We’re working hard on developing useful open source robotics software for the community! Check our GitHub for the most recent updates. The packages below are general contributions built by our laboratory; if you’re looking for code that is specific to a certain publication or dataset, please head over to the appropriate page.
GraphIK Library
GraphIK is a powerful library for solving inverse kinematics problems by modelling robots as geometric graphs and leveraging concepts from distance geometry and convex optimization. Fast solve times are possible for high-DOF robot models.
GraphIK is a powerful library for solving inverse kinematics problems by modelling robots as geometric graphs and leveraging concepts from distance geometry and convex optimization. Fast solve times are possible for high-DOF robot models.
Phoenix Tail-sitter Drone
Our open source tail-sitter platform, now called the ‘Phoenix’. This repository contains a complete package of design documents, CAD models, simulation tools, and onboard firmware code necessary to build, assemble, fly and experiment with a novel tail-sitter aerial vehicle!
Our open source tail-sitter platform, now called the ‘Phoenix’. This repository contains a complete package of design documents, CAD models, simulation tools, and onboard firmware code necessary to build, assemble, fly and experiment with a novel tail-sitter aerial vehicle!
Certifiable Extrinsic Calibration
MATLAB and Python code for fast and certifiably globally optimal extrinsic calibration of egomotion sensors (e.g., cameras, lidars, GNSS-INS, and shaft encoders). Uses CVX and cvxpy to model and solve convex optimization problems. Example scripts and experiments from our publications are also provided.
MATLAB and Python code for fast and certifiably globally optimal extrinsic calibration of egomotion sensors (e.g., cameras, lidars, GNSS-INS, and shaft encoders). Uses CVX and cvxpy to model and solve convex optimization problems. Example scripts and experiments from our publications are also provided.
Sun-BCNN
Training and test files for a Bayesian Convolutional Neural Network (implemented in Caffe) that can infer sun direction to within 10 degrees on most images. Preprocessed data and ground truth sun directions for the KITTI odometry benchmarks are also provided.
Training and test files for a Bayesian Convolutional Neural Network (implemented in Caffe) that can infer sun direction to within 10 degrees on most images. Preprocessed data and ground truth sun directions for the KITTI odometry benchmarks are also provided.
pykitti
This package provides a minimal set of tools for working with the KITTI dataset in Python.
Importing KITTI data is as easy as:
This package provides a minimal set of tools for working with the KITTI dataset in Python.
Importing KITTI data is as easy as:
data = pykitti.raw('/your/dataset/dir', '2011_09_26', '0019'). MSCKF SWF Comparison
Supporting code for Lee Clement’s and Valentin Peretroukhin’s CRV paper: The Battle for Filter Supremacy: A Comparative Study of the Multi-State Constraint Kalman Filter and the Sliding Window Filter.
Supporting code for Lee Clement’s and Valentin Peretroukhin’s CRV paper: The Battle for Filter Supremacy: A Comparative Study of the Multi-State Constraint Kalman Filter and the Sliding Window Filter.