Software

Open source

https://docs.nav2.org/

Open source

Software for Mark Rober's Domino Robot project.

Research

A reinforcement-learning navigation agent using lidar and camera observations.

Open source

URDF model of the Draco3 humanoid robot.

Research

Robotic system modeling, dynamics and optimization tools.

Open source

Dream to Control: Learning Behaviors by Latent Imagination, implemented in PyTorch.

Open source

Deep reinforcement-learning experiments for robotic grasping from octrees.

Open source

Self-Learning Exploration and Mapping for Mobile Robots via Deep Reinforcement Learning

Open source

End-to-End SLAM with camera calibration, monocular prior integration and dense Rendering

Research

Domain-randomization experiments for closed-loop soft-robot control.

Open source

DSP-SLAM: Object Oriented SLAM with Deep Shape Priors

Open source

Implementation of the D* lite algorithm in Python for "Improved Fast Replanning for Robot Navigation in Unknown Terrain"

Open source

A ROS implementation of the Dynamic Window Approach planner.

Research

1. Prerequisites

Open source

A point-cloud registration pipeline for robot localization and 3D perception.

Open source

A simulation system based on ROS and Gazebo which is specially built for multi-robot task allocation (exploration and destruction problem)

Open source

Master's Thesis on Simultaneous Localization and Mapping in dynamic environments. Separately reconstructs both the static environment and the dynamic objects from it, such as cars.

Research

EAO-SLAM: Monocular Semi-Dense Object SLAM Based on Ensemble Data Association

Open source

Examples of efficient trajectory optimization for robot motion planning

Open source

Robot-centric elevation mapping for rough-terrain navigation.

Open source

ROS meta-package for Elfin robot

Research

SO-ARM101 dual-view ACT experiments with documented runtime safeguards.

Research

Embodied Eval Automation provides workflows for collecting robot-benchmark and simulator episodes.

Open source

Research code for reinforced embodied reasoning in robot manipulation.