betaflight-sitl
Operate gym-pybullet-drones Betaflight SITL workflows, including BetaAviary layout checks, UDP port mapping, and external prerequisite troubleshooting.
- License 许可
- MIT
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- betaflight-sitl
- license
- MIT
- metadata
- { "disco-role": "operating" }
- description
- Operate gym-pybullet-drones Betaflight SITL workflows, including BetaAviary layout checks, UDP port mapping, and external prerequisite troubleshooting.
- disable-model-invocation
- true
02 资源文件 4
- 参考文档references/troubleshooting.md3.4 KB
- 参考文档references/workflows.md3.4 KB
- 脚本scripts/check_betaflight_layout.py3.9 KB
- 脚本scripts/run_beta_sitl.py6.0 KB
03 SKILL.md 正文
Betaflight SITL
Use this sub-skill when a task mentions Betaflight SITL, BetaAviary, beta.py, the betaflight_sitl/bfN directory layout, UDP ports, or the external build/check steps implied by the package's Betaflight example.
Route here for
- Checking whether a local checkout or installed package has the external Betaflight SITL binaries staged in the layout that
BetaAviaryexpects. - Understanding the port mapping used by
BetaAviaryand the BetaFlight example. - Running the bundled helper in check-only mode or, when explicitly requested, executing the wrapped BetaFlight workflow after prerequisites are present.
- Troubleshooting missing
betaflight_sitl/bfNdirectories, missing executables, terminal-launch differences, or port mismatches.
Do not handle here
- PID, velocity, downwash, or MRAC control simulations; route those to
control-simulation. - PPO hover training or playback; route those to
rl-workflows. - External Betaflight repository cloning/building itself. This sub-skill only describes and checks the prerequisites that must already exist.
Start here
-
Read workflows to understand the layout check, port map, and optional execution flow.
-
Read troubleshooting before attempting to run anything, especially on machines without a display or without the external SITL tree.
-
Prefer the bundled checker first:
python scripts/check_betaflight_layout.py --num-drones 2 -
If and only if the checker reports a complete layout and the user explicitly wants execution, run the wrapper in execute mode:
python scripts/run_beta_sitl.py --execute --num-drones 2 --duration-sec 5 --output-folder /tmp/gpd-beta --no-gui
Runtime guardrails
clone_bfs.shis reference evidence, not a bundled runtime helper. It clones and patches an external Betaflight repository and should not be auto-run by future agents from this skill.BetaAviaryexpects the external SITL binaries to exist in abetaflight_sitl/bfNlayout relative to the package checkout or installed-package path that the workflow is using.- The package's BetaFlight example maps drones to ports in steps of 10: drone 0 uses 9002/9003/9004, drone 1 uses 9012/9013/9014, and so on.
- Keep the bundled runner check-only unless
--executeis passed. This sub-skill is intentionally safe by default. - When the external layout is missing, stop and report exactly what is absent rather than trying to clone or build Betaflight inside the generated skill.
04 同仓库更多 Skills
passnet-triton-opt
Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.
passnet-solve
END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.
passnet-skill
PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.
passnet-pattern-fusion
Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.
passnet-orchestrate
Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.
passnet-feedback
Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).