Parametric tool simplifies robot design and control testing
Draft: A Parametric Tool for Robot Design Exploration
Robotics
Summary
Robot designers face challenges when changing robot shapes and controls because converting designs for testing takes a lot of time. The paper presents Draft, a tool that quickly creates testing-ready robot models without needing CAD software. Draft uses real-world data about robot parts to make sure designs are practical. The authors checked Draft by recreating existing robots with close accuracy and tested different robot designs to see how changes affect robot behavior. This helps engineers try many design ideas and see what works best.
What this means in practice
- •For robot engineers: Quickly generate simulation-ready robot models grounded in real hardware data to evaluate design and control combinations efficiently.
- •For robotics simulation developers: Integrate fast parametric robot model generation into simulation platforms to support diverse robot designs without creating CAD models for each variant.
Authors
David Nguyen, Marcelo Coelho, Sangbae Kim
Abstract
Robot performance is often limited by the cost of iterating on morphology and control together, since every computer-aided design (CAD) change has to be carried into a simulation-ready model before control work begins. Co-design methods attempt to close this gap, but each uses a model generator written for a single platform or lack the use of real-world data to suggest that designs are plausible. We present Draft, a parametric generation tool whose generalized engine compiles any parametric tree of serial chains into a simulation-ready MJCF model, without CAD. It allows engineers to explore design tradeoffs through easily adjustable models and evaluate how changes influence controller performance. Draft grounds the free parameters of each design using trends fitted to a survey of $114$ actuators and $49$ published robot descriptions, so that a generated robot is anchored to real-world hardware. We validate those trends wholistically by building twins of four off-the-shelf robots, whose masses agree to $1.10\times$ geometric mean fold error. Finally, we demonstrate how Draft exposes design tradeoffs by evaluating three quadrupeds through a two-stage reinforcement learning curriculum.