* mse err from 0.028070712 -> 5.8073703e-05
* build with weights fixup
* need thneed lib also
* don't break for binaries
* static analysis says i need init
* check the bias
* load_dlc_weights
* nicer scons
* tested scons
* fix static
* pylint issue
* new ref
* a few more asserts
Co-authored-by: Harald Schafer <harald.the.engineer@gmail.com>
* Added wide cam vipc client and bigmodel transform logic
* Added wide_frame to ModelState, should still work normally
* Refactored image input into addImage method, should still work normally
* Updated thneed/compile.cc
* Bigmodel, untested: 44f83118-b375-4d4c-ae12-2017124f0cf4/200
* Have to initialize extra buffer in SNPEModel
* Default paramater value in the wrong place I think
* Move USE_EXTRA to SConscript
* New model: 6c34d59a-acc3-4877-84bd-904c10745ba6/250
* move use extra check to runtime, not on C2
* this is always true
* more C2 checks
* log if frames are out of sync
* more logging on no frame
* store in pointer
* print sof
* add sync logic
* log based on sof difference as well
* keep both models
* less assumptions
* define above thneed
* typo
* simplify
* no need for second client is main is already wide
* more comments update
* no optional reference
* more logging to debug lags
* add to release files
* both defines
* New model: 6831a77f-2574-4bfb-8077-79b0972a2771/950
* Path offset no longer relevant
* Remove duplicate execute
* Moved bigmodel back to big_supercombo.dlc
* add wide vipc stream
* Tici must be tici
* Needs state too
* add wide cam support to model replay
* handle syncing better
* ugh, c2
* print that
* handle ecam lag
* skip first one
* so close
* update refs
Co-authored-by: mitchellgoffpc <mitchellgoffpc@gmail.com>
Co-authored-by: Harald Schafer <harald.the.engineer@gmail.com>
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
Co-authored-by: Comma Device <device@comma.ai>
* add thneed optimizer
* local work group opt
* kernels and final mods
* release files
* build system touchups
* fix kernel path, rand inputs for self test
* broken since extra is gone
* update model replay ref
Co-authored-by: Comma Device <device@comma.ai>
* base LatControl class, move sat check out of pid.py
clean up
clean up
* fix
* global variable for min control speed
* nicer name
* unify latcontrol class init arguments
* add to release files
* saturated if close to limit
* move angle mode saturation checks into class
* check_saturation function takes in current saturated status
undo
* apply latcontrol_angle's active checking to all controllers
* clean up
* move those back
* make abstract baseclass
* add test for saturation
* keep clip
* update ref
* fix static analysis
Co-authored-by: Willem Melching <willem.melching@gmail.com>
* should work
* Revert "should work"
This reverts commit dabc2ea17a072a6c835e4bd1c75a2c1e2d10623d.
* move lane change logic to DesireHelper class
* clean up desires
clean up desires
* comments
* Revert "clean up desires"
This reverts commit 7301c921e305fcbd4746b19040631d935d50dfd9.
* Update selfdrive/controls/lib/desire_helper.py
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
* add to files_common
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
Co-authored-by: Willem Melching <willem.melching@gmail.com>
* remove sienna dbc
same as avalon
* rx and nx are also the same as avalon
* highlander can also use avalon's dbc
* bump opendbc
* rename avalon to tnga-k
* pt
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
* use rav4h dbc for nx
also bump opendbc
* remove from release file
* same with highlander
* bump opendbc
* rav4h -> tngakh
also rxh
* bump opendbc
* bump again
* remove from release files
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
* device side of statsd
* need to start it
* enable in manager
* add sleep
* cleanup
* remove aggregates for now and standardize on industry terms
* manager needs main
* need to have a try/except
* atomic_write_on_fs_tmp does not work
* cleaner
* use dump
Co-authored-by: Willem Melching <willem.melching@gmail.com>
* one file at a time
* limit amount of files
* move to influx line protocol and cleanup
* needs to be a list
* fix timezone bug
* actually rate limit
* add to release
* normalized origin
* also log deviceType
* more stats
Co-authored-by: Willem Melching <willem.melching@gmail.com>
* USBDevice
* merge master
* rebase master
* add to fiels_common
* inline functions
* namespace
* init err
* remove nested if
* cleanup
* bump panda for branch
* change includes
* bump panda branch
* change name
* bump master panda
Co-authored-by: Igor Biletskyy <briskspirit@users.noreply.github.com>
Co-authored-by: Igor Biletskyy <bs@privacy.im>
* tesla long squashed changes
* fix no resume from stop
* try setting accel limits to 0 to remove jerk with fast switchover
* expand radard lookup tables
* bump merged panda submodule
* there is no QThread::create on device
* add files to files_common
* modify SConscript
* no memory_resouce on device
* #define HAS_MEMORY_RESOURCE
* fix hangs on shutdown
* build on device with the --extra flag
* delete later
* setup -> extras
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
* add sphinx
* switch theme
* Experiment: sphinx docs generation updated (#22708)
* moved build to root gitignore, added .gitkeep
* Improved makefile doc build process
- Removed auto-generated docs from source control
- Moved apidoc.sh into Makefile
- Removed make.bat (can add back if Windows support desired)
- Added sphinx viewcode and markdown extensions
- Added feature to source /docs in build, so any .rst file in /docs will
override the respective file during the build process
- Added feature to copy all markdown/rst files from source into /build/
during build process so they can be easily referenced while writing
docs (see examples in index.md)
- Wrote basic starter index.md file
TODO: Add new dependencies to Pipfile [dev-packages]
* Revert accidental modification to Pipfile
* fix command substitution
* exclude xx
* improve docs
* dont include all docs in release build
* Add dockerfile
* update title
* include normal readme
* build container in CI
* use buildkit
* add login
Co-authored-by: Chad Bailey <chadbailey904@gmail.com>
* just use MPC for fcw checking
* thats already bad
* model FCW is always good
* better fcw
* should be good for now
* comment
* linting
* cleaner
* unused
* rebased
* cleaner, seems to drive better?
* more stable
* wrong import
* new way of thinking
* reports look nice
* start move back
* works at leas
* good timestamps
* step by step
* somewhat work
* tests pass
* ALL CARS STOPPED
* should work
* fake a cruise obstacle
* cleaner costs
* pretty good except cruise braking
* works pretty well now!
* cleanup
* add source
* add source
* that is needed for unit tests
* nan recovery
* little cleaner
* stop wasting arrays
* unreasonable without unfair init
* this isnt needed without the exponential
* that works too
* unused
* uses less
* new ref
* long enough
* e2e long api
* DONT PUT IN A VIEW INTO ACADOS
* new ref for outside weights
* remove debug prints
Adeeb Shihadeh
George Hotz
Robbe Derks
Willem Melching
Shane Smiskol
cydia2020
Dean Lee
Igor Biletskyy
HaraldSchafer
Vehicle Researcher