Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination

• URL: http://arxiv.org/abs/2412.14957v1
• Date: Thu, 19 Dec 2024 15:38:15 GMT
• Title: Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination
• Authors: Leonardo Barcellona, Andrii Zadaianchuk, Davide Allegro, Samuele Papa, Stefano Ghidoni, Efstratios Gavves,
• Abstract summary: A world model provides an agent with a representation of its environment, enabling it to predict the causal consequences of its actions. We introduce a new paradigm for constructing world models that are explicit representations of the real world and its dynamics. DreMa replicates the observed world and its dynamics, allowing it to imagine novel configurations of objects and predict the future consequences of robot actions.
• Score: 25.62602420895531
• License:
• Abstract: A world model provides an agent with a representation of its environment, enabling it to predict the causal consequences of its actions. Current world models typically cannot directly and explicitly imitate the actual environment in front of a robot, often resulting in unrealistic behaviors and hallucinations that make them unsuitable for real-world applications. In this paper, we introduce a new paradigm for constructing world models that are explicit representations of the real world and its dynamics. By integrating cutting-edge advances in real-time photorealism with Gaussian Splatting and physics simulators, we propose the first compositional manipulation world model, which we call DreMa. DreMa replicates the observed world and its dynamics, allowing it to imagine novel configurations of objects and predict the future consequences of robot actions. We leverage this capability to generate new data for imitation learning by applying equivariant transformations to a small set of demonstrations. Our evaluations across various settings demonstrate significant improvements in both accuracy and robustness by incrementing actions and object distributions, reducing the data needed to learn a policy and improving the generalization of the agents. As a highlight, we show that a real Franka Emika Panda robot, powered by DreMa's imagination, can successfully learn novel physical tasks from just a single example per task variation (one-shot policy learning). Our project page and source code can be found in https://leobarcellona.github.io/DreamToManipulate/

Related papers

• Learning Interactive Real-World Simulators [96.5991333400566]
  We explore the possibility of learning a universal simulator of real-world interaction through generative modeling. We use the simulator to train both high-level vision-language policies and low-level reinforcement learning policies. Video captioning models can benefit from training with simulated experience, opening up even wider applications.
  arXiv  Detail & Related papers  (2023-10-09T19:42:22Z)
• Surfer: Progressive Reasoning with World Models for Robotic Manipulation [51.26109827779267]
  We introduce a novel and simple robot manipulation framework, called Surfer. Surfer treats robot manipulation as a state transfer of the visual scene, and decouples it into two parts: action and scene. It is based on the world model, treats robot manipulation as a state transfer of the visual scene, and decouples it into two parts: action and scene.
  arXiv  Detail & Related papers  (2023-06-20T07:06:04Z)
• 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. Our approach can effectively and robustly perceive object pose and enable sample-efficient generalization learning. 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)
• Real-World Humanoid Locomotion with Reinforcement Learning [92.85934954371099]
  We present a fully learning-based approach for real-world humanoid locomotion. Our controller can walk over various outdoor terrains, is robust to external disturbances, and can adapt in context.
  arXiv  Detail & Related papers  (2023-03-06T18:59:09Z)
• RT-1: Robotics Transformer for Real-World Control at Scale [98.09428483862165]
  We present a model class, dubbed Robotics Transformer, that exhibits promising scalable model properties. We verify our conclusions in a study of different model classes and their ability to generalize as a function of the data size, model size, and data diversity based on a large-scale data collection on real robots performing real-world tasks.
  arXiv  Detail & Related papers  (2022-12-13T18:55:15Z)
• DexTransfer: Real World Multi-fingered Dexterous Grasping with Minimal Human Demonstrations [51.87067543670535]
  We propose a robot-learning system that can take a small number of human demonstrations and learn to grasp unseen object poses. We train a dexterous grasping policy that takes the point clouds of the object as input and predicts continuous actions to grasp objects from different initial robot states. The policy learned from our dataset can generalize well on unseen object poses in both simulation and the real world.
  arXiv  Detail & Related papers  (2022-09-28T17:51:49Z)
• RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networks [32.00371492516123]
  We present a model-based planning framework for modeling and manipulating elasto-plastic objects. Our system, RoboCraft, learns a particle-based dynamics model using graph neural networks (GNNs) to capture the structure of the underlying system. We show through experiments that with just 10 minutes of real-world robotic interaction data, our robot can learn a dynamics model that can be used to synthesize control signals to deform elasto-plastic objects into various target shapes.
  arXiv  Detail & Related papers  (2022-05-05T20:28:15Z)
• Factored World Models for Zero-Shot Generalization in Robotic Manipulation [7.258229016768018]
  We learn to generalize over robotic pick-and-place tasks using object-factored world models. We use a residual stack of graph neural networks that receive action information at multiple levels in both their node and edge neural networks. We show that an ensemble of our models can be used to plan for tasks involving up to 12 pick and place actions using search.
  arXiv  Detail & Related papers  (2022-02-10T21:26:11Z)
• Full-Body Visual Self-Modeling of Robot Morphologies [29.76701883250049]
  Internal computational models of physical bodies are fundamental to the ability of robots and animals alike to plan and control their actions. Recent progress in fully data-driven self-modeling has enabled machines to learn their own forward kinematics directly from task-agnostic interaction data. Here, we propose that instead of directly modeling forward-kinematics, a more useful form of self-modeling is one that could answer space occupancy queries.
  arXiv  Detail & Related papers  (2021-11-11T18:58:07Z)

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.