Personal tools
You are here: Home Projects In-house Projects Robust 2D Assembly Sequencing via Geometric Planning with Learned Scores Robust 2D Assembly Sequencing via Geometric Planning with Learned Scores
« December 2020 »
December
SuMoTuWeThFrSa
12345
6789101112
13141516171819
20212223242526
2728293031
Log in


Forgot your password?
 

Robust 2D Assembly Sequencing via Geometric Planning with Learned Scores

Abstract

To compute robust 2D assembly plans, we present an approach that combines geometric planning with a deep neural network. We train the network using the Box2D physics simulator with added stochastic noise to yield robustness scores—the success probabilities of planned assembly motions. As running a simulation for every assembly motion is impractical, we train a convolutional neural network to map assembly operations, given as an image pair of the subassemblies before and after they are mated, to a robustness score. The neural network prediction is used within a planner to quickly prune out motions that are not robust. We demonstrate this approach on two-handed planar assemblies, where the motions are one-step translations. Results suggest that the neural network can learn robustness to plan robust sequences an order of magnitude faster than physics simulation.

highbad

 

Figure: (Left) A robust assembly operation, which we find as part of the assembly sequencing, versus an operation that is not (Right), which we opt to avoid.

 

Links

  • Tzvika Geft, Aviv Tamar, Ken Goldberg, Dan Halperin
    Robust 2D Assembly Sequencing via Geometric Planning with Learned Scores
    2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)
    IEEE Xplore
     [link]

Contacts

Tzvika Geft   null
Dan Halperin http://acg.cs.tau.ac.il/danhalperin danha@post.tau.ac.il
Document Actions