augcog / roar Goto Github PK

View Code? Open in Web Editor NEW

26.0 26.0 200.0 10.33 MB

Robot Open Autonomous Racing (ROAR)

Home Page: https://augcog.github.io/ROAR/

License: Apache License 2.0

Python 24.90% Jupyter Notebook 75.10%

roar's People

Contributors

Stargazers

Watchers

Forkers

wuxiaohua1011 cfanguo liqiaw cal-jackzhao jw5243 guineawheek xinyun-c amanda-chiang williamsitu sssdengshuwen trance-0 fcr3 ethansun666 hmtjyqs mavabene zetianluo jazzyrrao jiuqiwang4201 iacchris closest-num-2-0 marleahpuckett kevnnliu drivercool jackykwok2002 lemat9 black1149 josephinekoe scnerd42 chicken-tikkai mingjun-wu jasonjfang vadeshah jonathan-cw amit-palekar lynnromer asdegoyeneche njo12 ryougi1201 zil011 timothyjhurt danielchandg ryanc1681 mkscheble adrianliu99 moonwonlee sakura6227 roar-spring-2021 johnyu-github devamshri nickl77 nalinplad zhenjiasun pointyepic kylearffy danthecoderman06 vraju123 aiden126 petergourgui ponytai1j srihari-kothapalli rainfzy sxc-c micahrick pokemoners aserlloyd seankusu tuvana1234 robestan liamhoffmann teedsk al-nd jeiaso anniexu670 mahu0926 jloeffler4 burnttomato aarli421 lyraid-celest nexure n2qm gitignore1 shanqiong electzeus samuelzh1 anshul2 shizizhou bnjmnzmmrmn ploxtron berkeleycurtis baka-trashpanda 2jh0820 joy-ch li-sustech karim-elrefai sunishamf hengyuany xgao0613 jamesyang02 berkeleybear22ryan tlzh0001

roar's Issues

Separate Arduino and Intel realsense dependency

Is your feature request related to a problem? Please describe.
make sure that even if I don't have aruidno plugged in, the program is still going to run without panicking

runner_ Ios.py runtime exited unexpectedly

os:win10
describe：
1.python .\runner_ios.py -m vr --auto False
2.Xbox controls the car to reverse
result：
exited unexpectedly

kk.2021-08-25.19-05-36.mp4

ROAR Jetson Freeze after 1 min of runtime

Describe the bug
Running python3 runner_jetson.py and wait for about 1 minute, its going to freeze. It seems like the program is still runing in the background, but is just blocked by something.

To Reproduce
Steps to reproduce the behavior:

run python3 runner_jetson.py on Jetson Nano
Wait for about 1 minute

Expected behavior
It keeps going until agent is finished

Carla bridge functions doesn't work as expectation

Describe the bug
In carla_bridge.py:
convert_xx_from_agent_to_source functions have issue:

ROAR/Bridges/carla_bridge.py

Lines 182 to 197 in b7cd322

 def convert_location_from_agent_to_source(self, source: Location) -> carla.Location: 

 """Convert Agent's Location to a Carla.Location.""" 

 return carla.Location(x=source.x, y=-source.z, z=source.y) 

 def convert_rotation_from_agent_to_source(self, source: Rotation) -> carla.Rotation: 

 """Convert Agent's Rotation to a Carla.Rotation.""" 

 return carla.Rotation(pitch=source.yaw, yaw=source.pitch, roll=source.roll) 

 def convert_transform_from_agent_to_source( 

 self, source: Transform 

 ) -> carla.Transform: 

 """Convert Agent's Transform to a Carla.Transform.""" 

 return carla.Transform( 

 location=self.convert_location_from_agent_to_source(source=source.location), 

 rotation=self.convert_rotation_from_agent_to_source(source=source.rotation), 

 )

are not inverse functions of

ROAR/Bridges/carla_bridge.py

Lines 29 to 58 in b7cd322

 def convert_location_from_source_to_agent(self, source: carla.Location) -> Location: 

 """w 

  Convert Location data from Carla.location to Agent's location data type 

  invert the Z axis to make it into right hand coordinate system 

  Args: 

  source: carla.location 

  Returns: 

  """ 

 return Location(x=source.x, y=source.z, z=source.y) 

 # return Location(x=source.x, y=source.y, z=source.z) 

 def convert_rotation_from_source_to_agent(self, source: carla.Rotation) -> Rotation: 

 """Convert a CARLA raw rotation to Rotation(pitch=float,yaw=float,roll=float).""" 

 roll, pitch, yaw = source.roll, source.pitch, source.yaw 

 if yaw <= 90: 

 yaw = yaw + 90 

 else: 

 yaw = yaw - 270 

 return Rotation(roll=roll, pitch=pitch, yaw=-yaw) 

 def convert_transform_from_source_to_agent( 

 self, source: carla.Transform 

 ) -> Transform: 

 """Convert CARLA raw location and rotation to Transform(location,rotation).""" 

 return Transform( 

 location=self.convert_location_from_source_to_agent(source=source.location), 

 rotation=self.convert_rotation_from_source_to_agent(source=source.rotation), 

 )

To Reproduce

Create a agent transform
Convert it to carla transform using convert_transform_from_agent_to_source
Convert it back to agent transform using convert_transform_from_source_to_agent
The new agent transform is different from the original one

Expected behavior
The original agent transform should be the same thing as the new agent transform (the one converted to carla and converted back)

Desktop (please complete the following information):

OS: Windows 11, Carla

Multi Threading VS Multi Processing

Is your feature request related to a problem? Please describe.
The code currently is using Multi-Threadding. However, according to multiple sources
https://www.guru99.com/difference-between-multiprocessing-and-multithreading.html
https://stackoverflow.com/questions/3044580/multiprocessing-vs-threading-python

It seems like the proper solution should be using multi processing, to avoid race condition, and etc.

Might be useful to get the right parallelism right.

Describe the solution you'd like
Utilize multiprocessing in Jetson modules, and also ensure that proper Agent classes have the ability to run in parallel

Unknown object caused collision in ROAR easy map

Describe the bug
There is unknown object caused collision at a corner in ROAR easy map, but it didn't report collision.
Could you check the ROAR easy map?

ROAR_easy.mp4

Thanks,
To Reproduce
Steps to reproduce the behavior:

Go to 'roar_easy_windows'
Click on 'CarlaUE4.exe' to launch
Open terminal to run "python .\runner_competition_evaluator.py"
See attached video the car spin over near the corner in ROAR easy map, but it didn't report collision on the left.

Expected behavior
Expect the car can run near the corner in ROAR easy map without spin over or report collision.

Screenshots
Attached the video

Desktop (please complete the following information):

OS: Win10

runner_sim.py and runner_competition_evaluator.py work differently

Describe the bug
The car does not behave the same way when running runner_sim.py vs. runner_competition_evaluator.py.

To Reproduce
Steps to reproduce the behavior:

Run both scripts and observe the speed of the car.

Expected behavior
The car speeds up more during runner_sim.py.

Screenshots
If applicable, add screenshots to help explain your problem.

Desktop (please complete the following information):

OS: Windows 10
GPU

Additional context
Add any other context about the problem here.

Ground Plane detection module does not work on actual Realsense camera

Describe the bug
Ground Plane detection module does not work on actual realsense camera

To Reproduce
Steps to reproduce the behavior:

Use OccupancyMapAgent in jetson_runner.py
make sure in ground_plane_detector.py, the lines for displaying the image is enabled

Expected behavior
a cv2 windows should pop up, as do in the simulator

better look ahead + PID values

Is your feature request related to a problem? Please describe.
More aggressive/better PID values
current car doesn't move smoothly, that's probably due to a combination of PID and look ahead values. Need to do more experiment to find an optimal value set.

add astern function

Is your feature request related to a problem? Please describe.
the car running on the Carla can’t move backward. It will cause when the users operate the car collision with the 'wall', the car will can't move. The user have to restart the runner_sim.py .

No such file or directory: 'ROAR_Sim/configurations/occu_map_config.json'

To Reproduce
Steps to reproduce the behavior:

Follow QuickStart guide
Running python runner_sim.py gives the error No such file or directory: 'ROAR_Sim/configurations/occu_map_config.json'
JSON file is missing from local filesystem and the repo

Left hand vs Right hand coordinate issue

Describe the bug
So after some rolling back, i figured out that it is indeed some bad translation between left-hand and right hand coordinate system that messes things up. However, I am stucked at how to make it right. The commit that is working (in the left hand coordinate system) is this one:https://github.com/augcog/ROAR/tree/0bde066531e559e291fc8e395b9c3a53de8f014f/ROAR

Make sure to checkout both the ROAR_Sim and ROAR on that commit.
I've also raised an issue on Github.
I believe the core issue is that we've got many points where we need to notice the coordinate1. Translating data from ROAR Agent to Carla2. Translating data from Carla to ROAR Agent3. Reading in txt waypoint file (since the waypoint file is recorded by the ROAR agent, therefore it will be impacted if the ROAR agent is in the left or right coordinate system).4. Specifically this line that does the transformation in visualization:https://github.com/augcog/ROAR/blob/main/ROAR/visualization_module/visualizer.py#L141

To Reproduce
Steps to reproduce the behavior:
Just run the agent with next waypoint visulazation, it is not going to draw a straight line

find_k_values function PID Controller clips pid values

np.clip() got applied to Kp, Ki, Kd raw coefficients in find_k_values function in PIDController class.

PID values got clipped where the minimum is 0 and the maximum is 1.

Steps to reproduce the behavior:

Go to def find_k_values in class PIDController in 'pid_controller.py'.
return np.clip([k_p, k_d, k_i], a_min=0, a_max=1) # this is problematic

Expected behavior
PID values can go over 1, for example k_p = 10000 is valid

Additional context
np.clip is used in 33 places across 11 files. Need to be checked.

waypoint file is not accurate

Describe the bug
wapoint file is not accurate due to movement of base station. Need to recollect waypoints

	def convert_location_from_agent_to_source(self, source: Location) -> carla.Location:
	"""Convert Agent's Location to a Carla.Location."""
	return carla.Location(x=source.x, y=-source.z, z=source.y)

	def convert_rotation_from_agent_to_source(self, source: Rotation) -> carla.Rotation:
	"""Convert Agent's Rotation to a Carla.Rotation."""
	return carla.Rotation(pitch=source.yaw, yaw=source.pitch, roll=source.roll)

	def convert_transform_from_agent_to_source(
	self, source: Transform
	) -> carla.Transform:
	"""Convert Agent's Transform to a Carla.Transform."""
	return carla.Transform(
	location=self.convert_location_from_agent_to_source(source=source.location),
	rotation=self.convert_rotation_from_agent_to_source(source=source.rotation),
	)

	def convert_location_from_source_to_agent(self, source: carla.Location) -> Location:
	"""w
	Convert Location data from Carla.location to Agent's location data type
	invert the Z axis to make it into right hand coordinate system
	Args:
	source: carla.location

	Returns:

	"""
	return Location(x=source.x, y=source.z, z=source.y)
	# return Location(x=source.x, y=source.y, z=source.z)

	def convert_rotation_from_source_to_agent(self, source: carla.Rotation) -> Rotation:
	"""Convert a CARLA raw rotation to Rotation(pitch=float,yaw=float,roll=float)."""
	roll, pitch, yaw = source.roll, source.pitch, source.yaw
	if yaw <= 90:
	yaw = yaw + 90
	else:
	yaw = yaw - 270
	return Rotation(roll=roll, pitch=pitch, yaw=-yaw)

	def convert_transform_from_source_to_agent(
	self, source: carla.Transform
	) -> Transform:
	"""Convert CARLA raw location and rotation to Transform(location,rotation)."""
	return Transform(
	location=self.convert_location_from_source_to_agent(source=source.location),
	rotation=self.convert_rotation_from_source_to_agent(source=source.rotation),
	)

augcog / roar Goto Github PK

roar's People

Contributors

Stargazers

Watchers

Forkers

roar's Issues

Recommend Projects

Recommend Topics

Recommend Org