Underwater ROV Object Handover MLP Policy (PyTorch)
Object Handover for the Underwater ROV — a trained Object Handover policy network with reference loading code. Captured/authored with joint encoders in the loop and validated against real Underwater ROV kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Demonstration clipfree preview
Left: real-world source footage. Right: a signal derived from it (inter-frame motion field or edge/feature map). Source & license are credited in the clip.
Preview
Free preview — no purchase requiredDeployment
Runs on Jetson Orin; 16GB VRAM required.
Frameworks
- Gazebo
Hardware
- Velodyne VLP-16x86-64 CPUA100 80GB
Sensors
- joint encoders2D LiDAR
Specs
- GPU: 16GB VRAM
- Size: 616 KB
- Duration: 10s
- Task success rate 79% over 1507 trials
- ROS compatible
- Jetson compatible
- Isaac Sim compatible
Tags
$299
Commercial license
underwater-rov-object-handover-mlp-policy-pytorch.zip · 616 KB
ND-Dev✓
Trust score
Would you deploy this in production?
Not enough votes yet. (0/3 so far)
Sign in to vote.
Reviews
0 reviews
No reviews yet. Be the first to share your experience.
More from ND-Dev
View profile →Dual-Arm Torso Screw Driving Gym Environment
Screw Driving for the Dual-Arm Torso — a Gymnasium training environment. Captured/authored with joint encoders in the loop and validated against real Dual-Arm Torso kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Related assets
Object Handover Perception Net — 6-DoF Arm (RGB-D 480px)
Object Handover for the 6-DoF Arm — a convolutional perception model with the full module definition. Captured/authored with RGB-D camera in the loop and validated against real 6-DoF Arm kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.