AI Agent Skills

K-Sim Gym: Making robots useful with RL. Built on top of K-Sim.

Jiminy: a fast and portable Python/C++ simulator of poly-articulated robots with OpenAI Gym interface for reinforcement learning

RosTeamWorkspace is a framework for boosting collaboration in teams when developing software for robots using Robot Operating System (ROS1 and ROS2).

BTGenBot: a system to generate behavior trees for robots using lightweight (~7 billion parameters) large language models (LLMs)

High-Level Motion Library for Collaborative Robots

Controlling diverse robots by inferring jacobian fields with deep networks! Let's make robots understand their bodies!

A modular, real-time controller library for Franka Emika Panda robots

WoLF: Whole-body Locomotion Framework for quadruped robots

A Knowledge Base System for Cognition-enabled Robots

Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models

Invisible Highway is an experiment in controlling physical things in the real world by drawing in AR. Simply make a pathway along the floor on your phone and the robot c…

A trajectory planning framework for multiple robots: paper accepted in IEEE T-RO

⚙️ Zero-Shot Autonomous Robots

Replication package of the paper titled "How do you Architect your Robots? State of the Practice and Guidelines for ROS-based Systems" published at ICSE-SEIP 2020