UM-ARM-Lab
The Autonomous Robotic Manipulation Lab studies motion planning, manipulation, and human-robot collaboration.
Built from UM-ARM-Lab's public GitHub profile, University of Michigan. Not on Take My Repo yet, so there are no posts or updates here.
Model Predictive Path Integral (MPPI) with approximate dynamics implemented in pytorch
Volumetric structures such as voxels and SDFs implemented in pytorch
Builds 2D signed distance fields from images, 3D signed distance fields from pointclouds, 3D signed distance fields from Octomap, provides a lightweight signed distance field library, message types for signed distance fields, and tools to compress signed distance fields for transport.
The associated repo for paper "Data-Efficient Learning of Natural Language to Linear Temporal Logic Translators for Robot Task Specification"
Constrained pose Hypothesis Set Elimination official code for pose estimation
Multi-finger Reorientation benchmark featuring sensitive dexterous manipulation tasks
Packages for controlling our robots at a high-level, though simple to use ROS and Python interfaces.
Developmental controllers for the IIWA 7 robot, including a Catkinized version of the Kuka FRI SDK
ROS package for navigation of Clearpath Husky using visual SLAM with a stereo camera
Code accompanying "The Grasp Loop Signature: A Topological Representation for Manipulation Planning with Ropes and Cables"