Deformable Linear Object Prediction Using Locally Linear Latent Dynamics

• URL: http://arxiv.org/abs/2103.14184v1
• Date: Fri, 26 Mar 2021 00:29:31 GMT
• Title: Deformable Linear Object Prediction Using Locally Linear Latent Dynamics
• Authors: Wenbo Zhang, Karl Schmeckpeper, Pratik Chaudhari, Kostas Daniilidis
• Abstract summary: Prediction of deformable objects (e.g., rope) is challenging due to their non-linear dynamics and infinite-dimensional configuration spaces. We learn a locally linear, action-conditioned dynamics model that can be used to predict future latent states. We empirically demonstrate that our approach can predict the rope state accurately up to ten steps into the future.
• Score: 51.740998379872195
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: We propose a framework for deformable linear object prediction. Prediction of deformable objects (e.g., rope) is challenging due to their non-linear dynamics and infinite-dimensional configuration spaces. By mapping the dynamics from a non-linear space to a linear space, we can use the good properties of linear dynamics for easier learning and more efficient prediction. We learn a locally linear, action-conditioned dynamics model that can be used to predict future latent states. Then, we decode the predicted latent state into the predicted state. We also apply a sampling-based optimization algorithm to select the optimal control action. We empirically demonstrate that our approach can predict the rope state accurately up to ten steps into the future and that our algorithm can find the optimal action given an initial state and a goal state.

Related papers

• Physics-guided Active Sample Reweighting for Urban Flow Prediction [75.24539704456791]
  Urban flow prediction is a nuanced-temporal modeling that estimates the throughput of transportation services like buses, taxis and ride-driven models. Some recent prediction solutions bring remedies with the notion of physics-guided machine learning (PGML) We develop a atized physics-guided network (PN), and propose a data-aware framework Physics-guided Active Sample Reweighting (P-GASR)
  arXiv  Detail & Related papers  (2024-07-18T15:44:23Z)
• Reinforced Model Predictive Control via Trust-Region Quasi-Newton Policy Optimization [0.0]
  We propose a Quasi-Newton training algorithm for policy optimization with a superlinear convergence rate. A simulation study illustrates that the proposed training algorithm outperforms other algorithms in terms of data efficiency and accuracy.
  arXiv  Detail & Related papers  (2024-05-28T09:16:08Z)
• Kalman Filter for Online Classification of Non-Stationary Data [101.26838049872651]
  In Online Continual Learning (OCL) a learning system receives a stream of data and sequentially performs prediction and training steps. We introduce a probabilistic Bayesian online learning model by using a neural representation and a state space model over the linear predictor weights. In experiments in multi-class classification we demonstrate the predictive ability of the model and its flexibility to capture non-stationarity.
  arXiv  Detail & Related papers  (2023-06-14T11:41:42Z)
• Data-Driven Linear Koopman Embedding for Model-Predictive Power System Control [1.20855096102517]
  We develop a em Koopman-inspired deep neural network (KDNN) architecture for the linear embedding of the voltage dynamics subjected to reactive controls. The proposed framework learns the underlying system dynamics from the input/output data in the form of a triple of transforms. The model predictive control is computed over the linear dynamics, making the control computation scalable and also real-time.
  arXiv  Detail & Related papers  (2022-06-02T19:52:11Z)
• Adaptive Online Optimization with Predictions: Static and Dynamic Environments [5.553963083111226]
  We propose new step-size rules and OCO algorithms that exploit gradient predictions, function predictions and dynamics. The proposed algorithms enjoy static and dynamic regret bounds in terms of the dynamics of the reference action sequence. We present results for both convex and strongly convex costs.
  arXiv  Detail & Related papers  (2022-05-01T11:03:33Z)
• Time varying regression with hidden linear dynamics [74.9914602730208]
  We revisit a model for time-varying linear regression that assumes the unknown parameters evolve according to a linear dynamical system. Counterintuitively, we show that when the underlying dynamics are stable the parameters of this model can be estimated from data by combining just two ordinary least squares estimates.
  arXiv  Detail & Related papers  (2021-12-29T23:37:06Z)
• Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization [60.73540999409032]
  We show that expressive autoregressive dynamics models generate different dimensions of the next state and reward sequentially conditioned on previous dimensions. We also show that autoregressive dynamics models are useful for offline policy optimization by serving as a way to enrich the replay buffer.
  arXiv  Detail & Related papers  (2021-04-28T16:48:44Z)
• SLPC: a VRNN-based approach for stochastic lidar prediction and completion in autonomous driving [63.87272273293804]
  We propose a new LiDAR prediction framework that is based on generative models namely Variational Recurrent Neural Networks (VRNNs) Our algorithm is able to address the limitations of previous video prediction frameworks when dealing with sparse data by spatially inpainting the depth maps in the upcoming frames. We present a sparse version of VRNNs and an effective self-supervised training method that does not require any labels.
  arXiv  Detail & Related papers  (2021-02-19T11:56:44Z)
• Tensor network approaches for learning non-linear dynamical laws [0.0]
  We show that various physical constraints can be captured via tensor network based parameterizations for the governing equation. We provide a physics-informed approach to recovering structured dynamical laws from data, which adaptively balances the need for expressivity and scalability.
  arXiv  Detail & Related papers  (2020-02-27T19:02:40Z)
• Implicit Regularization and Momentum Algorithms in Nonlinearly Parameterized Adaptive Control and Prediction [13.860437051795419]
  We exploit strong connections between classical adaptive nonlinear control techniques and recent progress in machine learning. We show that there exists considerable untapped potential in algorithm development for both adaptive nonlinear control and adaptive dynamics prediction.
  arXiv  Detail & Related papers  (2019-12-31T03:13:25Z)

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.