Skip to content
View darshmenon's full-sized avatar

Block or report darshmenon

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
darshmenon/README.md

Darsh Menon

Robotics engineer focused on perception, planning, and learning for autonomous systems

LinkedInPortfolioRoboCloud Dashboard


End-to-end autonomous robots on ROS 2 — RL for manipulation/locomotion, CV for perception, expressive HRI, world models + VLAs for long-horizon tasks. Stack: ROS 2, MuJoCo, Nav2, SLAM, MoveIt 2, Open-RMF.

What I Build

  • Manipulation & Locomotion: UR arms + Robotiq grippers, CHAMP quadruped, RL policies via ROS 2 policy nodes
  • Animatronics & HRI: 25-servo Dynamixel face, multimodal emotion recognition, lip sync transformer, and a Three.js-based 3D avatar simulation
  • Navigation & Fleet: Nav2 + SLAM Toolbox, Open-RMF for multi-robot coordination

Open to robotics/AI/RL/CV/HRI collaborators building real deployable systems.

GitHub Stats

Support

Buy Me A Coffee

📧 darshmenon02@gmail.comLinkedIn

Pinned Loading

  1. UR3_ROS2_PICK_AND_PLACE UR3_ROS2_PICK_AND_PLACE Public

    UR Robotic Arm with Robotiq 2-Finger Gripper for ROS2

    C++ 61 6

  2. rosnav rosnav Public

    Full-stack ROS 2 autonomous navigation: Nav2, SLAM Toolbox, RTAB-Map & ORB-SLAM3 VSLAM, Gazebo Harmonic, Docker, multi-robot fleet coordination, collaborative loop closure, coordinated frontier exp…

    Python 48 9

  3. quadruped-robotics-stack quadruped-robotics-stack Public

    Unitree Go2 quadruped robot dog — RL locomotion training (MuJoCo + Gazebo Harmonic), ROS2 CHAMP and Quad-SDK NMPC walking controllers, PPO policy, keyboard teleop, and multi-terrain simulation

    C++ 18 6

  4. pickplace-rl-mobile-manipulator pickplace-rl-mobile-manipulator Public

    Mobile manipulator pick-and-place via reinforcement learning — UR3 arm on a diff-drive base, trained end-to-end with TQC in Gazebo/ROS2

    C++ 29 1

  5. ur-arm-rl ur-arm-rl Public

    Reinforcement learning environment for UR5e arms with MuJoCo 3 — SAC training for reach, pick-and-place, and symmetric multi-arm cooperative tasks. Includes a ROS 2 policy node for Gazebo deployment.

    Python 6 1

  6. rl-bipedal-walking rl-bipedal-walking Public

    Reinforcement learning (PPO) and whole-body control for humanoid bipedal locomotion, with MuJoCo/Isaac Gym training, QP-based balance and push-recovery, and ROS 2 sim-to-real deployment on Unitree …

    Python 3