Multiscale Sensor Fusion and Continuous Control with Neural CDEs

• URL: http://arxiv.org/abs/2203.08715v1
• Date: Wed, 16 Mar 2022 16:06:03 GMT
• Title: Multiscale Sensor Fusion and Continuous Control with Neural CDEs
• Abstract summary: We present 'InFuser', a unified architecture that trains continuous time-policies with Neural Controlled Equations Differential (CDEs) InFuser evolves a single latent state representation over time by (In)tegrating and (Fus)ing multi-sensory observations. Experiments demonstrate that InFuser learns robust policies for dynamic tasks.
• Score: 17.67182664077201
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Though robot learning is often formulated in terms of discrete-time Markov decision processes (MDPs), physical robots require near-continuous multiscale feedback control. Machines operate on multiple asynchronous sensing modalities, each with different frequencies, e.g., video frames at 30Hz, proprioceptive state at 100Hz, force-torque data at 500Hz, etc. While the classic approach is to batch observations into fixed-time windows then pass them through feed-forward encoders (e.g., with deep networks), we show that there exists a more elegant approach -- one that treats policy learning as modeling latent state dynamics in continuous-time. Specifically, we present 'InFuser', a unified architecture that trains continuous time-policies with Neural Controlled Differential Equations (CDEs). InFuser evolves a single latent state representation over time by (In)tegrating and (Fus)ing multi-sensory observations (arriving at different frequencies), and inferring actions in continuous-time. This enables policies that can react to multi-frequency multi sensory feedback for truly end-to-end visuomotor control, without discrete-time assumptions. Behavior cloning experiments demonstrate that InFuser learns robust policies for dynamic tasks (e.g., swinging a ball into a cup) notably outperforming several baselines in settings where observations from one sensing modality can arrive at much sparser intervals than others.

Related papers

• StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models [84.17128030384099]
  StreamPI is a streaming multimodal temporal modeling framework.<n>It equips single-frame VLA with temporal reasoning capability without introducing any additional parameters.<n> Experiments on real-robot tasks spanning memory-dependent and precise perception scenarios, as well as the simulation benchmark LIBERO, demonstrate that StreamPI outperforms pi0.5 across diverse tasks.
  arXiv  Detail & Related papers  (2026-08-26T17:33:19Z)
• Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control [51.92884966472683]
  MSCoT is a multi-scale, coarse-to-fine model for test-time human motion synthesis and control.<n> MSCoT discretizes motion into a multi-scale hierarchical representation and predicts the entire token sequence at each temporal scale.
  arXiv  Detail & Related papers  (2026-05-14T15:09:49Z)
• Ada3Drift: Adaptive Training-Time Drifting for One-Step 3D Visuomotor Robotic Manipulation [53.750389076941396]
  Diffusion-based visuomotor policies capture multimodal action distributions through iterative denoising, but their high inference latency limits real-time robotic control.<n>We propose Ada3Drift, which learns a training-time drifting field that attracts predicted actions toward expert demonstration modes.<n>Ada3Drift achieves state-of-the-art performance while requiring $10times$ fewer function evaluations than diffusion-based alternatives.
  arXiv  Detail & Related papers  (2026-03-12T14:36:53Z)
• PRISM: Performer RS-IMLE for Single-pass Multisensory Imitation Learning [51.24484551729328]
  We introduce PRISM, a single-pass policy based on a batch-global rejection-sampling variant of IMLE.<n> PRISM couples a temporal multisensory encoder with a linear-attention generator using a Performer architecture.<n>We demonstrate the efficacy of PRISM on a diverse real-world hardware suite, including loco-manipulation using a Unitree Go2 with a 7-DoF arm D1 and tabletop manipulation with a UR5 manipulator.
  arXiv  Detail & Related papers  (2026-02-02T17:57:37Z)
• Whenever, Wherever: Towards Orchestrating Crowd Simulations with Spatio-Temporal Spawn Dynamics [65.72663487116439]
  We propose nTPP-GMM that models spawn-temporal spawn dynamics using Neural Temporal Point Processes. We evaluate our approach by simulations of three diverse real-world datasets with nTPP-GMM.
  arXiv  Detail & Related papers  (2025-03-20T18:46:41Z)
• MPSDynamics.jl: Tensor network simulations for finite-temperature (non-Markovian) open quantum system dynamics [0.0]
  The MPSDynamics.jl package provides an easy to use interface for performing open quantum systems simulations at zero and finite temperatures. Written in the Julia programming language, MPSDynamics.jl is a versatile open-source package.
  arXiv  Detail & Related papers  (2024-06-11T08:34:59Z)
• Multistep Inverse Is Not All You Need [87.62730694973696]
  In real-world control settings, the observation space is often unnecessarily high-dimensional and subject to time-correlated noise. It is therefore desirable to learn an encoder to map the observation space to a simpler space of control-relevant variables. We propose a new algorithm, ACDF, which combines multistep-inverse prediction with a latent forward model.
  arXiv  Detail & Related papers  (2024-03-18T16:36:01Z)
• Motion Code: Robust Time Series Classification and Forecasting via Sparse Variational Multi-Stochastic Processes Learning [3.2857981869020327]
  We propose a novel framework that views each time series as a realization of a continuous-time process. This mathematical approach captures dependencies across timestamps and detects hidden, time-varying signals within the noise. Experiments on noisy datasets, including real-world Parkinson's disease sensor tracking, demonstrate Motion Code's strong performance against established benchmarks.
  arXiv  Detail & Related papers  (2024-02-21T19:10:08Z)
• Graph-Aware Contrasting for Multivariate Time-Series Classification [50.84488941336865]
  Existing contrastive learning methods mainly focus on achieving temporal consistency with temporal augmentation and contrasting techniques. We propose Graph-Aware Contrasting for spatial consistency across MTS data. Our proposed method achieves state-of-the-art performance on various MTS classification tasks.
  arXiv  Detail & Related papers  (2023-09-11T02:35:22Z)
• Value function estimation using conditional diffusion models for control [62.27184818047923]
  We propose a simple algorithm called Diffused Value Function (DVF) It learns a joint multi-step model of the environment-robot interaction dynamics using a diffusion model. We show how DVF can be used to efficiently capture the state visitation measure for multiple controllers.
  arXiv  Detail & Related papers  (2023-06-09T18:40:55Z)
• Robust Audio Anomaly Detection [10.75127981612396]
  The presented approach doesn't assume the presence of labeled anomalies in the training dataset. The temporal dynamics are modeled using recurrent layers augmented with attention mechanism. The output of the network is an outlier robust probability density function.
  arXiv  Detail & Related papers  (2022-02-03T17:19:42Z)
• Value Iteration in Continuous Actions, States and Time [99.00362538261972]
  We propose a continuous fitted value iteration (cFVI) algorithm for continuous states and actions. The optimal policy can be derived for non-linear control-affine dynamics. Videos of the physical system are available at urlhttps://sites.google.com/view/value-iteration.
  arXiv  Detail & Related papers  (2021-05-10T21:40:56Z)
• Behavioral Model Inference of Black-box Software using Deep Neural Networks [1.6593369275241105]
  Many software engineering tasks, such as testing, and anomaly detection can benefit from the ability to infer a behavioral model of the software. Most existing inference approaches assume access to code to collect execution sequences. We show how this approach can be used to accurately detect state changes, and how the inferred models can be successfully applied to transfer-learning scenarios.
  arXiv  Detail & Related papers  (2021-01-13T09:23:37Z)
• Motion Prediction Using Temporal Inception Module [96.76721173517895]
  We propose a Temporal Inception Module (TIM) to encode human motion. Our framework produces input embeddings using convolutional layers, by using different kernel sizes for different input lengths. The experimental results on standard motion prediction benchmark datasets Human3.6M and CMU motion capture dataset show that our approach consistently outperforms the state of the art methods.
  arXiv  Detail & Related papers  (2020-10-06T20:26:01Z)
• Learning Continuous-Time Dynamics by Stochastic Differential Networks [32.63114111531396]
  We propose a flexible continuous-time recurrent neural network named Variational Differential Networks (VSDN) VSDN embeds the complicated dynamics of the sporadic time series by neural Differential Equations (SDE) We show that VSDNs outperform state-of-the-art continuous-time deep learning models and achieve remarkable performance on prediction and tasks for sporadic time series.
  arXiv  Detail & Related papers  (2020-06-11T01:40:34Z)
• Liquid Time-constant Networks [117.57116214802504]
  We introduce a new class of time-continuous recurrent neural network models. Instead of declaring a learning system's dynamics by implicit nonlinearities, we construct networks of linear first-order dynamical systems. These neural networks exhibit stable and bounded behavior, yield superior expressivity within the family of neural ordinary differential equations.
  arXiv  Detail & Related papers  (2020-06-08T09:53:35Z)

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.