saferoboticslab / safe_occlusion_aware_planning Goto Github PK

Hi, I'm interested in reproducing the experiments from the paper, but am running into a few issues:

• FRS baseline
  • is it possible to upload the script(s) for running the baseline used in the paper? Currently, it seems like the script is empty: https://github.com/SafeRoboticsLab/Safe_Occlusion_Aware_Planning/blob/main/test_FRS.py
• Blind summit
  • in the paper (eg fig 3), the scenario is described as an incline on Town 5, however, the script test_blind_summit appears to be on Town 3, and also a decline (instead of an incline)
  • if I uncomment the lines involving the truck obstacle (which I presume is the hidden agent in figure 3), I get the following error:

  Traceback (most recent call last):
  File "test_blind_summit.py", line 44, in <module>
    truck = Agent(client, truck_path, 295, 10)
  File "Safe_Occlusion_Aware_Planning-main/client/agent.py", line 20, in __init__
    self.actor = self.client.spawn_objects(filter, self.init_waypoint)
  File "Safe_Occlusion_Aware_Planning-main/client/client.py", line 194, in spawn_objects
    spawn_point = waypoint.transform
  AttributeError: 'NoneType' object has no attribute 'transform'
  

• Intersection
  • If I uncomment the obstacle spawn/tick comments in test_intersection, I can see the hidden agent in figure 4, but it doesn't appear to move
• Overtake
  • Running test_overtake gives me the following error:

  Safe_Occlusion_Aware_Planning-main/risk_analysis/shadow_utils.py:785: 
    RuntimeWarning: divide by zero encountered in true_divide
    V_in_max = (delta_s - 0.5*self.a_max*delta_t**2)/delta_t
  

Let me know if you'd like me to test anything on my end in case there's user error.

Hello! I'm really impressed with this work.
Regarding this framework, I have a question to seek your advice. When I run test_overtake.py, I find that the relpanning close loop takes a long time, maybe 90s on my device. Is this normal? My cpu is Intel Core i7-12700.
Thanks in advance for your reply！