• Corpus ID: 227012590

A User's Guide to Calibrating Robotics Simulators

@article{Mehta2020AUG,
  title={A User's Guide to Calibrating Robotics Simulators},
  author={Bhairav Mehta and Ankur Handa and Dieter Fox and Fabio Tozeto Ramos},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.08985}
}
Simulators are a critical component of modern robotics research. Strategies for both perception and decision making can be studied in simulation first before deployed to real world systems, saving on time and costs. Despite significant progress on the development of sim-to-real algorithms, the analysis of different methods is still conducted in an ad-hoc manner, without a consistent set of tests and metrics for comparison. This paper fills this gap and proposes a set of benchmarks and a… 
View PDF on arXiv
View With Semantic Reader
7 Citations
Background Citations
3
Methods Citations
2

7 Citations

Citation Type

Citation Type

Robot Learning From Randomized Simulations: A Review
TLDR
A comprehensive review of sim-to-real research for robotics, focusing on a technique named “domain randomization” which is a method for learning from randomized simulations.
DiSECt: A Differentiable Simulator for Parameter Inference and Control in Robotic Cutting
TLDR
DiSECt: the first differentiable simulator for cutting soft materials is presented, showing that the simulator can be calibrated to match resultant forces and deformation from a state-of-the-art commercial solver and real-world cutting datasets, with generality across cutting velocities and object instances.
DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cutting
TLDR
DiSECt: the first differentiable simulator for cutting soft materials is presented, which can be calibrated to match resultant forces and deformation fields from a state-of-the-art commercial solver and real-world cutting datasets, with generality across cutting velocities and object instances.
Neural Posterior Domain Randomization
TLDR
NPDR is introduced, an algorithm that alternates between learning a policy from a randomized simu lator and adapting the posterior distribution over the simulator’s parameters in a Bayesian fashion and can learn transferable policies using fewer real-world rollouts than comparable algorithms.
A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulation
TLDR
This letter forms the real-to-sim problem as probabilistic inference over simulation parameters of deformable objects as well as a principled way to incorporate noisy state observations into modern Bayesian tools for simulation parameter inference.
BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with IsaacGym
TLDR
A library that provides an implementation of BayesSim integrated with the recently released NVIDIA IsaacGym that allows large-scale parameter inference with end-toend GPU acceleration and provides an integration with TensorBoard to easily visualize slices of high-dimensional posteriors.
Scene Understanding and Distribution Modeling with Mixed-Integer Scene Parsing
We present a probabilistic procedural modeling strategy for capturing the distribution of scenes of varying numbers of rigid objects, motivated by the need for such models to enable verification of…

References

SHOWING 1-10 OF 42 REFERENCES
Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
TLDR
By randomizing the dynamics of the simulator during training, this paper is able to develop policies that are capable of adapting to very different dynamics, including ones that differ significantly from the dynamics on which the policies were trained.
Assessing Transferability From Simulation to Reality for Reinforcement Learning
TLDR
An algorithm called Simulation-based Policy Optimization with Transferability Assessment (SPOTA) which uses an estimator of the SOB to formulate a stopping criterion for training and is able to learn a control policy exclusively from a randomized simulator, which can be applied directly to real systems without any additional training.
Evolutionary Robotics and the Radical Envelope-of-Noise Hypothesis
TLDR
New ways of thinking about and building simulations upon which fitness assessments of evolving controllers can be performed are outlined and a potential methodology for building simulations in which evolving controllers are forced to satisfy these conditions if they are to be reliably fit is developed.
BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators
TLDR
Results show that the posterior computed from BayesSim can be used for domain randomization outperforming alternative methods that randomize based on uniform priors.
Benchmarking Simulated Robotic Manipulation Through a Real World Dataset
We present a benchmark to facilitate simulated manipulation; an attempt to overcome the obstacles of physical benchmarks through the distribution of a real world, ground truth dataset. Users are…
Domain randomization for transferring deep neural networks from simulation to the real world
TLDR
This paper explores domain randomization, a simple technique for training models on simulated images that transfer to real images by randomizing rendering in the simulator, and achieves the first successful transfer of a deep neural network trained only on simulated RGB images to the real world for the purpose of robotic control.
Model-Based Generalization Under Parameter Uncertainty Using Path Integral Control
This letter addresses the problem of robot interaction in complex environments where online control and adaptation is necessary. By expanding the sample space in the free energy formulation of path…
Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience
TLDR
This work adapts the simulation parameter distribution using a few real world roll-outs interleaved with policy training to improve the policy transfer by matching the policy behavior in simulation and the real world.
RoboNet: Large-Scale Multi-Robot Learning
TLDR
This paper proposes RoboNet, an open database for sharing robotic experience, which provides an initial pool of 15 million video frames, from 7 different robot platforms, and studies how it can be used to learn generalizable models for vision-based robotic manipulation.
(CAD)$^2$RL: Real Single-Image Flight without a Single Real Image
TLDR
This paper proposes a learning method that they call CAD$^2$RL, which can be used to perform collision-free indoor flight in the real world while being trained entirely on 3D CAD models, and shows that it can train a policy that generalizes to thereal world, without requiring the simulator to be particularly realistic or high-fidelity.
...
1
2
3
4
5
...