Using Mujoco and Gymansium, RL Training of Kinova robot arm to move from random start position to goal position in the absence of obstacles. Trained on PPO for 50 million and 20 million timesteps.
Finetuning and deploying Octo, a VLA on a Kinova Gen3 (7-DoF) robot for goal-image-conditioned bottle pick-and-lift using diffusion arm actions, a BCE gripper head, and latency-aware receding-horizon control.
A simple and explicit vision guided pick and place using Kinova Gen3, Intel RealSense, Kortex API, and ArUco marker
ROS-based Kinova Gen3 Lite demo for unseen-object grasping using RGB-D perception and calibration
A lightweight wrapper around Kinova Kortex API to work with Gen3 Lite robotic arms.
A lightweight command interface for executing Kinova Gen 3 7-DoF robot arm skills using typed natural-language-style commands, cartesian motion primitives, gripper control, and ArUco-based object pose detection.
Kinova RL with avoidance of static and dynamic obstacles integrated using curriculum learning
Add a description, image, and links to the kinova-gen3 topic page so that developers can more easily learn about it.
To associate your repository with the kinova-gen3 topic, visit your repo's landing page and select "manage topics."