Smart mapping for robots exploring huge areas! 🗺️
@lukas_m_ziegler66K followers
15,730 views
8 Comments
Comments from the original post on X (Twitter)

@fomo_feed
Rolling-Bonxai trades full-map RAM for disk I/O latency on reloads. That mirrors the sim-to-real transfer bet I wrote about last month. The real test is whether chunk swaps stay fast enough for continuous locomotion.
2 likes

@cspaliwa1
Where do you keep on finding banger upon banger codes and papers in robotics? Do you taste like the sauce because you are dipped in the sauce? Or is it because you know where to find the best sauce?
1 like

@DamirWallener
Chunked voxel grid. Watch for… - boundaries -> thrashing -> planning stalls - integration errors -> drift -> can’t find right chunks - map fragmentation -> loop closure -> ghosting - alt/range est. errors -> scale drift -> matching failures It’s simple until it meets the real world. 🙂

@MendysRobotics
Sliding-window maps are the pragmatic answer for warehouse-scale AMRs too - you rarely need the full global map in RAM, just local occupancy plus anchors for loop closure. Curious how Rolling-Bonxai handles loop closure corrections once old chunks are already on disk.

@joemeno
@facontidavide check this out

@geospatialfm
That’s what they’ve always done with computer games

@WanderingDuck7
Your data is too dense. If the space is rectilinear just use a line and width and height.

@JohannesTscharn
Quite interesting how we developed solutions to these kinds of problems in video games.
