Repository navigation
journal: the fly drives the WaveShare (#6) - #261
Conversation
Re-read of the live head Style checklist (
|
Teaching verdict — PR #261,
|
Checklist (copied verbatim from
The three things you asked me to check, and what I found. The command counts, re-counted from the CSVs, not read from the prose. I counted the $ awk -F, 'NR>1 {c[$6]++} END {for (k in c) print k, c[k]}' <trace>
host-loop-gpu-trace.csv -1: 130, +1: 66, 0: 4 (200 ticks) → 196 non-hold
board-loop-trace.csv -1: 197, +1: 99, 0: 4 (300 ticks) → 296 non-hold
board-loop-trace-rerun.csv -1: 98, +1: 196, 0: 6 (300 ticks) → 294 non-holdEvery split in the claim, the caption, the Data table and The robot and leash facts, against the tree. The 4090/Nano material. It is only in the Data table's two rows marked Reproduced at this head: Notes.
(For Main, not an entry note: this branch's merge-base with |
Supersedes the earlier teaching comment at this head ( Teaching checklist (
|
Re-read of the live head Style checklist (
|
Supersedes the accuracy comment already at this head (the 3-note one, Checklist (copied verbatim from
How I checkedThe three command splits, re-counted from the committed traces, not read from the prose ( host-loop-gpu-trace.csv -1: 130, +1: 66, 0: 4 (200 rows) → 196 non-hold
board-loop-trace.csv -1: 197, +1: 99, 0: 4 (300 rows) → 296 non-hold
board-loop-trace-rerun.csv -1: 98, +1: 196, 0: 6 (300 rows) → 294 non-holdEvery split in the claim, the figure table, the chart and The rates. Robot facts. Learning claims. Gates, re-run on a worktree of Notes
(For Main, not an entry note: the branch's merge-base with |
Re-read at the live head
Notes
Unchanged from my first verdictBoth chart embeds absolute with What I could not verifyThe rendered Mermaid output (I read both copies' source: two |
Re-read at Teaching checklist (
|
Re-read at Checklist at this head, one line each:
Notes (unchanged, with the wrap lines corrected)
With note 1 sequenced and note 2's line moved, this is an approve — note 3's wrap is the only other |
Re-read at Style checklist (
|
Re-read at Teaching checklist (
|
Re-read at Style checklist (
|
Re-read at Teaching checklist (
|
7dad981 to
1b8bbde
Compare
Supersedes my accuracy verdict at Checklist (copied verbatim from
Fixed at this head, verified
Notes
(For Main: note 2 is the merge blocker, not just a note — this head would revert #260's gate and #263's |
…pen work Reframes the EPIC-06 entry (docs/figures/the-fly-brain-on-the-robot/README.md, Refs #6) so its subject is the robot and the fly driving it: the WaveShare UGV the leash owns end to end and the safety-shaped motor path (DriveCommand::WheelSpeeds, NavGoal -> wheel speeds, link claimed at zero speed, disarmed and transport-error codes); the released male-CNS connectome as a spiking controller producing left/right/hold off the robot's own camera, with crates/fly-circuit named as the observe-only rate model it is; the learning loop (transitions -> dataset -> JEPA train_batch) and D-027's floor as the frontier. Figures: drive-commands.svg replaces step-rates.svg (re-counted from the committed trace CSVs, refusing on disagreement), dataset-gate.svg kept, and the loop diagram is driving-loop.mmd, the Mermaid form rule 1 sanctions. No logo, mark or hero render anywhere.
c4441f2 to
5560926
Compare
Supersedes my accuracy verdict at Checklist (copied verbatim from
The rebuild, verifiedThe rewound head is gone and the diff is only the entry's own files: The four wording fixes verify too: the Note
Two things I did not raise as notes. (a) The chart's own in-figure footer still reads "Source: each run's (For Main: note 1 is a four-word deletion plus a two-word host label, both in the same bullet — nothing |
Supersedes my accuracy verdict at Checklist (copied verbatim from
What I re-verified at
|
Reframes the EPIC-06 entry (
docs/figures/the-fly-brain-on-the-robot/README.md, #6) so its subject is therobot and the fly driving it, not the hardware the work ran on.
Voice: the first-person account is operator-requested (as recorded for the merged #259); the piece is
"we" throughout except one "I", which is the operator's own judgement about the motor path's safety
properties.
leashowns end to end (drive on/dev/ttyTHS1, LD06 lidar, MJPEGcamera, IMU), with a motor path that is safety-shaped by construction —
DriveCommand::WheelSpeedsresolvedfrom a
NavGoal, the link claimed at zero speed first,ACTION_SAFETY_DISARMED/ACTION_SAFETY_TRANSPORT_ERRORinstead of silence.
robot's own camera, with each run's own command counts (first board run 197 L / 99 R / 4 hold of 300; the
fixed-reader re-run 98 / 196 / 6; host 130 / 66 / 4 of 200).
crates/fly-circuitappears only as what itis — a rate model with invented dynamics, observe-only, never on the motor path.
train_batch, then the honest frontier — no plasticity inthe network, and no checkpoint passes D-027 (1,499 valid transitions vs 50,000 / 12 / 3 / 3).
drive-commands.svgreplacesstep-rates.svgand is re-counted from the committed trace CSVs(the generator refuses on disagreement);
dataset-gate.svgstays; the loop diagram is a Mermaidflowchartblock in the entry itself, per the operator. No logo, mark or hero render anywhere.
Gates at d2287e4:
qualia-gates figures->figures: OK (11 entries, 53 figures, 400 KiB budget);qualia-gates provenance->provenance: OK.Base: rebuilt from a clean base (parent = current
main,4b36422) after accuracy caught a rewoundrebase; the branch now differs from
mainby exactly the ten files of this entry, andfigures/provenancepass at this head.
Refs #6