Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Launch HN: Flywheel (YC S25) – Waymo for Excavators

news.ycombinator.com

Post reply on HN
Print view View original

81–82 of 82 posts

Re: Launch HN: Flywheel (YC S25) – Waymo for Excavators

#81

Post by jasongill »

jashmota wrote: post #76
jasongill wrote: post #69

Earlier quoted context omitted.

I disagree - your AI model should be decoupled from your control logic; so if the model determines that you need to move the boom, your control logic takes that action - either via hydraulic retrofit, canbus control, or just faking it in a simulator, and the AI model observes and reacts to the change as a result of that action. So in reality, CANbus control should be no different than hydraulic control to your system…

I totally agree, what I meant was if we only do CANbus retrofit, we would really limit ourselves in how compatible we are. So we have to focus on doing the right kind of retrofit really well. CANbus retrofit is easier and we've done that many times before. Especially because my cofounder Mahimana used to work in self-driving company and worked on this and single-handedly built out their current ML data and eval pipel…

awesome, sounds like you guys are on the path to success already! can't wait to see how things turn out

Re: Launch HN: Flywheel (YC S25) – Waymo for Excavators

#82

Post by aorloff »

jashmota wrote: post #77
aorloff wrote: post #60

I would create a bespoke training set from the very best operator you can find, after significant interviewing, and then only use that to train your model (eg. partner with a local firm that rents at Herc or United Rentals a lot and has a skilled operator and train on their jobs while you rent them free equipment). The range of skillset on these things is large, there are 2 dominant (fairly swappable - meaning most m…

This is a great idea - I would dig into this. I disagree on AI not winning here. Support crew mostly work on eliminating blindspots for operator. Yes you can eliminate blindspots with cameras and a 7inch TFT screen, but those are small, don't work great in direct sunlight. The current solution not being 10x better is why they still fallback to having those crew members. I genuinely believe we will change that.

So if you just built the blind spot detection for the rig and offered that it probably would be enough product
Post reply on HN