Simulating a Dextrous Hand For Robotics With OpenUSD
TL;DR
This hands-on course presents a workflow for configuring robot simulations using OpenUSD and PhysX in NVIDIA Isaac Sim, with an emphasis on physics tuning, stability, and asset authoring best practices, and situates OpenUSD’s composability within the broader physical AI ecosystem.
Abstract
Accurate, stable simulation is foundational to robot learning, digital twins, and physical AI. This hands-on course presents a workflow for configuring robot simulations using OpenUSD and PhysX in NVIDIA Isaac Sim, with an emphasis on physics tuning, stability, and asset authoring best practices. The course frames physics tuning as a prerequisite for meaningful training and evaluation, and situates OpenUSD’s composability within the broader physical AI ecosystem. Attendees work with a production Inspire underactuated robot hand asset, inspecting the scene—joints, masses, and collision shapes—to diagnose why the asset fails to simulate stably. Through guided activities, they configure colliders, select appropriate collision shapes, apply collision filters, and resolve overlapping-collider artifacts. They then configure joint drives and tune PD gains—stiffness and damping—using the Gain Tuner to achieve stable, responsive behavior. The session concludes with a demonstration of the tuned asset and an overview of downstream workflows in Isaac Lab. Outcomes include a repeatable workflow for preparing robot USDs for simulation, established best practices for colliders and joint drives, and hands-on experience with OpenUSD and PhysX in a production-grade toolchain.