Skip to content

docs: route-staged vs free-drive navigation modes + script pointers - #17

Merged
transfix merged 1 commit into
mainfrom
docs/nav-modes-comparison
Jul 26, 2026
Merged

docs: route-staged vs free-drive navigation modes + script pointers#17
transfix merged 1 commit into
mainfrom
docs/nav-modes-comparison

Conversation

@transfix

Copy link
Copy Markdown
Contributor

Adds a comparison table to docs/training-navigation-on-geometry.md distinguishing the two ways the trained SDF policy drives a real scene — route-staged (A* occupancy spine + learned local control; robust for any A→B) vs free-drive (end-to-end, no route, wall-follow escape, live goal re-targeting) — with pointers to each demo (volrover_grl_snam_austin_learned.py, volrover_grl_snam_austin_freedrive.py, volrover_grl_snam_planner.py) and the offscreen capture_drive_video.py. Docs only.

…inters

Add a 'Two ways to drive' table distinguishing the stagewise A* route + learned
local control (robust, any A->B) from the end-to-end free-drive (no route, wall-
follow escape, live goal re-targeting), with pointers to each demo script and the
offscreen video capture tool.
@transfix
transfix merged commit b5466ae into main Jul 26, 2026
1 check passed
@transfix
transfix deleted the docs/nav-modes-comparison branch July 26, 2026 23:52
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant