Reactive Motion Generation via Phase-varying Neural Potential Functions

• URL: http://arxiv.org/abs/2604.26450v1
• Date: Wed, 29 Apr 2026 09:05:27 GMT
• Title: Reactive Motion Generation via Phase-varying Neural Potential Functions
• Abstract summary: We introduce Phase-varying Neural Potential Functions (PNPF) for Learning-from-Demonstration (LfD)<n>PNPF generalizes effectively across point-to-point, periodic, and full 6D motion tasks, outperforms existing baselines on trajectories with intersections, and demonstrates robust performance in real-time robotic manipulation under external disturbances.
• Score: 11.19363093406338
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dynamical systems (DS) methods for Learning-from-Demonstration (LfD) provide stable, continuous policies from few demonstrations. First-order dynamical systems (DS) are effective for many point-to-point and periodic tasks, as long as a unique velocity is defined for each state. For tasks with intersections (e.g., drawing an "8"), extensions such as second-order dynamics or phase variables are often used. However, by incorporating velocity, second-order models become sensitive to disturbances near intersections, as velocity is used to disambiguate motion direction. Moreover, this disambiguation may fail when nearly identical position-velocity pairs correspond to different onward motions. In contrast, phase-based methods rely on open-loop time or phase variables, which limit their ability to recover after perturbations. We introduce Phase-varying Neural Potential Functions (PNPF), an LfD framework that conditions a potential function on a phase variable which is estimated directly from state progression, rather than on open-loop temporal inputs. This phase variable allows the system to handle state revisits, while the learned potential function generates local vector fields for reactive and stable control. PNPF generalizes effectively across point-to-point, periodic, and full 6D motion tasks, outperforms existing baselines on trajectories with intersections, and demonstrates robust performance in real-time robotic manipulation under external disturbances.

Related papers

• SegDiff: Segmented Trajectory Diffusion for Consistent and Adaptive Robot Manipulation [65.81476183180527]
  We introduce SegDiff, a closed-loop visuomotor policy that integrates the strengths of both paradigms.<n>SegDiff decomposes demonstrations into motion segments between keyposes and learns to predict the continuous trajectory from the current state to the next keypose.<n>SegDiff demonstrates significant performance gains over existing approaches across various simulated and real-world scenarios.
  arXiv  Detail & Related papers  (2026-07-13T02:48:03Z)
• Hypergraph-State Collaborative Reasoning for Multi-Object Tracking [63.32950991964095]
  We propose a collaborative reasoning framework that enhances motion estimation through joint inference among multiple correlated objects.<n>By allowing objects with similar motion states to mutually constrain and refine each other, our framework stabilizes noisy trajectories and infers plausible motion continuity even when target is occluded.
  arXiv  Detail & Related papers  (2026-04-14T12:37:39Z)
• Sparse Autoencoders as a Steering Basis for Phase Synchronization in Graph-Based CFD Surrogates [6.396157607535812]
  Graph-based surrogate models provide fast alternatives to high-fidelity CFD solvers, but their opaque latent spaces and limited controllability restrict use in safety-critical settings.<n>We ask whether phase drift can instead be corrected post hoc by manipulating the latent space of a frozen surrogate.<n>We propose a phase-steering framework for pretrained graph-based CFD models that combines the right representation with the right intervention mechanism.
  arXiv  Detail & Related papers  (2026-03-28T07:03:44Z)
• 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)
• Neural Implicit Action Fields: From Discrete Waypoints to Continuous Functions for Vision-Language-Action Models [35.98187913967879]
  We propose a paradigm shift that reformulates action prediction from discrete waypoints to continuous action function regression.<n>Our approach achieves state-of-the-art results on CALVIN and LIBERO benchmarks across diverse backbones.
  arXiv  Detail & Related papers  (2026-03-02T11:48:24Z)
• Learning Discrete Successor Transitions in Continuous Attractor Networks: Emergence, Limits, and Topological Constraints [0.0]
  Continuous attractor networks (CANs) represent low-dimensional continuous variables such as head direction, spatial position, and phase.<n>In canonical spatial domains, transitions along the attractor manifold are driven by continuous displacement signals.<n>We present an experimental framework for training CANs to perform successor-like transitions between stable attractor states.
  arXiv  Detail & Related papers  (2026-01-20T10:41:18Z)
• FunPhase: A Periodic Functional Autoencoder for Motion Generation via Phase Manifolds [2.6041136107390037]
  We introduce FunPhase, a functional periodic autoencoder that learns a phase manifold for motion and replaces discrete temporal decoding with a function-space formulation.<n>FunPhase supports downstream tasks such as super-resolution and partial-body motion completion, generalizes across skeletons and datasets, and unifies motion prediction and generation within a single interpretable manifold.
  arXiv  Detail & Related papers  (2025-12-10T08:46:53Z)
• Simulating Distribution Dynamics: Liquid Temporal Feature Evolution for Single-Domain Generalized Object Detection [58.25418970608328]
  Single-Domain Generalized Object Detection (Single-DGOD) aims to transfer a detector trained on one source domain to multiple unknown domains.<n>Existing methods for Single-DGOD typically rely on discrete data augmentation or static perturbation methods to expand data diversity.<n>We propose a new method, which simulates the progressive evolution of features from the source domain to simulated latent distributions.
  arXiv  Detail & Related papers  (2025-11-13T03:10:39Z)
• Bidirectional Feature-aligned Motion Transformation for Efficient Dynamic Point Cloud Compression [97.66080040613726]
  We propose a Bidirectional Feature-aligned Motion Transformation (Bi-FMT) framework that implicitly models motion in the feature space.<n>Bi-FMT aligns features across both past and future frames to produce temporally consistent latent representations.<n>We show Bi-FMT surpasses D-DPCC and AdaDPCC in both compression efficiency and runtime.
  arXiv  Detail & Related papers  (2025-09-18T03:51:06Z)
• Forecasting Continuous Non-Conservative Dynamical Systems in SO(3) [51.510040541600176]
  We propose a novel approach to modeling the rotation of moving objects in computer vision.<n>Our approach is agnostic to energy and momentum conservation while being robust to input noise.<n>By learning to approximate object dynamics from noisy states during training, our model attains robust extrapolation capabilities in simulation and various real-world settings.
  arXiv  Detail & Related papers  (2025-08-11T09:03:10Z)
• Stochastic Latent Transformer: Efficient Modelling of Stochastically Forced Zonal Jets [0.0]
  We present a novel deep probabilistic learning approach, the 'Stochastic Latent Transformer' (SLT) The SLT accurately reproduces system dynamics across various integration periods, validated through quantitative diagnostics. It achieves a five-order-of-magnitude speedup in emulating the zonally-averaged flow.
  arXiv  Detail & Related papers  (2023-10-25T16:17:00Z)
• 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)

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.