Humanoid whole-body motion tracking with one differentiable world model.

An Open Flexible Quadrotor Simulator

SuperMimic: humanoid whole-body control with one differentiable world model — implementation on mjlab / MuJoCo Warp

[RSS 2026] Parallel Differentiable Reachability for Learning and Planning with Certified Neural Dynamics and Controllers

Reachability Engine of [RSS 2026] Parallel Differentiable Reachability for Learning and Planning with Certified Neural Dynamics and Controllers

Multi-drone environment for RL with MuJoCo, with GPU vectorization, wind models, domain randomization, and curriculum learning

Supplemental code for Vision-TL-Action [paper] experiments

[RSS 2024] Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion

[IROS2025] & [RA-L2025] Official Code for GRaD-Nav series

Making it easier to work with shaders

Source code to pbrt, the ray tracer described in the forthcoming 4th edition of the "Physically Based Rendering: From Theory to Implementation" book.

Decision-making for orbital game scenarios

[RA-L/ICRA2024] A differentiable robot learning framework for task specifications and controller synthesis.

VertiSim is a multi-agent discrete-event vertiport network simulator

A parametric aircraft geometry tool

Aircraft Design, Analysis and Optimization Code

This repo is the official implementation of "τ0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation".

Headless A320 systems simulator built on FlyByWire, with a CLI and an MCP server so LLM agents can detect and manage failures following real ECAM/QRH procedures.

The A32NX & A380X Project are community driven open source projects to create free Airbus aircraft in Microsoft Flight Simulator that are as close to reality as possible.

[T-ASE 2026] From Edge to Edge: A Flow-Inspired Scheduling Planner for Multi-Robot Systems.

Multi-robot planning under context uncertainty: infer context, then plan preference-aligned collision-free paths. IROS 2026.

Event-Driven Sleep-Wake Scheduling for Heterogeneous Robots under LTL Constraints (RSS 2026)

Hindsight: Agent Memory That Learns

RobotFleet: An Open-Source Framework for Centralized Multi-Robot Task Planning

Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

Fast Robot Kinematics and Dynamics in JAX

Agnes Harness: A pluggable agent harness for Forward Deployed Engineering (FDE). Built for trust. Made for the real world.

Skills for Real Engineers. Straight from my .agents directory.