How to obtained the computer path using neural planner ?

[Muhayyuddin]

Hi Thank you for sharing your work, I am trying to reproduce the results. I downloaded the 2D sample data and run the following commands

Assuming paths to obstacles point-cloud are declared, train obstacle-encoder: python MPNET/AE/CAE.py

Assuming paths to demonstration dataset and obstacle-encoder are declared, run mpnet_trainer:

python MPNET/train.py

it trained correctly but when I run the neural planner using the following command

Run tests by first loading the trained models:
python MPNET/neuralplanner.py

it shows the above-stated output. I don't know if it is correct or not, how can I get the computed path to visualize it using visulizer.py.

Thank you

[scploeger]

@Muhayyuddin I have the same question. I am just trying to visualize the output. I get the same output as you, but I dont see anywhere where a "path file" is generated. Did you ever figure it out?

From visualizer.py, line 37: parser.add_argument('--path_file', type=str, default='./results/env_0/path_0.txt',help='path file') ...but as I search through the repo I see nowhere where this will be generated. Did you ever figure it out? Maybe @ahq1993 can point us in the right direction? Thanks in advance

Spencer

[Muhayyuddin]

Hi Spencer, I was able to visualize the path by extending the code to generate the path file. In fact Actual path[0] represents X values and Actual path[1] represents Y values. Just to try, you can manually generate a path file at any location e.g. default='./results/env_0/path_1.txt' and save the values for instance according to the above example. -14.23 -17.22 -7.30 -10.07 2.84 -1.10 and so on.

@ahq1993 I hope my understand is correct :-)

Good luck Muhayy

[scploeger]

Thanks @Muhayyuddin ! I will give this a try. Do you know what the difference between actual_path and new_path is?

[scploeger]

Hi again @Muhayyuddin, I meant to ask in the previous post if you have looked at the sample 2D data file? https://drive.google.com/drive/folders/1oADJ85qxb3WKHXE4Bj6lwio-soGOktRa (provided in the readme)

I am struggling to figure out what the difference is between the obstacle point cloud data files in dataset/obs_cloud/ compared to the obs.dat and obs_perm2.dat files in dataset/ directory. Let me know if you know what the difference is, thanks :)

• spencer