Create model_explainability.md
Browse files- model_explainability.md +14 -0
model_explainability.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Explainability
|
| 2 |
+
Field | Response
|
| 3 |
+
:------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------
|
| 4 |
+
Intended Task/Domain: | Robotic Manipulation
|
| 5 |
+
Model Type: | Denoising Diffusion Probabilistic Model
|
| 6 |
+
Intended Users: | Roboticists and researchers in academia and industry who are interested in robot manipulation research
|
| 7 |
+
Output: | Actions consisting of end-effector poses, gripper states and head orientation.
|
| 8 |
+
Describe how the model works: | ``mindmap`` is a Denoising Diffusion Probabilistic Model that samples robot trajectories conditioned on sensor observations and a 3D reconstruction of the environment.
|
| 9 |
+
Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: | Not Applicable
|
| 10 |
+
Technical Limitations & Mitigation: | - Limitation: This policy is only effective in the exact simulation environment in which it was trained. Mitigation: Recommended to retrain the model in new simulation environments. - Limitation: The policy was not tested on a physical robot and likely only works in simulation. Mitigation: Expand training, testing and validation on physical robot platforms.
|
| 11 |
+
Verified to have met prescribed NVIDIA quality standards: | Yes
|
| 12 |
+
Performance Metrics: | Closed loop success rate on simulated robotic manipulation tasks.
|
| 13 |
+
Potential Known Risks: | The model might be susceptible to rendering changes on the simulation tasks it was trained on.
|
| 14 |
+
Licensing: | [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/)
|