FetchBot: Learning Generalizable Object Fetching in Cluttered Scenes via Zero-Shot Sim2Real

• URL: http://arxiv.org/abs/2502.17894v2
• Date: Sun, 24 Aug 2025 07:39:58 GMT
• Title: FetchBot: Learning Generalizable Object Fetching in Cluttered Scenes via Zero-Shot Sim2Real
• Abstract summary: Generalizable object fetching in cluttered scenes remains a fundamental and application-critical challenge in embodied AI.<n>FetchBot is a sim-to-real framework for this challenge.<n>It achieves an average real-world success rate of 89.95%, significantly outperforming prior methods.
• Score: 25.60751532514627
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generalizable object fetching in cluttered scenes remains a fundamental and application-critical challenge in embodied AI. Closely packed objects cause inevitable occlusions, making safe action generation particularly difficult. Under such partial observability, effective policies must not only generalize across diverse objects and layouts but also reason about occlusion to avoid collisions. However, collecting large-scale real-world data for this task remains prohibitively expensive, leaving this problem largely unsolved. In this paper, we introduce FetchBot, a sim-to-real framework for this challenge. We first curate a large-scale synthetic dataset featuring 1M diverse scenes and 500k representative demonstrations. Based on this dataset, FetchBot employs a depth-conditioned method for action generation, which leverages structural cues to enable robust obstacle-aware action planning. However, depth is perfect in simulation but noisy in real-world environments. To address this sim-to-real gap, FetchBot predicts depth from RGB inputs using a foundation model and integrates local occupancy prediction as a pre-training task, providing a generalizable latent representation for sim-to-real transfer. Extensive experiments in simulation and real-world environments demonstrate the strong zero-shot sim-to-real transfer, effective clutter handling, and adaptability to novel scenarios. In cluttered environments, it achieves an average real-world success rate of 89.95%, significantly outperforming prior methods. Moreover, FetchBot demonstrates excellent robustness in challenging cases, such as fetching transparent, reflective, and irregular objects, highlighting its practical value.

Related papers

• Learning to Throw Objects Safely in Multi-Obstacle Environments [14.544049936179071]
  Existing approaches, such as TossingBot, learn throwing strategies from visual input but assume obstacle-free settings.<n>We introduce a potential field state representation that compactly encodes both basket attraction and obstacle repulsion on a fixed-size grid.<n>We show that PFR provides a practical and robust representation for safe and efficient robotic throwing in unstructured environments.
  arXiv  Detail & Related papers  (2026-07-07T15:24:12Z)
• GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environments [63.222920701596564]
  Training embodied agents in the real world requires skilled operators and expensive hardware.<n> Simulation environments offer a compelling alternative by enabling large-scale, cost-effective data augmentation.<n>Fastly constructing high-fidelity simulation scenes with a minimal sim-to-real gap has become a critical objective in robot learning.
  arXiv  Detail & Related papers  (2026-06-16T05:00:42Z)
• 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)
• ExoGS: A 4D Real-to-Sim-to-Real Framework for Scalable Manipulation Data Collection [27.18540416686717]
  ExoGS is a robot-free 4D Real-to-Sim-to-Real framework.<n>It captures both static environments and dynamic interactions in the real world and transfers them seamlessly to a simulated environment.<n>It provides a new solution for scalable manipulation data collection and policy learning.
  arXiv  Detail & Related papers  (2026-01-26T16:04:12Z)
• Generalizable Domain Adaptation for Sim-and-Real Policy Co-Training [21.855770200309674]
  We propose a unified sim-and-real co-training framework for learning generalizable manipulation policies.<n>We show it can leverage abundant simulation data to achieve up to a 30% improvement in the real-world success rate.
  arXiv  Detail & Related papers  (2025-09-23T04:32:53Z)
• Object-level Scene Deocclusion [92.39886029550286]
  We present a new self-supervised PArallel visible-to-COmplete diffusion framework, named PACO, for object-level scene deocclusion. To train PACO, we create a large-scale dataset with 500k samples to enable self-supervised learning. Experiments on COCOA and various real-world scenes demonstrate the superior capability of PACO for scene deocclusion, surpassing the state of the arts by a large margin.
  arXiv  Detail & Related papers  (2024-06-11T20:34:10Z)
• RPMArt: Towards Robust Perception and Manipulation for Articulated Objects [56.73978941406907]
  We propose a framework towards Robust Perception and Manipulation for Articulated Objects ( RPMArt) RPMArt learns to estimate the articulation parameters and manipulate the articulation part from the noisy point cloud. We introduce an articulation-aware classification scheme to enhance its ability for sim-to-real transfer.
  arXiv  Detail & Related papers  (2024-03-24T05:55:39Z)
• Closing the Visual Sim-to-Real Gap with Object-Composable NeRFs [59.12526668734703]
  We introduce Composable Object Volume NeRF (COV-NeRF), an object-composable NeRF model that is the centerpiece of a real-to-sim pipeline. COV-NeRF extracts objects from real images and composes them into new scenes, generating photorealistic renderings and many types of 2D and 3D supervision.
  arXiv  Detail & Related papers  (2024-03-07T00:00:02Z)
• Robust Visual Sim-to-Real Transfer for Robotic Manipulation [79.66851068682779]
  Learning visuomotor policies in simulation is much safer and cheaper than in the real world. However, due to discrepancies between the simulated and real data, simulator-trained policies often fail when transferred to real robots. One common approach to bridge the visual sim-to-real domain gap is domain randomization (DR)
  arXiv  Detail & Related papers  (2023-07-28T05:47:24Z)
• Transferring Foundation Models for Generalizable Robotic Manipulation [82.12754319808197]
  We propose a novel paradigm that effectively leverages language-reasoning segmentation mask generated by internet-scale foundation models.<n>Our approach can effectively and robustly perceive object pose and enable sample-efficient generalization learning.<n>Demos can be found in our submitted video, and more comprehensive ones can be found in link1 or link2.
  arXiv  Detail & Related papers  (2023-06-09T07:22:12Z)
• 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)
• Robot Active Neural Sensing and Planning in Unknown Cluttered Environments [0.0]
  Active sensing and planning in unknown, cluttered environments is an open challenge for robots intending to provide home service, search and rescue, narrow-passage inspection, and medical assistance. We present the active neural sensing approach that generates the kinematically feasible viewpoint sequences for the robot manipulator with an in-hand camera to gather the minimum number of observations needed to reconstruct the underlying environment. Our framework actively collects the visual RGBD observations, aggregates them into scene representation, and performs object shape inference to avoid unnecessary robot interactions with the environment.
  arXiv  Detail & Related papers  (2022-08-23T16:56:54Z)
• Discovering Objects that Can Move [55.743225595012966]
  We study the problem of object discovery -- separating objects from the background without manual labels. Existing approaches utilize appearance cues, such as color, texture, and location, to group pixels into object-like regions. We choose to focus on dynamic objects -- entities that can move independently in the world.
  arXiv  Detail & Related papers  (2022-03-18T21:13:56Z)
• IFOR: Iterative Flow Minimization for Robotic Object Rearrangement [92.97142696891727]
  IFOR, Iterative Flow Minimization for Robotic Object Rearrangement, is an end-to-end method for the problem of object rearrangement for unknown objects. We show that our method applies to cluttered scenes, and in the real world, while training only on synthetic data.
  arXiv  Detail & Related papers  (2022-02-01T20:03:56Z)
• MetaGraspNet: A Large-Scale Benchmark Dataset for Vision-driven Robotic Grasping via Physics-based Metaverse Synthesis [78.26022688167133]
  We present a large-scale benchmark dataset for vision-driven robotic grasping via physics-based metaverse synthesis. The proposed dataset contains 100,000 images and 25 different object types. We also propose a new layout-weighted performance metric alongside the dataset for evaluating object detection and segmentation performance.
  arXiv  Detail & Related papers  (2021-12-29T17:23:24Z)
• Intervention Design for Effective Sim2Real Transfer [48.9711031777803]
  This work addresses the recent success of domain randomization and data augmentation for the sim2real setting. We explain this success through the lens of causal inference, positioning domain randomization and data augmentation as interventions on the environment.
  arXiv  Detail & Related papers  (2020-12-03T16:38:54Z)
• Reactive Long Horizon Task Execution via Visual Skill and Precondition Models [59.76233967614774]
  We describe an approach for sim-to-real training that can accomplish unseen robotic tasks using models learned in simulation to ground components of a simple task planner. We show an increase in success rate from 91.6% to 98% in simulation and from 10% to 80% success rate in the real-world as compared with naive baselines.
  arXiv  Detail & Related papers  (2020-11-17T15:24:01Z)
• Transferable Active Grasping and Real Embodied Dataset [48.887567134129306]
  We show how to search for feasible viewpoints for grasping by the use of hand-mounted RGB-D cameras. A practical 3-stage transferable active grasping pipeline is developed, that is adaptive to unseen clutter scenes. In our pipeline, we propose a novel mask-guided reward to overcome the sparse reward issue in grasping and ensure category-irrelevant behavior.
  arXiv  Detail & Related papers  (2020-04-28T08:15:35Z)

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.