EgoPush: Learning End-to-End Egocentric Multi-Object Rearrangement for Mobile Robots

• URL: http://arxiv.org/abs/2602.18071v1
• Date: Fri, 20 Feb 2026 08:54:20 GMT
• Title: EgoPush: Learning End-to-End Egocentric Multi-Object Rearrangement for Mobile Robots
• Abstract summary: EgoPush is a policy learning framework that enables egocentric, perception-driven rearrangement.<n>We show that EgoPush significantly outperforms end-to-end RL baselines in success rate.<n>We also demonstrate zero-shot sim-to-real transfer on a mobile platform in the real world.
• Score: 13.858983945750081
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Humans can rearrange objects in cluttered environments using egocentric perception, navigating occlusions without global coordinates. Inspired by this capability, we study long-horizon multi-object non-prehensile rearrangement for mobile robots using a single egocentric camera. We introduce EgoPush, a policy learning framework that enables egocentric, perception-driven rearrangement without relying on explicit global state estimation that often fails in dynamic scenes. EgoPush designs an object-centric latent space to encode relative spatial relations among objects, rather than absolute poses. This design enables a privileged reinforcement-learning (RL) teacher to jointly learn latent states and mobile actions from sparse keypoints, which is then distilled into a purely visual student policy. To reduce the supervision gap between the omniscient teacher and the partially observed student, we restrict the teacher's observations to visually accessible cues. This induces active perception behaviors that are recoverable from the student's viewpoint. To address long-horizon credit assignment, we decompose rearrangement into stage-level subproblems using temporally decayed, stage-local completion rewards. Extensive simulation experiments demonstrate that EgoPush significantly outperforms end-to-end RL baselines in success rate, with ablation studies validating each design choice. We further demonstrate zero-shot sim-to-real transfer on a mobile platform in the real world. Code and videos are available at https://ai4ce.github.io/EgoPush/.

Related papers

• DreamMimic: Learning Visuomotor Whole-Body Loco-Manipulation via World Model [5.082137967180834]
  Vision-based whole-body loco-manipulation on humanoid robots is challenging due to partial observability, contact-rich dynamics, and the difficulty of learning long-horizon behaviors from high-dimensional visual inputs.<n>We present a framework that distills privileged teacher policies into vision-based humanoid controllers via world-model-assisted distillation.
  arXiv  Detail & Related papers  (2026-08-23T08:08:39Z)
• VAIC: Vision-Guided Humanoid Agile Object Interaction Control via Decoupled Commands [56.029505206531155]
  Vision Guided Agile Interaction Control (VAIC) is a unified framework that bridges the gap between current controllers and humanoid robots.<n>First, a privileged teacher policy masters diverse interaction skills using precise object kinematics and exact environmental states.<n>Second, a deployable student policy distills these capabilities by replacing full body tracking with velocity targets across multiple axes.
  arXiv  Detail & Related papers  (2026-06-08T09:52:55Z)
• AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization [79.26935895370191]
  AnchorWorld is a framework that advances egocentric simulation through enhanced interaction integrity.<n> auxiliary training supervision incorporates viewpoints decoupled from the agent's first-person sensorium.<n>We propose a simple yet effective mechanism for customizing self-evolving worlds.
  arXiv  Detail & Related papers  (2026-06-05T14:43:13Z)
• Self-supervised Hierarchical Visual Reasoning with World Model [82.64295546475257]
  3D open-world environments with adversarial opponents remain a core challenge for reinforcement learning.<n>We propose ResDreamer, a hierarchical world model in which each higher-level layer is trained to reconstruct the residuals of the layer below.<n>This design enables progressive abstraction of increasingly sophisticated world dynamics and fosters the emergence of richer latent representations.
  arXiv  Detail & Related papers  (2026-05-17T16:42:42Z)
• EgoSim: Egocentric World Simulator for Embodied Interaction Generation [93.11209644808783]
  EgoSim is a closed-loop egocentric world simulator that generates spatially consistent interaction videos.<n>It persistently updates the underlying 3D scene state for continuous simulation.<n>EgoSim significantly outperforms existing methods in terms of visual quality, spatial consistency, and generalization.
  arXiv  Detail & Related papers  (2026-04-01T15:00:46Z)
• EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language Models [31.768426199719816]
  We propose EgoActing, which requires directly grounding high-level instructions into various, precise, spatially aware humanoid actions.<n>We further instantiate this task by introducing EgoActor, a unified and scalable vision-language model (VLM) that can predict locomotion primitives.<n>We leverage broad supervision over egocentric RGB-only data from real-world demonstrations, spatial reasoning question-answering, and simulated environment demonstrations.
  arXiv  Detail & Related papers  (2026-02-04T13:04:56Z)
• Revisiting Multi-Task Visual Representation Learning [52.93947931352643]
  We introduce MTV, a principled multi-task visual pretraining framework.<n>We leverage high-capacity "expert" models to synthesize dense, structured pseudo-labels at scale.<n>Our results demonstrate that MTV achieves "best-of-both-worlds" performance.
  arXiv  Detail & Related papers  (2026-01-20T11:59:19Z)
• HumanoidVerse: A Versatile Humanoid for Vision-Language Guided Multi-Object Rearrangement [51.16740261131198]
  We introduce HumanoidVerse, a novel framework for vision-language guided humanoid control.<n>HumanoidVerse supports consecutive manipulation of multiple objects, guided only by natural language instructions and egocentric camera RGB observations.<n>Our work represents a key step toward robust, general-purpose humanoid agents capable of executing complex, sequential tasks under real-world sensory constraints.
  arXiv  Detail & Related papers  (2025-08-23T08:23:14Z)
• EgoWorld: Translating Exocentric View to Egocentric View using Rich Exocentric Observations [4.252119151012245]
  We introduce EgoWorld, a novel framework that reconstructs an egocentric view from rich exocentric observations.<n>Our approach reconstructs a point cloud from estimated exocentric depth maps, reprojects it into the egocentric perspective, and then applies diffusion-based inpainting to produce dense, semantically coherent egocentric images.<n>EgoWorld achieves state-of-the-art performance and demonstrates robust generalization to new objects, actions, scenes, and subjects.
  arXiv  Detail & Related papers  (2025-06-22T04:21:48Z)
• GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control [122.65089441381741]
  We present GEM, a Generalizable Ego-vision Multimodal world model.<n>It predicts future frames using a reference frame, sparse features, human poses, and ego-trajectories.<n>Our dataset is comprised of 4000+ hours of multimodal data across domains like autonomous driving, egocentric human activities, and drone flights.
  arXiv  Detail & Related papers  (2024-12-15T14:21:19Z)
• A Virtual Reality Tool for Representing, Visualizing and Updating Deep Learning Models [1.9785872350085878]
  We demonstrate a virtual reality tool for automating the process of assigning data inputs to different categories. A dataset is represented as a cloud of points in virtual space. The user explores the cloud through movement and uses hand gestures to categorise portions of the cloud.
  arXiv  Detail & Related papers  (2023-05-24T17:06:59Z)
• DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization [67.85434518679382]
  We present DynaVol, a 3D scene generative model that unifies geometric structures and object-centric learning. The key idea is to perform object-centric voxelization to capture the 3D nature of the scene. voxel features evolve over time through a canonical-space deformation function, forming the basis for global representation learning.
  arXiv  Detail & Related papers  (2023-04-30T05:29:28Z)
• Self-Supervised Object Goal Navigation with In-Situ Finetuning [110.6053241629366]
  This work builds an agent that builds self-supervised models of the world via exploration. We identify a strong source of self-supervision that can train all components of an ObjectNav agent. We show that our agent can perform competitively in the real world and simulation.
  arXiv  Detail & Related papers  (2022-12-09T03:41:40Z)
• Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams [64.82800502603138]
  This paper proposes a novel neural-network-based approach to progressively and autonomously develop pixel-wise representations in a video stream. The proposed method is based on a human-like attention mechanism that allows the agent to learn by observing what is moving in the attended locations. Our experiments leverage 3D virtual environments and they show that the proposed agents can learn to distinguish objects just by observing the video stream.
  arXiv  Detail & Related papers  (2022-04-26T09:52:31Z)
• End-to-End Partially Observable Visual Navigation in a Diverse Environment [30.895264166384685]
  This work aims at three challenges: (i) complex visual observations, (ii) partial observability of local sensing, and (iii) multimodal navigation behaviors. We propose a novel neural network (NN) architecture to represent a local controller and leverage the flexibility of the end-to-end approach to learn a powerful policy. We implement the NN controller on the SPOT robot and evaluate it on three challenging tasks with partial observations.
  arXiv  Detail & Related papers  (2021-09-16T06:53:57Z)

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.