Lists (5)
Starred repositories
Autonomous robot navigation using Reinforcement Learning techniques. and DQN
Unified framework for robot learning built on NVIDIA Isaac Sim
ROBOKINE IK-ML is a free Python-based platform for machine learning-based inverse kinematics of configurable serial robot manipulators. It supports robots up to 6 DOF for dataset generation, model …
This project implements and compares multiple reinforcement learning algorithms for multi-robot path planning in grid-based environments with obstacles. The system enables robots to navigate from s…
Multi-agent reinforcement learning for warehouse robot navigation, order assignment, and fleet coordination using DQN, PPO, and MAPPO.
Physical AI learning lab with VLA evaluation, action-representation benchmarks, and browser-based robot policy simulations
Robust Learning from Demonstration Pipeline based on Inertial Motion Capture and Force Tracking for Industrial Demoulding Tasks by Collaborative Robots
Multipal policy locomotions including backclip, noise reduce locomotion, obstacle crossing.Base on concurrent teacher- student architectrue reinforment learning. TRAINING &DEPOLY /EVALUATION CODECODE
UR5e SFP cable insertion — Isaac Lab environment + imitation learning (ACT / Diffusion Policy)
Q-learning simulation for warehouse robot navigation, obstacle avoidance and pickup-to-drop-off path optimisation.
Exploring computational neuroscience and world models for robot learning at the UW Paul G. Allen School's Neural Systems Lab.
A MuJoCo simulation of the UR10e robot arm with Robotiq 2F85 gripper, featuring Gymnasium RL environments, keyboard teleoperation, and automatic demonstration collection. 基于 MuJoCo 的 UR10e 机械臂 + R…
This is a repository for reinforcement learning implementation for PNDbotics robots, based on Mujoco.
A workspace for my multiple projects for robot pick and place learning in Gazebo simulation using UR5e With robotiq gripper with ROS2 Jazzy and python.
RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning
From Vision-Language-Action Models to a Real-World Robot Learning Stack
This repository provides tutorials for reinforcement learning and imitation learning using ROBOTIS robots, and supports Sim2Real functionality for deploying the learned policies on real robots.
LocoVLA - Learn robot control, RL and VLA on a wheeled biped (Upkie + MuJoCo). 58-lesson open course: classical control, state estimation, reinforcement learning, vision-language-action, C++/ROS2 d…
LLM & VLA Collaboration for Robot Curriculum Learning — SKKU Industry-Academic Collaboration Project 2 (Spring–Summer 2026)
A connected visual field guide to reinforcement learning, world models, and vision-language-action robotics
Smooth real-time leader–follower teleoperation for 6-DoF robot arms (Alicia-D → FAIRINO FR3), built for imitation-learning data collection.
Full-stack robot learning for the SO-101 arm: teleoperation, imitation learning, and RL in MuJoCo.
A on-robot reinforcement learning framework for steering vision-language-action models (VLAs)
Robot house sensor based Manifold-Aligned In-Context Learning: Hybrid Retrieval-Augmented Tabular Foundation Models for Ambient Intelligenceroject