobility devices and modern construction equipment are 'robots in varying degrees of disguise'. Practical knowledge regarding any of these systems transfers well if you know where to apply it.
Do this course https://github.com/henki-robotics/robotics_essentials_ros2 Totally free, don't need to buy anything just a computer. I've been designing electrical hardware for robots for the last 4 years for a big corporation and I can tell you, the fun and money is in the software but having another skill is awesome. Robotics is a place where multiple fields converge and if you find a good team they will help you to…
> the fun and money is in the software This could change if there are breakthroughs in AI, which is not unlikely in the coming few years. Any thoughts on that?
Robotics-oriented ML trivializes current robot design problems: demand for robotics engineers increases, the projects do cooler things but the day-to-day gets less interesting.
Both: this is probably just AGI right?
https://store.steampowered.com/app/573090/Stormworks_Build_a...
The idea of that game is that you build vehicles to do rescues and deal with natural disasters. While there is a career mode where you gain currency that you can spend on parts and fuel, most people who play that game play it in sandbox mode where you essentially design vehicles to do certain things, while also configuring the game to chose missions it generates. For example, you can make it so you only have to deal with land rescue missions or only fight enemy ai.
The building system is VERY in depth. While you don't have to worry about structural strength, you do have to keep things in mind like part placement, CG location, internal volume for buoyancy for ships. Then you get to propulsion, which you have to build out of components - the game has a fairly indepth internal combustion engine simulator where you build custom engines, and have to make sure they are fed with adequate fuel, air, and cooled appropriately. You can do jet engines, you can do nuclear, you can do full electric, and so on.
Then you have to build systems to do missions - for example, to transport a container you have to build a crane to be able to pick it up.
Finally, the game features a microcontroller system which is the bread and butter of doing cool things. There is a bunch of sensors that can read data (GPS, laser distance, pitch, roll, heading, radar, e.t.c), which you can route into a microcontroller, and do math either with logic blocks or Lua code, and thats how you build automation. You will get very familiar with things like PID controller tuning, trigonometry math (for things like distance sensing), state machine coding practices, and other things that are all applicable to the real world.
It's not that hard to get started! I make robots like this (that one's just to enter the wiring stage) using alu extrusion beams, some 3D printing, off-the-shelf servos and SBCs: https://i.imgur.com/9YIHT9P.jpeg Modern SBCs are decently powerful and run for long enough off a standard drone LiPo pack that you can fairly easily build yourself a solid little platform to learn and experiment with different controller app…
1. Start by learning a simulation tool, e.g. Mujoco (open source) or Isaac Sim. 2. Learn basics of optimal control and reinforcement learning, reproduce papers/ideas in the simulation. 3. Get your hands dirty on a cheap robot, and try deploy your trained model on it. For mobility and manipulation. Unitree Go1/Go2 for mobility, and robotic arms for manipulation.
Yet, today, people easily build simple robots using a few rc servos and an Arduino. Somehow kinematics is not really essential if you just want to build simple robotic toys. The pedagogy of robotics courses could have been so much better...
No one here mentioned to get a 3D printer but get a 3D Printer asap.