Surface Constraint Policy for Learning Surface-Constrained and Dynamically Feasible Robot Skills

• URL: http://arxiv.org/abs/2605.31321v1
• Date: Fri, 29 May 2026 13:54:21 GMT
• Title: Surface Constraint Policy for Learning Surface-Constrained and Dynamically Feasible Robot Skills
• Abstract summary: Diffusion-based imitation methods have driven rapid progress in robot dexterous manipulation tasks.<n>We propose a novel surface constraint policy for generating robot actions that satisfy free-form surface constraints.<n>The experimental results demonstrate superior task success rates and contact stability under surface constraints.
• Score: 6.038943291323218
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion-based imitation learning methods have driven rapid progress in robot dexterous manipulation tasks. However, they have limitations when applied to tasks that involve complex free-form surface constraints because of their lack of explicit surface geometry constraint modeling and the dynamic feasibility issue, resulting in stochastic action generation that fails to achieve reliable surface alignment and maintain stable contact. To address these limitations, we propose a novel surface constraint policy (SCP) for generating robot actions that satisfy free-form surface constraints on the basis of human demonstrations and real-time visual observations. First, the surface geometry constraint is encoded using a two-dimensional weighted Gaussian kernel function that is derived from demonstrations. Building on the encoded surface geometry constraints, the diffusion-based policy is used to infer task-level action intentions from multimodal sensory inputs, including visual observations and robot state feedback. These intentions are further transformed into surface-constrained dynamic movement primitives (DMPs) through a similarity-based action mapping method, thereby enabling smooth and compliant motion execution. The SCP achieves generation of structured surface geometric intent and dynamically admissible actions. The proposed method is validated on multiple surface manipulation tasks and compared with existing techniques. The experimental results demonstrate superior task success rates and contact stability under surface constraints.

Related papers

• ErgoSurf: Ergodic Control for the Coverage of Unknown Surfaces [10.42763227391628]
  Contact-centric tasks require robots to systematically cover the surface while maintaining stable contact.<n>Traditional ergodic control methods rely on prior knowledge of surface geometry or require a vision sensory input to scan the geometry beforehand.<n>This paper introduces a novel online ergodic control framework that achieves systematic surface coverage while simultaneously reconstructing unknown surface geometry.
  arXiv  Detail & Related papers  (2026-08-06T16:01:21Z)
• A Task-Space Receding Horizon Controller for Fast Collision Avoidance [0.08594140167290099]
  Real-time collision avoidance for robotic manipulators requires fast reactions to unexpected obstacle motion.<n>Full model predictive control can provide this foresight, but its online cost may grow quickly with horizon length, model fidelity, and the number of active geometric constraints.<n>We present a task-space receding-horizon controller that uses a short contact-consistent rollout to generate a terminal kinematic reference.
  arXiv  Detail & Related papers  (2026-07-17T08:13:12Z)
• Learning Transferable Motor Skills for Geometry-Aware Robotic Surface Tasks [3.0714301039424776]
  Robotic surface-interaction tasks, such as spray painting or welding, require both accurate geometric planning and precise motion execution.<n>We propose a modular framework that decouples geometric motion planning from execution-level expertise.<n>We train a multimodal neural network to infer rule parameters jointly from kinematic trajectory data and CAD model geometry.
  arXiv  Detail & Related papers  (2026-05-24T05:49:33Z)
• STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System [76.3920413336862]
  We present STABLE, a semantics-physics dual-system tailored for simulation-ready tabletop scene generation.<n>STABLE consists of two complementary modules: a Semantic Reasoner and a Physics Corrector.<n> Experiments demonstrate that STABLE successfully generates simulation-ready tabletop scenes that strictly conform to task instructions.
  arXiv  Detail & Related papers  (2026-05-15T16:18:42Z)
• Learning Smooth and Robust Space Robotic Manipulation of Dynamic Target via Inter-frame Correlation [12.529803316934176]
  In microgravity environments, objects are typically free-floating, lacking the support and frictional constraints found on Earth.<n>This letter proposes a data-driven space robotic manipulation approach that integrates historical temporal information and inter-frame correlation mechanisms.
  arXiv  Detail & Related papers  (2026-03-29T06:27:30Z)
• RL-Based Coverage Path Planning for Deformable Objects on 3D Surfaces [32.12472154789291]
  We train a reinforcement learning agent in a simulator to manipulate deformable objects for surface wiping tasks.<n>We simplify the state representation of object surfaces using harmonic UV mapping, process contact feedback from the simulator on 2D feature maps, and use scaled grouped convolutions (SGCNN) to extract features efficiently.<n>Experiments demonstrate that our method outperforms previous approaches in key metrics, including total path length and coverage area.
  arXiv  Detail & Related papers  (2026-03-03T16:16:06Z)
• HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model [56.4392302336014]
  We present HAIC, a framework for robust interaction across diverse object dynamics without external state estimation.<n>Our key contribution is a dynamics predictor that estimates high-order object states (velocity, acceleration) solely from proprioceptive history.<n> Experiments on a humanoid robot show HAIC achieves high success rates in agile tasks.
  arXiv  Detail & Related papers  (2026-02-12T09:34:35Z)
• Graph neural networks for learning liquid simulations in dynamic scenes containing kinematic objects [5.185131234265025]
  We propose a graph neural network-based framework to learn the dynamics of liquids under rigid body interactions.<n>Our model accurately captures fluid behavior in dynamic settings and can also function as a simulator in static free-fall environments.<n>We show that the learned dynamics can be leveraged to solve control and manipulation tasks using gradient-based optimization methods.
  arXiv  Detail & Related papers  (2025-09-03T16:13:52Z)
• Dynamic Manipulation of Deformable Objects in 3D: Simulation, Benchmark and Learning Strategy [88.8665000676562]
  Prior methods often simplify the problem to low-speed or 2D settings, limiting their applicability to real-world 3D tasks.<n>To mitigate data scarcity, we introduce a novel simulation framework and benchmark grounded in reduced-order dynamics.<n>We propose Dynamics Informed Diffusion Policy (DIDP), a framework that integrates imitation pretraining with physics-informed test-time adaptation.
  arXiv  Detail & Related papers  (2025-05-23T03:28:25Z)
• TamedPUMA: safe and stable imitation learning with geometric fabrics [14.885339698387991]
  Imitation learning (IL) provides an intuitive and effective way of teaching stable task-space motions to robots with goal convergence.<n>With this work, we solve this challenge via TamedPUMA, an IL algorithm augmented with a recent development in motion generation called geometric fabrics.<n>The result is a stable imitation learning strategy within which we can seamlessly blend geometrical constraints like collision avoidance and joint limits.
  arXiv  Detail & Related papers  (2025-03-21T13:13:17Z)
• Unified Task and Motion Planning using Object-centric Abstractions of Motion Constraints [56.283944756315066]
  We propose an alternative TAMP approach that unifies task and motion planning into a single search. Our approach is based on an object-centric abstraction of motion constraints that permits leveraging the computational efficiency of off-the-shelf AI search to yield physically feasible plans.
  arXiv  Detail & Related papers  (2023-12-29T14:00:20Z)
• Nonprehensile Riemannian Motion Predictive Control [57.295751294224765]
  We introduce a novel Real-to-Sim reward analysis technique to reliably imagine and predict the outcome of taking possible actions for a real robotic platform. We produce a closed-loop controller to reactively push objects in a continuous action space. We observe that RMPC is robust in cluttered as well as occluded environments and outperforms the baselines.
  arXiv  Detail & Related papers  (2021-11-15T18:50:04Z)
• Latent Space Roadmap for Visual Action Planning of Deformable and Rigid Object Manipulation [74.88956115580388]
  Planning is performed in a low-dimensional latent state space that embeds images. Our framework consists of two main components: a Visual Foresight Module (VFM) that generates a visual plan as a sequence of images, and an Action Proposal Network (APN) that predicts the actions between them.
  arXiv  Detail & Related papers  (2020-03-19T18:43:26Z)

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.