Published December 14, 2022
| Version 1.0.4
Dataset
Open
Motion Policy Networks
Creators
- 1. University of Washington, NVIDIA
- 2. NVIDIA
Description
This is the pretrained model, training data set, evaluation problem sets, and sample real robot data accompanying Motion Policy Networks, an end-to-end neural model that can be used to generate collision-free, smooth motion from just a single depth camera observation. The training data set consists of over 3 million motion planning problems for a Franka Panda arm in over 500,000 environments.
Notes
Version 1.0.4 includes the 6,540,000 trajectory dataset of Global Planner demonstrations
Files
Files
(17.2 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:12588a06789a5bc3865c239e549502d7
|
11.4 MB | Download |
|
md5:c017df4f55f145784b7e1d6a2eaff853
|
11.7 MB | Download |
|
md5:3d042ef5f67abb61e86ee1603ab8b644
|
11.3 MB | Download |
|
md5:e26e77d3649a9cd2d941381b9f6023dd
|
8.4 GB | Download |
|
md5:d2eb2da582f1934dea75ce9f4e5efbc9
|
228.9 MB | Download |
|
md5:82161cf3370910aa037dc6cfdf4c5485
|
8.5 GB | Download |
|
md5:d60043a54952673c708208af810aada3
|
42.7 MB | Download |