Publication 2024
ASAP
Automated Sequence Planning for Complex Robotic Assembly with Physical Feasibility
Fig. 1: Assembly plans generated autonomously from ASAP for a desk positioned on a rotary table including physically feasible assembly sequences, collision-free paths, gravitationally stable poses, gripper grasps, and robot arm motion.
Abstract
The automated assembly of complex products requires a system that can automatically plan a physically feasible sequence of actions for assembling many parts together. In this paper, we present ASAP, a physics-based planning approach for automatically generating such a sequence for general-shaped assemblies. ASAP accounts for gravity to design a sequence where each sub-assembly is physically stable with a limited number of parts being held and a support surface. We apply efficient tree search algorithms to reduce the combinatorial complexity of determining such an assembly sequence. The search can be guided by either geometric heuristics or graph neural networks trained on data with simulation labels. Finally, we show the superior performance of ASAP at generating physically realistic assembly sequence plans on a large dataset of hundreds of complex product assemblies. We further demonstrate the applicability of ASAP on both simulation and real-world robotic setups.
Download publicationAssociated Researchers
Yunsheng Tian
Massachusetts Institute of Technology
Bassel Al Omari
University of Waterloo
Jieliang (Rodger) Luo
Sr. Principal AI Research Scientist
Pingchuan Ma
Massachusetts Institute of Technology
Yichen Li
Massachusetts Institute of Technology
Edward Gu
Massachusetts Institute of Technology
Joshua Jacob
Massachusetts Institute of Technology
Shinjiro Sueda
Texas A&M University
Wojciech Matusik
Massachusetts Institute of Technology
Related Publications
2024
Autonomous Robotic Assembly of a Skateboard TruckThe Autodesk Research robotics team set out to solve a complex…
2024
Bridging the Sim-to-Real Gap with Dynamic Compliance Tuning for Industrial InsertionA novel framework for robustly learning manipulation skills…
2023
Constrained-Context Conditional Diffusion Models for Imitation LearningA diffusion model policy for solving 6-DoF robotic manipulation tasks…
2022
A force-mediated controller for cooperative object manipulation with independent autonomous robotsWe consider cooperative manipulation by multiple robots assisting a…
Get in touch
Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.
Contact us