Open FahadRazaKhan opened 2 years ago
@FahadRazaKhan I ran to this issue before. Could you paste your code snippet to help us better understand your script?
The experimental trace path could be download by following the instruction of this tutorial.
trace_path = ["./trace/20210726-154641_lexus_devens_center"]
world = vista.World(trace_path, trace_config={'road_width': 4})
@MarkCodering thanks for your response. Actually, I have just downloaded the Repo from Github, and after the installation, I tried to run the scripts in the example folder. I did not write anything. Do you still need to see the script?
@FahadRazaKhan Good morning from Taiwan. If you want to run an example code like sim_rgb.py is not possible since the sample code hasn't loaded any trace dataset. You need to add the trace data like the code snippet I gave you in the comment before.
@MarkCodering thanks for your help and good morning from Singapore. I downloaded the traces as you suggested, but I am still getting some warnings and it seems simulator is not working properly. Here is the screenshot of my code sim_control.py (edited in basic examples).
Good morning, @FahadRazaKhan. I just looked up your reply. I would suggest doing the following to solve the problem potentially.
Here is my code snippet for your reference.
def main():
trace_path = ["./trace/20210726-154641_lexus_devens_center"]
world = vista.World(trace_path, trace_config={'road_width': 4})
car = world.spawn_agent(
config={
'length': 5.,
'width': 2.,
'wheel_base': 2.78,
'steering_ratio': 14.7,
'lookahead_road': True
})
display = vista.Display(world)
state_space_controller = [
follow_human_trajectory, pure_pursuit_controller
][1]
world.reset()
display.reset()
while not car.done:
action = state_space_controller(car)
car.step_dynamics(action)
vis_img = display.render()
cv2.imshow('Visualize control', vis_img[:, :, ::-1])
cv2.waitKey(20)
Good morning, @FahadRazaKhan. I just looked up your reply. I would suggest doing the following to solve the problem potentially.
- Install openeb dependency and initialize the module with set_env.sh
- Choose one trace path to run instead of multiple traces (It might confuse VISTA to run the computation.)
Here is my code snippet for your reference.
def main(): trace_path = ["./trace/20210726-154641_lexus_devens_center"] world = vista.World(trace_path, trace_config={'road_width': 4}) car = world.spawn_agent( config={ 'length': 5., 'width': 2., 'wheel_base': 2.78, 'steering_ratio': 14.7, 'lookahead_road': True }) display = vista.Display(world) state_space_controller = [ follow_human_trajectory, pure_pursuit_controller ][1] world.reset() display.reset() while not car.done: action = state_space_controller(car) car.step_dynamics(action) vis_img = display.render() cv2.imshow('Visualize control', vis_img[:, :, ::-1]) cv2.waitKey(20)
Hi, the latest repository doesn't contain trace/20210726-154641_lexus_devens_center; how could I obtain the data? Thanks in advance!
Hi, @osugiw you can search for the author’s class, introduction to deep learning with its dataset sample
Hello MarkCodering, I am not able to run basic example code: import argparse import numpy as np import os import cv2
import vista from vista.utils import transform from vista.entities.agents.Dynamics import tireangle2curvature
def main():
trace_path = ["/home/parvez_alam/Downloads/vista_traces/20210726-131322_lexus_devens_center"]
world = vista.World(trace_path, trace_config={'road_width': 4})
car = world.spawn_agent(
config={
'length': 5.,
'width': 2.,
'wheel_base': 2.78,
'steering_ratio': 14.7,
'lookahead_road': True
})
display = vista.Display(world)
# follow_human_trajectory, pure_pursuit_controller
#][1]
world.reset()
display.reset()
while not car.done:
#action = state_space_controller(car)
#car.step_dynamics(action)
vis_img = display.render()
cv2.imshow('Visualize control', vis_img[:, :, ::-1])
cv2.waitKey(20)
main()
error:
2023-08-01 15:15:54,426::WARNING::[vista.entities.sensors.EventCamera.
May you help ?
Hello MarkCodering, I am not able to run basic example code: import argparse import numpy as np import os import cv2
import vista from vista.utils import transform from vista.entities.agents.Dynamics import tireangle2curvature
def main(): trace_path = ["/home/parvez_alam/Downloads/vista_traces/20210726-131322_lexus_devens_center"] world = vista.World(trace_path, trace_config={'road_width': 4}) car = world.spawn_agent( config={ 'length': 5., 'width': 2., 'wheel_base': 2.78, 'steering_ratio': 14.7, 'lookahead_road': True }) display = vista.Display(world) #state_space_controller = [ # follow_human_trajectory, pure_pursuit_controller #][1]
world.reset() display.reset() while not car.done: #action = state_space_controller(car) #car.step_dynamics(action) vis_img = display.render() cv2.imshow('Visualize control', vis_img[:, :, ::-1]) cv2.waitKey(20)
main()
error: 2023-08-01 15:15:54,426::WARNING::[vista.entities.sensors.EventCamera.] Fail to import module for event camera. Remember to do source /openeb/build/utils/scripts/setup_env.shCan ignore this if not using it 2023-08-01 15:15:55,130::WARNING::[vista.core.Trace._divide_to_good_segments] No video_label.csv Traceback (most recent call last): File "vista1.py", line 43, in main() File "vista1.py", line 37, in main vis_img = display.render() File "/home/parvez_alam/.local/lib/python3.8/site-packages/vista/core/Display.py", line 227, in render patch = PolygonPatch(patch, File "/home/parvez_alam/.local/lib/python3.8/site-packages/descartes/patch.py", line 87, in PolygonPatch return PathPatch(PolygonPath(polygon), **kwargs) File "/home/parvez_alam/.local/lib/python3.8/site-packages/descartes/patch.py", line 62, in PolygonPath vertices = concatenate([ File "/home/parvez_alam/.local/lib/python3.8/site-packages/descartes/patch.py", line 63, in concatenate([asarray(t.exterior)[:, :2]] + IndexError: too many indices for array: array is 0-dimensional, but 2 were indexed
May you help ?
@ParvezAlam123 Had the same issue. This reply helped me: https://github.com/vista-simulator/vista/issues/20#issuecomment-1623287350
Hi,
I am trying to run basic examples (i.e sim_control.py, sim_lidar.py) after the installation, however, it gives me the following error "~/python3.8/site-packages/vista/core/World.py", line 32, in init self._traces: List[Trace] = [ TypeError: 'NoneType' object is not iterable"
Any help would be appreciated.
Thanks.