NeuralSim: Augmenting Differentiable Simulators with Neural Networks
Explore this paper's citation graph
- Type
- preprint
- Published
- 2020-11-09
- Cited by
- 181
- References
- 60
- Access
- Open access
- OpenAlex
- https://openalex.org/W3098074920
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:226281782
Keywords
Computer science, Differentiable function, Artificial neural network, Physics engine, Solver
References
- Rigid Body Dynamics Algorithms
- Stabilization of constraints and integrals of motion in dynamical systems
- A Sparse-Group Lasso
- Coefficient of Restitution Interpreted as Damping in Vibroimpact
- An implicit time-stepping scheme for rigid body dynamics with Coulomb friction
- Fast, Robust Adaptive Control by Learning only Forward Models
- Robot juggling: implementation of memory-based learning
- MuJoCo: A physics engine for model-based control
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- The Stan Math Library: Reverse-Mode Automatic Differentiation in C++
- Automatic Differentiation of Rigid Body Dynamics for Optimal Control and Estimation
- OSQP: an operator splitting solver for quadratic programs
- Sparse-Input Neural Networks for High-dimensional Nonparametric Regression and Classification
- A 3D ellipsoidal volumetric foot–ground contact model for forward dynamics
- Parallel Monotonic Basin Hopping for Low Thrust Trajectory Optimization
- Data-Augmented Contact Model for Rigid Body Simulation
- DART: Dynamic Animation and Robotics Toolkit
- Analytical Derivatives of Rigid Body Dynamics Algorithms
- Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing
- End-to-End Differentiable Physics for Learning and Control
Cited by
- Data-Augmented Contact Model for Rigid Body Simulation
- Fundamental Challenges in Deep Learning for Stiff Contact Dynamics
- A Review of Physics Simulators for Robotic Applications
- Efficient Analytical Derivatives of Rigid-Body Dynamics Using Spatial Vector Algebra
- Design and Control of Soft Robots Using Differentiable Simulation
- DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cutting
- Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulation
- GRiD: GPU-Accelerated Rigid Body Dynamics with Analytical Gradients
- Fast Contact-Implicit Model Predictive Control
- Robot Learning From Randomized Simulations: A Review
- Differentiable Simulation of Soft Multi-body Systems
- SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learning
- The Free Energy Principle for Perception and Action: A Deep Learning Perspective
- Leveraging Reward Gradients For Reinforcement Learning in Differentiable Physics Simulations
- Accelerated Policy Learning with Parallel Differentiable Simulation
- Model Based Meta Learning of Critics for Policy Gradients
- Direct Policy Optimization with Differentiable Physical Consistency for Dexterous Manipulation
- Collective intelligence for deep learning: A survey of recent developments
- The Use of Deep Learning Model for Effect Analysis of Conventional Friction Power Confinement
- Dojo: A Differentiable Simulator for Robotics
Related papers
- End-to-End Differentiable Physics for Learning and Control
- Combining Physical Simulators and Object-Based Networks for Control
- Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing
- Automatic Differentiation and Continuous Sensitivity Analysis of Rigid Body Dynamics
- Fast Neural Network Emulation and Control of Dynamical Systems
- NeuroAnimator: fast neural network emulation and control of physics-based models
- PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics
- Towards Commoditizing Simulations of System Models Using Recurrent Neural Networks
- Simulated Data Generation through Algorithmic Force Coefficient Estimation for AI-Based Robotic Projectile Launch Modeling