umich-bipedlab Goto Github PK
Name: University of Michigan Dynamic Legged Locomotion Robotics Lab
Type: Organization
Bio: We do feedback control of bipedal robots and we do it better than anyone else.
Location: Ann Arbor, MI 48109-2122
Name: University of Michigan Dynamic Legged Locomotion Robotics Lab
Type: Organization
Bio: We do feedback control of bipedal robots and we do it better than anyone else.
Location: Ann Arbor, MI 48109-2122
Gazebo simulator for the Agility Robotics Cassie robot
This repository provides an implementation of a bipedal locomotion controller, described in the paper Terrain-Adaptive, ALIP-Based Bipedal Locomotion Controller via Model Predictive Control and Virtual Constraints(pdf)(arXiv). The controller has two components: (1) an Angular Momentum Linear Inverted Pendulum (ALIP)-based Model Predictive Control (MPC) foot placement planner and (2) a gait controller which takes the foot placement solution as an input. This controller enables improved stability for walking on a variety of sloped and textured terrains. The controller is implemented on the Agility Robotics Cassie Robot.
UDRF model of CASSIE robot
Repo containing the urdf and frost based models of Cassie
Code for various extended Kalman filter state estimation methods for Cassie.
This package provides a CLF-based reactive planning system, described in paper: Efficient Anytime CLF Reactive Planning System for a Bipedal Robot on Undulating Terrain. The reactive planning system consists of a 5-Hz planning thread to guide a robot to a distant goal and a 300-Hz Control-Lyapunov-Function-based (CLF-based) reactive thread to cope with robot deviations. The planning system allowed Cassie Blue to autonomously traverse sinusoidally varying terrain. More experiments are still being conducted and this repo and the paper will be updated accordingly.
Example code for contact-aided invariant extended Kalman filtering.
Continuous Preintegration for Graph-based Visual-Inertial Navigation
This dataset is comprised of simulation and hardware trajectories with various faults for the Digit robot during the task of standing. The simulation trajectories contain abrupt, incipient, and intermittent faults, while the hardware trajectories contain abrupt and incipient faults. A tutorial of the dataset can be found in the viz branch.
Custom ROS messages for digit
This is a package for extrinsic calibration between a 3D LiDAR and a camera, described in paper: Improvements to Target-Based 3D LiDAR to Camera Calibration. This package is used for Cassie Blue's 3D LiDAR semantic mapping and automation.
This package introduces the concept of optimizing target shape to remove pose ambiguity for LiDAR point clouds. Both the simulation and the experimental results confirm that by using the optimal shape and the global solver, we achieve centimeter error in translation and a few degrees in rotation even when a partially illuminated target is placed 30 meters away!
Universal grid map library for mobile robotic mapping
This work proposes an anytime iterative system to concurrently solve the multi-objective path planning problem and determine the visiting order of destinations. The paper has been uploaded to arXiv at https://arxiv.org/abs/2205.14853
A Framework for the Volumetric Integration of Depth Images
Guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and Jetson TX1/TX2.
Julia implementation of the Kinodynamic Fabrics whole-body control framework
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.