ctu-vras/monoforce
[IROS 2024] [ICML 2024 Workshop Differentiable Almost Everything] MonoForce: Learnable Image-conditioned Physics Engine
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.
Stars
89
Forks
7
Language
Jupyter Notebook
License
BSD-3-Clause
Category
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.
Higher-rated alternatives
lululxvi/deepxde
A library for scientific machine learning and physics-informed learning
pnnl/neuromancer
Pytorch-based framework for solving parametric constrained optimization problems,...
wilsonrljr/sysidentpy
A Python Package For System Identification Using NARMAX Models
dynamicslab/pysindy
A package for the sparse identification of nonlinear dynamical systems from data
google-research/torchsde
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.