Downloads · 30 days
6
16% of all-time downloads
han-humanoid-navigation-transformer-v1
Caplin43/han-humanoid-navigation-transformer-v1
han-humanoid-navigation-transformer-v1 is a reinforcement learning model from Caplin43. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This model is designed for humanoid robot navigation and path planning. It predicts optimal movement directions based on multi-sensor input.
All-time downloads
38
Public
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 54%
At a glance
- Task
- Reinforcement Learning
- License
- mit
- Model type
- transformer
- Access
- Public
- Created
- Feb 14, 2026
- Updated
- Feb 14, 2026
- SHA
- 50d122fc
Model card
From the Hugging Face model README
HAN Humanoid Navigation Transformer v1
Overview
This model is designed for humanoid robot navigation and path planning. It predicts optimal movement directions based on multi-sensor input.
The model focuses on indoor navigation with obstacle avoidance.
Architecture
- Transformer Encoder
- 6 Layers
- 8 Attention Heads
- Hidden Size: 512
- Feedforward Size: 2048
- Activation: GELU
Observation Space
- Depth sensor input
- IMU orientation
- Distance sensors
- Velocity vectors
Action Space
- Forward movement
- Turning angle
- Step length adjustment
Training Data
- Simulated indoor navigation environments
- Random obstacle layouts
- Dynamic object movement scenarios
Intended Use
- Humanoid navigation research
- Robotics simulation projects
- Indoor autonomous movement
Limitations
Trained in simulation. Real-world deployment requires domain adaptation.
Author
Caplin43
- Task
- Reinforcement Learning
- Type
- transformer
- License
- mit
- Created
- Feb 14, 2026
- Updated
- Feb 14, 2026