Bayesian estimation of non-rigid mechanical parameters using temporal sequences of deformation samples

Yang, Shan

doi:10.1109/icra.2016.7487594

Cited by 2 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Marker‐less methods exist and often use a physics‐based probabilistic approach to track the deformation of the soft object. This is quite robust to noise and occlusion [YL16, WWY*15, WDK*20].…”

Section: Previous Workmentioning

confidence: 99%

“…Selecting correct parameter values in material models is important in a wide range of areas such as modelling soft tissue [BT07], cloth [BTH*03, WOR11, MBT*12, MTB*13, YLL17, SNW20], fabrication [BKS*12, STC*13, CLSM15, CLMK17, YLYW18, WWY*15, WDK*20], haptics [VCO20, PKLD20] and robotics [YL16, BCC17, BBPC19, BSB*20, HBBC19, SLK*20]. Our work is inspired by the problem of producing a computer model of a soft robot that visually matches reality.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Differentiable Depth for Real2Sim Calibration of Soft Body Simulations

Arnavaz

Nielsen

Kry

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

In this work, we present a novel approach for calibrating material model parameters for soft body simulations using real data. We use a fully differentiable pipeline, combining a differentiable soft body simulator and differentiable depth rendering, which permits fast gradient-based optimizations. Our method requires no data pre-processing, and minimal experimental set-up, as we directly minimize the L2-norm between raw LIDAR scans and rendered simulation states. In essence, we provide the first markerfree approach for calibrating a soft-body simulator to match observed real-world deformations. Our approach is inexpensive as it solely requires a consumer-level LIDAR sensor compared to acquiring a professional marker-based motion capture system. We investigate the effects of different material parameterizations and evaluate convergence for parameter optimization in both single and multi-material scenarios of varying complexity. Finally, we show that our set-up can be extended to optimize for dynamic behaviour as well.

show abstract

Section: Previous Workmentioning

confidence: 99%