proroklab / magat_pathplanning Goto Github PK

Hello, I have executed cmake and make, recompiled the ecbs file, and replaced the ecbs file in onlineExpert of this project, but still failed to generate any file in the /failure_cases/output_ECBS/ folder during the train process. I did not report the above error and my train was not interrupted, but the terminal showed the following error：
[Errno 2] No such file or directory: './Data/experiments/dcpOEGAT_map20x20_rho1_10Agent/K2_HS0_P1/1688619991/failure_cases/output_ECBS/output_map20x20_IDMap00421_IDCase00041_ECBS.yaml'
terminate called after throwing an instance of 'YAML::BadFile'
what(): bad file

I don't know why, please advise, thank you!

Hi, thank you for sharing the work and code.

I believe there are some issues with the generation of the offline dataset part (CasesSolver_cropfromMap_fixedLength.py). When I generate 10 maps with 10 cases using "Generate_cropmap.py" and then create an offline dataset using "CasesSolver_cropfromMap_fixedLength.py," it appears to only consider the first map file (Map_ID00000.png).

Additionally, I noticed that the "Map_ID00000.png" generated from both "Generate_cropmap.py" and "CasesSolver_cropfromMap_fixedLength.py" appears to be different."

Thank you.

For example, I have generated input_map20x20_IDMap00000_IDCase00000.yaml, then I need to run onlineExpert/ecbs to generate output_map20x20_IDMap00000_IDCase00000_ECBS.yaml. I find the system(CentOS) will return Segmentation fault (core dumped). So, is this ecbs file the final version? Did you upload the wrong file?
The contents of input_map20x20_IDMap00000_IDCase00000.yaml are as follows
P.S. My code is running on the CPU instead of GPU, I don't know if it will affect ecbs file, which will make it unable to work normally

map:
    dimensions: [20, 20]
    ID_Map: 0
    ID_Case: 0
    obstacles:
    - [0, 2]
    - [0, 15]
    - [0, 18]
    - [1, 2]
    - [1, 6]
    - [1, 15]
    - [2, 0]
    - [2, 8]
    - [3, 1]
    - [3, 17]
    - [3, 19]
    - [4, 0]
    - [4, 6]
    - [4, 12]
    - [4, 15]
    - [5, 3]
    - [5, 4]
    - [6, 3]
    - [6, 5]
    - [6, 16]
    - [6, 17]
    - [6, 18]
    - [7, 1]
    - [7, 2]
    - [7, 3]
    - [8, 6]
    - [8, 14]
    - [8, 18]
    - [9, 11]
    - [9, 15]
    - [9, 19]
    - [10, 17]
    - [11, 2]
    - [12, 0]
    - [13, 1]
    - [13, 15]
    - [15, 2]
    - [15, 8]
    - [15, 9]
    - [16, 4]
    - [16, 7]
    - [16, 8]
    - [17, 3]
    - [17, 14]
    - [18, 1]
    - [18, 2]
    - [18, 3]
    - [18, 15]
    - [18, 19]
    - [19, 13]
agents:
  - name: agent0
    start: [17, 4]
    goal: [11, 19]
  - name: agent1
    start: [12, 1]
    goal: [16, 11]
  - name: agent2
    start: [8, 7]
    goal: [17, 9]
  - name: agent3
    start: [5, 5]
    goal: [18, 10]
  - name: agent4
    start: [2, 2]
    goal: [10, 11]
  - name: agent5
    start: [14, 0]
    goal: [3, 15]
  - name: agent6
    start: [6, 6]
    goal: [11, 3]
  - name: agent7
    start: [2, 1]
    goal: [14, 13]
  - name: agent8
    start: [0, 3]
    goal: [12, 16]
  - name: agent9
    start: [18, 4]
    goal: [6, 2]

Thanks for the open source codebase! I am hoping to use MAGAT for some experiments and have got the codebase to work on custom maps and start-goal scenarios. However I want to use MAGAT on some instances where the provided ECBS script is not finding a solution. Is there a way to run MAGAT without needing ECBS solutions? I have spent a non-trivial amount of time trying to figure it out but have been unsuccessful so far.

Please let me know if there is an easy way to run MAGAT without needing ECBS to find a solution.

Best,
Rishi

said like title~