Pixel2Catch: Multi-Agent Sim-to-Real Transfer for Agile Manipulation with a Single RGB Camera

• URL: http://arxiv.org/abs/2602.22733v1
• Date: Thu, 26 Feb 2026 08:15:38 GMT
• Title: Pixel2Catch: Multi-Agent Sim-to-Real Transfer for Agile Manipulation with a Single RGB Camera
• Abstract summary: This work focuses on a novel approach that recognizes object motion using pixel-level visual information extracted from a single RGB image.<n>To achieve stable learning in a high-DoF system composed of a robot arm equipped with a multi-fingered hand, we design a heterogeneous multi-agent reinforcement learning framework.<n>Each agent is trained cooperatively using role-specific observations and rewards, and the learned policies are successfully transferred from simulation to the real world.
• Score: 3.219880761967806
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: To catch a thrown object, a robot must be able to perceive the object's motion and generate control actions in a timely manner. Rather than explicitly estimating the object's 3D position, this work focuses on a novel approach that recognizes object motion using pixel-level visual information extracted from a single RGB image. Such visual cues capture changes in the object's position and scale, allowing the policy to reason about the object's motion. Furthermore, to achieve stable learning in a high-DoF system composed of a robot arm equipped with a multi-fingered hand, we design a heterogeneous multi-agent reinforcement learning framework that defines the arm and hand as independent agents with distinct roles. Each agent is trained cooperatively using role-specific observations and rewards, and the learned policies are successfully transferred from simulation to the real world.

Related papers

• Trans2Occ: Voxel Occupancy Estimation and Grasp for Transparent Objects from Simulation to Reality [125.76063573012853]
  We present a framework for transparent object perception and manipulation based on single-view RGB input.<n>Our approach predicts voxel-space occupancy directly from a single image, providing a geometry-aware representation that supports downstream robotic grasping.
  arXiv  Detail & Related papers  (2026-06-01T06:59:13Z)
• ComPose: When to Trust Hands for Object Pose Tracking [44.085148707189035]
  ComPose is a 6DoF object tracking framework designed for hand-aware object pose estimation from RGB video.<n>Our method harmonizes hand motions as a textitcomplementary cue for object tracking.<n>Result can effectively transfer to downstream robot manipulation by enabling robots to reconstruct human actions from online videos.
  arXiv  Detail & Related papers  (2026-05-22T11:39:49Z)
• OCRA: Object-Centric Learning with 3D and Tactile Priors for Human-to-Robot Action Transfer [84.22494391514066]
  OCRA is a framework for video-based human-to-Robot Action transfer.<n>It learns directly from human demonstration videos to enable robust manipulation.
  arXiv  Detail & Related papers  (2026-03-15T14:31:03Z)
• ArtReg: Visuo-Tactile based Pose Tracking and Manipulation of Unseen Articulated Objects [2.9793019246605676]
  We present a novel method for visuo-tactile-based tracking of unseen objects.<n>Our approach integrates visuo-tactile point clouds in an unscented Kalman Filter formulation.<n>We have extensively evaluated our approach on various types of unknown objects through real robot experiments.
  arXiv  Detail & Related papers  (2025-11-09T13:30:51Z)
• Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control [72.00655365269]
  We present RoboMaster, a novel framework that models inter-object dynamics through a collaborative trajectory formulation.<n>Unlike prior methods that decompose objects, our core is to decompose the interaction process into three sub-stages: pre-interaction, interaction, and post-interaction.<n>Our method outperforms existing approaches, establishing new state-of-the-art performance in trajectory-controlled video generation for robotic manipulation.
  arXiv  Detail & Related papers  (2025-06-02T17:57:06Z)
• Modular Neural Network Policies for Learning In-Flight Object Catching with a Robot Hand-Arm System [55.94648383147838]
  We present a modular framework designed to enable a robot hand-arm system to learn how to catch flying objects. Our framework consists of five core modules: (i) an object state estimator that learns object trajectory prediction, (ii) a catching pose quality network that learns to score and rank object poses for catching, (iii) a reaching control policy trained to move the robot hand to pre-catch poses, and (iv) a grasping control policy trained to perform soft catching motions. We conduct extensive evaluations of our framework in simulation for each module and the integrated system, to demonstrate high success rates of in-flight
  arXiv  Detail & Related papers  (2023-12-21T16:20:12Z)
• ROAM: Robust and Object-Aware Motion Generation Using Neural Pose Descriptors [73.26004792375556]
  This paper shows that robustness and generalisation to novel scene objects in 3D object-aware character synthesis can be achieved by training a motion model with as few as one reference object. We leverage an implicit feature representation trained on object-only datasets, which encodes an SE(3)-equivariant descriptor field around the object. We demonstrate substantial improvements in 3D virtual character motion and interaction quality and robustness to scenarios with unseen objects.
  arXiv  Detail & Related papers  (2023-08-24T17:59:51Z)
• Learning Sim-to-Real Dense Object Descriptors for Robotic Manipulation [4.7246285569677315]
  We present Sim-to-Real Dense Object Nets (SRDONs), a dense object descriptor that not only understands the object via appropriate representation but also maps simulated and real data to a unified feature space with pixel consistency. We demonstrate in experiments that pre-trained SRDONs significantly improve performances on unseen objects and unseen visual environments for various robotic tasks with zero real-world training.
  arXiv  Detail & Related papers  (2023-04-18T02:28:55Z)
• V-MAO: Generative Modeling for Multi-Arm Manipulation of Articulated Objects [51.79035249464852]
  We present a framework for learning multi-arm manipulation of articulated objects. Our framework includes a variational generative model that learns contact point distribution over object rigid parts for each robot arm.
  arXiv  Detail & Related papers  (2021-11-07T02:31:09Z)
• MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion [19.034317851914725]
  We present a system which can estimate the accurate poses of multiple known objects in contact and occlusion from real-time, embodied multi-view vision. Our approach makes 3D object pose proposals from single RGB-D views, accumulates pose estimates and non-parametric occupancy information from multiple views as the camera moves. We verify the accuracy and robustness of our approach experimentally on 2 object datasets: YCB-Video, and our own challenging Cluttered YCB-Video.
  arXiv  Detail & Related papers  (2020-04-09T02:29:30Z)

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.