# Model Learning (Nov 2023-)

### Next

- [ ] [Robot Model Identification and Learning: A Modern Perspective](https://www.annualreviews.org/doi/pdf/10.1146/annurev-control-061523-102310)

### Paper list

- [ ] [On the Design of LQR Kernels for Efficient Controller Learning](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8264429)
- [ ] [A Tutorial on Energy-based methods](http://yann.lecun.org/exdb/publis/pdf/lecun-06.pdf)
- [ ] [Combining physics and deep learning to learn continuous-time dynamics models](https://journals.sagepub.com/doi/pdf/10.1177/02783649231169492?casa_token=xIxbtWxVJFQAAAAA:IfURj4s0N_Hz-irWV1AljhtUQh3GhXSTLi9Ryzat_576mO2Np_tcJriP-FJzlFaf68WKK-fH4nFW)
- [ ] [ENERGY-BASED MODELS FOR CONTINUAL LEARNING](https://arxiv.org/pdf/2011.12216.pdf)
- [ ] [Can Direct Latent Model Learning Solve Linear Quadratic Gaussian Control?](https://proceedings.mlr.press/v211/tian23a/tian23a.pdf)
- [ ] [Geometric Robot Dynamic Identification: A Convex Programming Approach](https://ieeexplore.ieee.org/abstract/document/8922724)
- [ ] [Robot Model Identification and Learning: A Modern Perspective](https://www.annualreviews.org/doi/pdf/10.1146/annurev-control-061523-102310)
- [ ] [Beyond Inverted Pendulums: Task-optimal Simple Models of Legged Locomotion](https://dair.seas.upenn.edu/assets/pdf/Chen2023b.pdf)
- [ ] [Reinforcement Learning for Reduced-order Models of Legged Robots](https://arxiv.org/abs/2310.09873)
- [ ] [Enabling Efficient, Reliable Real-World Reinforcement Learning with Approximate Physics-Based Models](https://arxiv.org/pdf/2307.08168.pdf)

# Sim-to-real (July-August 2023)

**Next**: Andrew, _Sim-to-Real Transfer with Neural-Augmented Robot Simulation_

## Possible papers

- [ ] [Auto-Tuned Sim-to-Real Transfer](https://ieeexplore.ieee.org/abstract/document/9562091)
- [ ] [On the use of simulation in robotics: Opportunities, challenges, and suggestions for moving forward](https://www.pnas.org/doi/abs/10.1073/pnas.1907856118)
- [x] [Sim-to-Real Transfer with Neural-Augmented Robot Simulation](http://proceedings.mlr.press/v87/golemo18a.html)
- [ ] [ Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks](https://openaccess.thecvf.com/content_CVPR_2019/html/James_Sim-To-Real_via_Sim-To-Sim_Data-Efficient_Robotic_Grasping_via_Randomized-To-Canonical_Adaptation_Networks_CVPR_2019_paper.html)
- [ ] [Learning Locomotion Skills for Cassie: Iterative Design and Sim-to-Real](http://proceedings.mlr.press/v100/xie20a.html)
- [ ] [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://ieeexplore.ieee.org/abstract/document/8460528)
- [x] [Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience](https://ieeexplore.ieee.org/abstract/document/8793789)

# Fabrics (May 2023)

## Papers

### schedule

1. - [x] [Generalized Nonlinear and Finsler Geometry for Robotics](https://arxiv.org/pdf/2010.14745.pdf) **Steve**
2. - [x] [Exploring Kinodynamic Fabrics for Reactive Whole-Body Control of Underactuated Humanoid Robots](https://arxiv.org/pdf/2303.04279.pdf) **Matt**
- based off of [Geometric Fabrics for the Acceleration-based Design of Robotic Motion](https://arxiv.org/abs/2010.14750)
- similar to [Integration of Riemannian Motion Policy and Whole-Body Control for Dynamic Legged Locomotion](https://arxiv.org/abs/2010.14750)
3. - [x] [Learning Riemannian Stable Dynamical Systems via Diffeomorphisms](https://openreview.net/pdf?id=o8dLx8OVcNk) **Glen**
4. - [x] [Neural geometric fabrics: Efficiently learning high-dimensional policies from demonstration](https://proceedings.mlr.press/v205/xie23a/xie23a.pdf) **Steve**

### Assorted possible papers

- [ ] [Riemannian Motion Policies](https://arxiv.org/pdf/1801.02854.pdf) Ratliff, lalala, Fox
- [ ] [Geometric Fabrics: Generalizing Classical Mechanics to Capture the Physics of Behavior](https://ieeexplore.ieee.org/abstract/document/9682604/authors#authors)_Wyk, lalala, Ratliff_ in-depth
- [x] [Neural geometric fabrics: Efficiently learning high-dimensional policies from demonstration](https://proceedings.mlr.press/v205/xie23a/xie23a.pdf), _Xie, lalala, Ratliff, Wyk_ make it deep
- [x] [Generalized nonlinear and finsler geometry for robotics](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9561543) _Ratliff, Wyk, lalala, Rana_ Tutorial intro into math?
- [Extended version of paper](https://arxiv.org/pdf/2010.14745.pdf)
- [ ] [Dynamic Optimization Fabrics for Motion Generation](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10086617) _Spahn, Wisse, Mora_ application paper
- [x] [Learning Riemannian Stable Dynamical Systems via Diffeomorphisms](https://openreview.net/forum?id=o8dLx8OVcNk) _Zhang, Mohammadi, Rozo_ learning dynamics models with fabric properties
- [ ] Hybrid Quadratic Programming - Pullback Bundle Dynamical Systems Control, _Fichera, Billard_
- [ ] [Learning Reactive Motion Policies in Multiple Task Spaces from Human Demonstrations](http://proceedings.mlr.press/v100/rana20a/rana20a.pdf), _Rana, lalala, Ratliff
- [ ] [Euclideanizing flows: Diffeomorphic reduction for learning stable dynamical systems](http://proceedings.mlr.press/v120/rana20a/rana20a.pdf), _Rana, lalala, Ratliff_
- [ ] [Learning control Lyapunov function to ensure stability of dynamical system-based robot reaching motions](https://www.sciencedirect.com/science/article/pii/S0921889014000372) Khansari-Zadeh, Billard
- [ ] [RMPflow: A Geometric Framework for Generation of Multitask Motion Policies
](https://ieeexplore.ieee.org/document/9388869) : nice explanations for the mechanisms of pushforward, pullback, and resolve operators.