Simulation-based Bayesian inference for multi-fingered robotic grasping

• URL: http://arxiv.org/abs/2109.14275v1
• Date: Wed, 29 Sep 2021 08:44:36 GMT
• Title: Simulation-based Bayesian inference for multi-fingered robotic grasping
• Authors: Norman Marlier, Olivier Br\"uls, Gilles Louppe
• Abstract summary: Multi-fingered robotic grasping is an undeniable stepping stone to universal picking and dexterous manipulation. Yet, multi-fingered grippers remain challenging to control because of their rich nonsmooth contact dynamics or because of noise. We propose a novel simulation-based approach for full Bayesian inference based on a deep neural network surrogate of the likelihood-to-evidence ratio.
• Score: 6.677646909984405
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Multi-fingered robotic grasping is an undeniable stepping stone to universal picking and dexterous manipulation. Yet, multi-fingered grippers remain challenging to control because of their rich nonsmooth contact dynamics or because of sensor noise. In this work, we aim to plan hand configurations by performing Bayesian posterior inference through the full stochastic forward simulation of the robot in its environment, hence robustly accounting for many of the uncertainties in the system. While previous methods either relied on simplified surrogates of the likelihood function or attempted to learn to directly predict maximum likelihood estimates, we bring a novel simulation-based approach for full Bayesian inference based on a deep neural network surrogate of the likelihood-to-evidence ratio. Hand configurations are found by directly optimizing through the resulting amortized and differentiable expression for the posterior. The geometry of the configuration space is accounted for by proposing a Riemannian manifold optimization procedure through the neural posterior. Simulation and physical benchmarks demonstrate the high success rate of the procedure.

Related papers

• DeepCloth-ROB$^2_{\text{QS}}$P&P: Towards a Robust Robot Deployment for Quasi-Static Pick-and-Place Cloth-Shaping Neural Controllers [2.720296126199296]
  The fidelity gap between simulation-trained vision-based data-driven cloth neural controllers and real-world operation impedes reliable deployment of methods from simulation into physical trials. We propose DeepCloth-ROB$2_textQS$P&P with a simulation-to-reality transfer strategy Towel-Sim2Real and a cloth grasping protocol. Our approach allows us to compare multiple neural controllers in a real environment for the first time, offering valuable insights to the cloth manipulation community.
  arXiv  Detail & Related papers  (2024-09-23T16:08:16Z)
• Amortized Bayesian Decision Making for simulation-based models [11.375835331641548]
  We address the question of how to perform Bayesian decision making on simulators. Our method trains a neural network on simulated data and can predict the expected cost. We then apply the method to infer optimal actions in a real-world simulator in the medical neurosciences.
  arXiv  Detail & Related papers  (2023-12-05T11:29:54Z)
• Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability [50.44439018155837]
  We propose to include a calibration term directly into the training objective of the neural model. By introducing a relaxation of the classical formulation of calibration error we enable end-to-end backpropagation. It is directly applicable to existing computational pipelines allowing reliable black-box posterior inference.
  arXiv  Detail & Related papers  (2023-10-20T10:20:45Z)
• DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation [81.11585774044848]
  We present DeepSimHO, a novel deep-learning pipeline that combines forward physics simulation and backward gradient approximation with a neural network. Our method noticeably improves the stability of the estimation and achieves superior efficiency over test-time optimization.
  arXiv  Detail & Related papers  (2023-10-11T05:34:36Z)
• Learning to Simulate Tree-Branch Dynamics for Manipulation [26.808346972775368]
  We propose to use a simulation driven inverse inference approach to model the dynamics of tree branches under manipulation. We show that our model can predict deformation trajectories, quantify the estimation uncertainty, and it can perform better when base-lined against other inference algorithms.
  arXiv  Detail & Related papers  (2023-06-06T05:17:02Z)
• Implicit representation priors meet Riemannian geometry for Bayesian robotic grasping [5.533353383316288]
  In this study, we explore the use of implicit representations to construct scene-dependent priors. Results from both simulation and physical benchmarks showcase the high success rate and promising potential of this approach.
  arXiv  Detail & Related papers  (2023-04-18T08:08:14Z)
• Simulation-based Bayesian inference for robotic grasping [6.218934678555297]
  General robotic grippers are challenging to control because of their rich nonsmooth contact dynamics and the many sources of uncertainties due to the environment or sensor noise. In this work, we demonstrate how to compute 6-DoF grasp poses using simulation-based Bayesian inference.
  arXiv  Detail & Related papers  (2023-03-10T11:56:56Z)
• Neural Posterior Estimation with Differentiable Simulators [58.720142291102135]
  We present a new method to perform Neural Posterior Estimation (NPE) with a differentiable simulator. We demonstrate how gradient information helps constrain the shape of the posterior and improves sample-efficiency.
  arXiv  Detail & Related papers  (2022-07-12T16:08:04Z)
• Nonprehensile Riemannian Motion Predictive Control [57.295751294224765]
  We introduce a novel Real-to-Sim reward analysis technique to reliably imagine and predict the outcome of taking possible actions for a real robotic platform. We produce a closed-loop controller to reactively push objects in a continuous action space. We observe that RMPC is robust in cluttered as well as occluded environments and outperforms the baselines.
  arXiv  Detail & Related papers  (2021-11-15T18:50:04Z)
• Probabilistic Human Motion Prediction via A Bayesian Neural Network [71.16277790708529]
  We propose a probabilistic model for human motion prediction in this paper. Our model could generate several future motions when given an observed motion sequence. We extensively validate our approach on a large scale benchmark dataset Human3.6m.
  arXiv  Detail & Related papers  (2021-07-14T09:05:33Z)
• Harnessing Heterogeneity: Learning from Decomposed Feedback in Bayesian Modeling [68.69431580852535]
  We introduce a novel GP regression to incorporate the subgroup feedback. Our modified regression has provably lower variance -- and thus a more accurate posterior -- compared to previous approaches. We execute our algorithm on two disparate social problems.
  arXiv  Detail & Related papers  (2021-07-07T03:57:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.