* only pick ecus from brand
* use superset of all requests
* much better
* clean up
* clean up
* try 150
* ?
* ???
* faster debug
* wtf
* no clue
* run push!
* this shouldn't catch it
* clean up
* rm
* debug: disable FW cache
* Ford: detect missing TJA/LCA config and disable LKAS
* set dashcamOnly
* revert
* clean up
* clean up
* some CAN FD do not have 0x01 block for PSCM
* bump cereal (fork)
* remove confusing comment
* add flags/event
* remove duplicate from events
* copy can be next pr
* dashcamOnly if no config comes back either (this shouldn't happen)
* flipped
* can do this
* Revert "can do this"
This reverts commit c3d311b2ff.
* Revert "flipped"
This reverts commit 75c01fb4c5.
* Revert "dashcamOnly if no config comes back either (this shouldn't happen)"
This reverts commit f82624a0eb.
---------
Co-authored-by: Shane Smiskol <shane@smiskol.com>
* format card
* standalone process
* no class member CS, there's no point
also can be confusing; what else could be using this?
* rename CoS
* Update selfdrive/controls/controlsd.py
* never works first time :D
* canRcvTimeout is bool
* hack
* add cpu
* see what testing closet comes up with
* first
* some clean up
* support passable CI, fix test models
* fix startup alert
* process replay changes
* test_fuzzy
* gate carOutput valid on carControl valid
* we should publish after we update carOutput
* controlsd was using actuatorsOutput from 2 frames ago for torque, not the most up to date
* check all checks for carControl in case controlsd dies
* log more timestamps
* more generic latency logger; needs some clean up
latency_logger.py was difficult to understand and modify
* card polls on can and carControl to get latest carControl possible
* temp try to send earlier
* add log
* remove latencylogger
* no mpld3!
* old loop
* detect first event
* normal send
* revert "card polls on can and carControl to get latest carControl possible"
how it was is best
* sheesh! update should be first
* first timestamp
* temp comment ( timestamp is slow :( )
* more final ordering, and make polling on/off test repeatable
* Received can
* new plot timestamps
* clean up
* no poll
* add controllers (draft)
* Revert "add controllers (draft)"
This reverts commit e2c3f01b2f.
* fix that
* conventions
* just use CS
* consider controlsd state machine in card: not fully done
* hmm it's just becoming controlsd
* rm debugging
* Revert "hmm it's just becoming controlsd"
This reverts commit 534a357ee9.
* Revert "just use CS"
This reverts commit 9fa7406f30.
* add vCruise
* migrate car state
* Revert "migrate car state"
This reverts commit 4ae86ca163.
* Revert "add vCruise"
This reverts commit af247a8da4.
* simple state machine in card (doesn't work as is)
* Revert "simple state machine in card (doesn't work as is)"
This reverts commit b4af8a9b0a.
* poll carState without conflate
* bump
* remove state transition
* fix
* update refs
* ignore cumLagMs and don't ignore valid
* fix controls mismatch; controlsd used to set alt exp
* controlsd_config_callback not needed for card
* revert ref temp
* update refs
* no poll
* not builder!
* test fix
* need to migrate initialized
* CC will be a reader
* more as_reader!
* fix None
* init after publish like before - no real difference
* controlsd clean up
* remove redundant check and check passive for init
* stash
* flip
* migrate missing carOutput for controlsd
* Update ref_commit
* bump cereal
* comment
* no class params
* no class
* Revert "no class"
This reverts commit 5499b83c2d.
* add todo
* regen and update refs
* fix
* update refs
* and fix that
* should be controlsstate
* remove controlsState migration
CoS.initialized isn't needed yet
* fix
* flip!
* bump
* fix that
* update refs
* fix
* if canValid goes false, controlsd would still send
* bump
* rm diff
* need to be very careful with initializing
* update refs
* Revert "card: move all car events (#32427)"
This reverts commit 8f46028bd4.
* keep the event here
* oops
* Revert "oops"
This reverts commit ea99a2768f.
* Revert "keep the event here"
This reverts commit ec089b4e1a.
* card: create pedal pressed event (#32393)
* move pedalPressed to card
* rm
* needs to be a builder
* move these
* clean up
* reader later
* Update ref_commit
* moved to card
* move stateless, common car events to car interface
* try to reduce process replay diff a bit
* Revert "try to reduce process replay diff a bit"
This reverts commit b12798deab.
* update refs
* VW: Steer to zero, for large values of zero
* ah, the joy of floating point
* comment, style
* actually fix floating point issue
* follow PlatformConfig refactor
* this check is not useful after PlatformConfig
* don't really need that
* work around docs assert
* little better
* one comment
* update refs
---------
Co-authored-by: Shane Smiskol <shane@smiskol.com>
* Ford: use platform codes to fuzzy fingerprint
TODO: write scripts/tests (print platform codes and version ranges etc.)
May close#31052
* get_platform_codes: fix return type
* add print_platform_codes.py script
* print_platform_codes: sort versions
* match_fw_to_car_fuzzy: use set comprehension, and fix typo
* Ford: add missing Mach-E fw
From the route 83a4e056c7072678/2023-11-13--16-51-33 (which is already
in selfdrive/car/tests/routes.py, added in #30691).
* add ford_fuzzy_fingerprint.ipynb notebook
* get_platform_codes: use regex to parse firmware
* test_ford: test_platform_codes_fuzzy_fw
* test_ford: use get_platform_codes in test_fw_versions
* match_fw_to_car_fuzzy: improve comments
* test_ford: add test_platform_codes_spot_check
* test_ford: add test_match_fw_fuzzy
* remove comment from notebook
* TestFordFW: remove engine ECU FW
* update print_platform_codes.py
* remove part number (unecessary)
* platform codes can just use platform hint and model year - software revision not useful
* fuzzy FP on the platform hint and model year hint range
* fix platform codes test
* update notebook
* add notebook
* explain model year hint better
* test part numbers again
* cleanup notebooks
* remove notebook
* cleanup match_fw_to_car_fuzzy and add comments
* update comment
* .
* Revert "remove notebook"
This reverts commit 5d4ca202f2.
* add notebook back
* remove PSCM from PLATFORM_CODE_ECUS
ABS and IPMA are the best for uniquely matching, and the radar is always required
* Revert "remove PSCM from PLATFORM_CODE_ECUS"
This reverts commit b7baeac19c.
* fix from merge
* more fixes
revert
* FW_RE -> FW_PATTERN
* this can actually be set
* conventions
* just add
* convention
* refactor matcher, this brings it more in line with Hyundai. IMPORTANT NOTE:
NOTE THAT WE remove the separation for the different platform code model year hint ranges, I don't see that being a problem
* better/smaller test
* add test to catch overlapping platform codes
* remove nb
* not now
---------
Co-authored-by: Shane Smiskol <shane@smiskol.com>
Shane Smiskol
roberttruong
Marcin Perlikowski
Cameron Clough
LostEon
Curtis Jiang
cl0cks4fe
Jason Young
YI418LT
young
andreasdamm
Jack Merrill