ctu-vras/monoforce

[IROS 2024] [ICML 2024 Workshop Differentiable Almost Everything] MonoForce: Learnable Image-conditioned Physics Engine

45
/ 100
Emerging

This project helps roboticists and autonomous system developers predict how a robot will interact with various terrains using just standard camera images. It takes RGB camera images and camera calibration data to output detailed predictions of the robot's trajectory, the terrain's shape and properties (like friction and stiffness), and the forces involved in robot-terrain contact. This tool is designed for those building or deploying mobile robots, especially in challenging or unknown outdoor environments.

Use this if you need to accurately predict robot movement and terrain interaction in real-time for autonomous navigation using only visual input.

Not ideal if your application primarily relies on other sensor data like LiDAR or IMU for terrain analysis, or if you need to model very specific, non-standard robot-terrain interactions not covered by typical physics.

robotics autonomous-navigation mobile-robot-design terrain-analysis path-planning
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

89

Forks

7

Language

Jupyter Notebook

License

BSD-3-Clause

Last pushed

Feb 03, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ctu-vras/monoforce"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.