indraneelpatil

Havent seen that, will check it out thank you!

I have been reading "Design of Everyday things" By Don Norman. A friend recommended it to me because I have been trying to learn more about Design thinking and also just get in a habit of not taking things / products around me for granted as they are but noticing the tiny design decisions that someone made, understanding them, questioning them etc..

Aaah interesting, does stuff like this generalise to furniture moving around and different lighting conditions and stuff? Also sounds like if the route gets blocked it just wont move

I dont know any but try this!

https://www.blueprint.am/

Wow this is awesome! Thanks a ton for taking the time to think about the project and post this! Yeah I think the way to go is:

1. Improve the model input by stacking frames 2. Then try model distillation to a smaller model

Wow okay there is a lot here, just so that I understand this correctly:

1. Make a replica of my home/ room in a game engine or a simulator 2. Generate trajectories with RL where the reward is hand specified by me 3. Automate trajectory rewards using some proximity flags

Some stupid questions: 1. How do I build a replica of my home? Is there an SFM algorithm I could use to do this just from camera images? 2. Would this still work even if things/ furniture move around the house? 3. This data collection strategy will have a distribution shift compared to real data so it might struggle with different lighting conditions and stuff?

Very cool! Glad this post inspired someone! Keep me posted if you actually end up building one!

[email protected]

Thanks! Appreciate it!

Very very cool! Thanks for sharing! I'll try it out!

Apart from just detecting obstacles, we wanted to build a robot which is intelligent enough to take in semantic cues like this is a doorway so I can go through it, or this is a kitchen I can clean it this way and so on

Damn thats very cool! Thanks for sharing! I guess we would only need to detect dust somehow which believe it or not is really hard, the camera isnt great quality but I guess this could work for slightly larger debris?

Thanks! Its probably both, too little train data and insufficient quality.

Thats a cool idea, is there any VLM you would suggest? I can think of Gemini maybe? Or any would do?

Yeah agreed 100%, might also need to factor in the cost of the charging dock but the overall thesis is still sound.

Do you know any cheap wifi MCU with a little ML accelerator that we can buy off the shelf? The only one we could think of was the Jetson Orin Nano and thats not cheap

Yeah this would help a lot to collect good trainable data, teleoperating the robot around and collecting large amount of good data is quite hard

200$ is insane, sounds like economies of scale is really working for them

Thank you! We'll check it out! Yeah building a map might be the way to go. With E2E its quite hard to ensure "intelligent" cleaning

Thanks! Our main goal was to build a vacuum which understands semantics inside the house so that it can "clean the kitchen" or "clean the bedroom" so we wanted to do machine learning and since we were doing machine learning we were like why not try to do something E2E instead of first doing SLAM, optical flow etc..