Robotics
LeRobot
Safetensors
act
aadarshram commited on
Commit
577b292
·
verified ·
1 Parent(s): 9c4c00f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -12,7 +12,11 @@ tags:
12
 
13
  # Model Card for act
14
 
15
- <!-- Provide a quick summary of what the model is/does. -->
 
 
 
 
16
 
17
 
18
  [Action Chunking with Transformers (ACT)](https://huggingface.co/papers/2304.13705) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates.
 
12
 
13
  # Model Card for act
14
 
15
+ This is an Action Chunking Transformer (ACT) model trained for pick and place tape task.
16
+ Notes:
17
+ 1. Model trained only with front camera to see how well it can perform with just that.
18
+ 2. Partial Observabilty in front camera. During motion some parts of the robot go off camera's frame. Can the model handle that?
19
+ 3. Pick location fixed and drop location has slight variations (considering the difficulty to learn to grasp a tape)
20
 
21
 
22
  [Action Chunking with Transformers (ACT)](https://huggingface.co/papers/2304.13705) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates.