Gradient-Based Trajectory Optimization With Learned Dynamics
- URL: http://arxiv.org/abs/2204.04558v3
- Date: Sun, 25 Jun 2023 16:40:36 GMT
- Title: Gradient-Based Trajectory Optimization With Learned Dynamics
- Authors: Bhavya Sukhija, Nathanael K\"ohler, Miguel Zamora, Simon Zimmermann,
Sebastian Curi, Andreas Krause, Stelian Coros
- Abstract summary: We use machine learning techniques to learn a differentiable dynamics model of the system from data.
We show that a neural network can model highly nonlinear behaviors accurately for large time horizons.
In our hardware experiments, we demonstrate that our learned model can represent complex dynamics for both the Spot and Radio-controlled (RC) car.
- Score: 80.41791191022139
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Trajectory optimization methods have achieved an exceptional level of
performance on real-world robots in recent years. These methods heavily rely on
accurate analytical models of the dynamics, yet some aspects of the physical
world can only be captured to a limited extent. An alternative approach is to
leverage machine learning techniques to learn a differentiable dynamics model
of the system from data. In this work, we use trajectory optimization and model
learning for performing highly dynamic and complex tasks with robotic systems
in absence of accurate analytical models of the dynamics. We show that a neural
network can model highly nonlinear behaviors accurately for large time
horizons, from data collected in only 25 minutes of interactions on two
distinct robots: (i) the Boston Dynamics Spot and an (ii) RC car. Furthermore,
we use the gradients of the neural network to perform gradient-based trajectory
optimization. In our hardware experiments, we demonstrate that our learned
model can represent complex dynamics for both the Spot and Radio-controlled
(RC) car, and gives good performance in combination with trajectory
optimization methods.
Related papers
- Learning Low-Dimensional Strain Models of Soft Robots by Looking at the Evolution of Their Shape with Application to Model-Based Control [2.058941610795796]
This paper introduces a streamlined method for learning low-dimensional, physics-based models.
We validate our approach through simulations with various planar soft manipulators.
Thanks to the capability of the method of generating physically compatible models, the learned models can be straightforwardly combined with model-based control policies.
arXiv Detail & Related papers (2024-10-31T18:37:22Z) - Real-to-Sim: Predicting Residual Errors of Robotic Systems with Sparse
Data using a Learning-based Unscented Kalman Filter [65.93205328894608]
We learn the residual errors between a dynamic and/or simulator model and the real robot.
We show that with the learned residual errors, we can further close the reality gap between dynamic models, simulations, and actual hardware.
arXiv Detail & Related papers (2022-09-07T15:15:12Z) - Model-Based Reinforcement Learning with SINDy [0.0]
We propose a novel method for discovering the governing non-linear dynamics of physical systems in reinforcement learning (RL)
We establish that this method is capable of discovering the underlying dynamics using significantly fewer trajectories than state of the art model learning algorithms.
arXiv Detail & Related papers (2022-08-30T19:03:48Z) - Human Trajectory Prediction via Neural Social Physics [63.62824628085961]
Trajectory prediction has been widely pursued in many fields, and many model-based and model-free methods have been explored.
We propose a new method combining both methodologies based on a new Neural Differential Equation model.
Our new model (Neural Social Physics or NSP) is a deep neural network within which we use an explicit physics model with learnable parameters.
arXiv Detail & Related papers (2022-07-21T12:11:18Z) - Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate
Model Predictive Trajectory Tracking [76.27433308688592]
Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation.
We present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience.
Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions.
arXiv Detail & Related papers (2022-06-07T13:51:35Z) - STEADY: Simultaneous State Estimation and Dynamics Learning from
Indirect Observations [17.86873192361793]
Many state-of-the-art approaches in learning kinodynamic models require precise measurements of robot states as labeled input/output examples.
We propose a new technique for learning neural kinodynamic models by performing simultaneous state estimation and dynamics learning.
Our approach achieves significantly higher accuracy but is also more robust to observation noise, thereby showing promise for boosting the performance of many other robotics applications.
arXiv Detail & Related papers (2022-03-02T18:25:56Z) - Efficient Differentiable Simulation of Articulated Bodies [89.64118042429287]
We present a method for efficient differentiable simulation of articulated bodies.
This enables integration of articulated body dynamics into deep learning frameworks.
We show that reinforcement learning with articulated systems can be accelerated using gradients provided by our method.
arXiv Detail & Related papers (2021-09-16T04:48:13Z) - Iterative Semi-parametric Dynamics Model Learning For Autonomous Racing [2.40966076588569]
We develop and apply an iterative learning semi-parametric model, with a neural network, to the task of autonomous racing.
We show that our model can learn more accurately than a purely parametric model and generalize better than a purely non-parametric model.
arXiv Detail & Related papers (2020-11-17T16:24:10Z) - Trajectory-wise Multiple Choice Learning for Dynamics Generalization in
Reinforcement Learning [137.39196753245105]
We present a new model-based reinforcement learning algorithm that learns a multi-headed dynamics model for dynamics generalization.
We incorporate context learning, which encodes dynamics-specific information from past experiences into the context latent vector.
Our method exhibits superior zero-shot generalization performance across a variety of control tasks, compared to state-of-the-art RL methods.
arXiv Detail & Related papers (2020-10-26T03:20:42Z) - Automatic Differentiation and Continuous Sensitivity Analysis of Rigid
Body Dynamics [15.565726546970678]
We introduce a differentiable physics simulator for rigid body dynamics.
In the context of trajectory optimization, we introduce a closed-loop model-predictive control algorithm.
arXiv Detail & Related papers (2020-01-22T03:54:00Z)
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.