Data-Driven Contact Clustering for Robot Simulation

Kim, Myungsin; Yoon, Jaemin; Son, Dongwon; Lee, Dongjun

doi:10.1109/icra.2019.8793938

“…Penetration depth culls bins and contacts with negligible penetration, as these often have minimal impact on dynamics. Data-driven methods train networks to perform the reduction [40], but require a separate data collection and learning phase to be effective.…”

Section: A Contact-rich Simulationmentioning

confidence: 99%

Factory: Fast Contact for Robotic Assembly

Narang¹,

Storey²,

Akinola³

et al. 2022

Robotics: Science and Systems XVIII

View full text Add to dashboard Cite

Robotic assembly is one of the oldest and most challenging applications of robotics. In other areas of robotics, such as perception and grasping, simulation has rapidly accelerated research progress, particularly when combined with modern deep learning. However, accurately, efficiently, and robustly simulating the range of contact-rich interactions in assembly remains a longstanding challenge. In this work, we present Factory, a set of physics simulation methods and robot learning tools for such applications. We achieve real-time or faster simulation of a wide range of contact-rich scenes, including simultaneous simulation of 1000 nut-and-bolt interactions. We provide 60 carefullydesigned part models, 3 robotic assembly environments, and 7 robot controllers for training and testing virtual robots. Finally, we train and evaluate proof-of-concept reinforcement learning policies for nut-and-bolt assembly. We aim for Factory to open the doors to using simulation for robotic assembly, as well as many other contact-rich applications in robotics. Please see our website for supplementary content, including videos. 1

show abstract

“…Penetration depth culls bins and contacts with negligible penetration, as these often have minimal impact on dynamics. Data-driven methods train networks to perform the reduction [41], but require a separate data collection and learning phase to be effective.…”

Section: A Contact-rich Simulationmentioning

confidence: 99%

Factory: Fast Contact for Robotic Assembly

Narang¹,

Storey²,

Akinola³

et al. 2022

Preprint

View full text Add to dashboard Cite

Robotic assembly is one of the oldest and most challenging applications of robotics. In other areas of robotics, such as perception and grasping, simulation has rapidly accelerated research progress, particularly when combined with modern deep learning. However, accurately, efficiently, and robustly simulating the range of contact-rich interactions in assembly remains a longstanding challenge. In this work, we present Factory, a set of physics simulation methods and robot learning tools for such applications. We achieve real-time or faster simulation of a wide range of contact-rich scenes, including simultaneous simulation of 1000 nut-and-bolt interactions. We provide 60 carefullydesigned part models, 3 robotic assembly environments, and 7 robot controllers for training and testing virtual robots. Finally, we train and evaluate proof-of-concept reinforcement learning policies for nut-and-bolt assembly. We aim for Factory to open the doors to using simulation for robotic assembly, as well as many other contact-rich applications in robotics. Please see our website for supplementary content, including videos. 1

show abstract

“…applied regardless of the number of original contact nodes 5) can be calculated regardless of N c . It cannot be achieved by using MLP [16] or Long Short-Term Memory models (LSTM [31]). Further, by using the IN, we can capture the effect of physical interaction between the dynamic characteristics of contact nodes, which can affect the contact force.…”

Section: B Data-driven Contact Clusteringmentioning

confidence: 99%

“…Along the same vein as this paper, an accuracy-optimized data-driven contact clustering for rigid-body contact simulation was proposed in [16]. The contact clustering of [16] however is applicable only for simple primitive-primitive contact scenarios (e.g., cylinder-on-plane contact in [16]), since, from its being based on the (static) architecture of MLP [29] with all the (pre-defined) contact nodes of all the (predefined) meshes as its input, for the target bolting and pegin-hole tasks with complex/non-convex shape objects, it is impossible to learn and real-time compute its MLP, which will become exceedingly large with those massive number of nodes carried with all the time. On the other hand, our proposed data-driven contact clustering, from its instead being based on the (variable) architecture of IN, is scalable for such objects for our target tasks with very complex/non-convex geometries.…”

Section: Introductionmentioning

confidence: 99%

“…In contrast, we formulate this contact clustering as a datadriven machine learning process trained to match the experimental data given the dynamic information (i.e., pose, twist, and wrench) of all the contact points, thereby, significantly improving the contact simulation accuracy. We also adopt IN architecture [15] for this to accommodate vastly-varying contact point set for the two tasks due to their complex/non-convex geometries, that cannot be addressed with other typical learning architectures (e.g., MLP (Multi-Layer Perceptron [16])); • Constraint/energy-based robust contact solving: Given the clustered points (and normals), the process of con-tact solving computes the contact force for each point using relevant physics principles. For this, two main methodologies exist: penalty-based method (e.g., [17], [18]) and constraint-based method (e.g., [19], [20]), with the latter preferred when the accuracy is concerned, since the former, from its relying on virtual springs, typically cannot precisely enforce physical principles of contact (e.g., Signorini condition for no penetration [21],…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast and Accurate Data-Driven Simulation Framework for Contact-Intensive Tight-Tolerance Robotic Assembly Tasks

Yoon¹,

Lee²,

Son³

et al. 2022

Preprint

Self Cite

0

View full text Add to dashboard Cite

We propose a novel fast and accurate simulation framework for contact-intensive tight-tolerance robotic assembly tasks. The key components of our framework are as follows: 1) data-driven contact point clustering with a certain variableinput network, which is explicitly trained for simulation accuracy (with real experimental data) and able to accommodate complex/non-convex object shapes; 2) contact force solving, which precisely/robustly enforces physics of contact (i.e., no penetration, Coulomb friction, maximum energy dissipation) with contact mechanics of contact nodes augmented with that of their object; 3) contact detection with a neural network, which is parallelized for each contact point, thus, can be computed very quickly even for complex shape objects with no exhaust pair-wise test; and 4) time integration with PMI (passive mid-point integration [1]), whose discrete-time passivity improves overall simulation accuracy, stability, and speed. We then implement our proposed framework for two widely-encountered/benchmarked contactintensive tight-tolerance tasks, namely, peg-in-hole assembly and bolt-nut assembly, and validate its speed and accuracy against real experimental data. It is worthwhile to mention that our proposed simulation framework is applicable to other general contact-intensive tight-tolerance robotic assembly tasks as well. We also compare its performance with other physics engines and manifest its robustness via haptic rendering of virtual bolting task.

show abstract

Data-Driven Contact Clustering for Robot Simulation

Cited by 6 publications

References 29 publications

Factory: Fast Contact for Robotic Assembly

Factory: Fast Contact for Robotic Assembly

Factory: Fast Contact for Robotic Assembly

Fast and Accurate Data-Driven Simulation Framework for Contact-Intensive Tight-Tolerance Robotic Assembly Tasks

Contact Info

Product

Resources

About