Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ASAP: Automated Sequence Planning for Complex Robotic Assembly with Physical Feasibility

Yunsheng Tian, Karl D. D. Willis, Bassel Al Omari, Jieliang Luo, Pingchuan Ma, Yichen Li, Farhad Javid, Edward Gu, Joshua Jacob, Shinjiro Sueda, Hui Li, Sachin Chitta, Wojciech Matusik

TL;DR

This paper presents ASAP, a physics-based planning approach for automatically generating such a sequence for general-shaped assemblies that 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.

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. Project website: asap.csail.mit.edu

ASAP: Automated Sequence Planning for Complex Robotic Assembly with Physical Feasibility

TL;DR

This paper presents ASAP, a physics-based planning approach for automatically generating such a sequence for general-shaped assemblies that 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.

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. Project website: asap.csail.mit.edu
Paper Structure (25 sections, 5 figures, 2 tables, 2 algorithms)

This paper contains 25 sections, 5 figures, 2 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Assembly sequence planning
  4. Physics-based simulation for assembly
  5. Learning for assembly sequence planning
  6. Physically feasible sequence planning
  7. Disassembly tree search
  8. Node selection
  9. Part selection
  10. Geometric heuristic
  11. Learning-based
  12. Pose selection
  13. Feasibility check for assembly sequences
  14. Physics-based simulation for assembly
  15. Disassembly path planning
  16. ...and 10 more sections

Figures (5)

  • Figure 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.
  • Figure 2: An example disassembly tree where nodes represent partial assemblies and edges represent feasible (green) and infeasible (red) disassembly actions.
  • Figure 3: Network architecture for learning part disassembly priority. Given an assembly as input, a graph neural network is used to predict the next part to be removed.
  • Figure 4: Assembly sequence comparison between ASAP and Assemble Them Alltian2022assemble on camera, train, and gear set.
  • Figure 5: Robotic assembly plans of 3D printed beams generated by ASAP executed in simulation (top row) and real-world (bottom row).