HACMan: Learning Hybrid Actor-Critic Maps for 6D Non-Prehensile Manipulation

• URL: http://arxiv.org/abs/2305.03942v5
• Date: Mon, 15 Jul 2024 03:49:48 GMT
• Title: HACMan: Learning Hybrid Actor-Critic Maps for 6D Non-Prehensile Manipulation
• Authors: Wenxuan Zhou, Bowen Jiang, Fan Yang, Chris Paxton, David Held,
• Abstract summary: We introduce Hybrid Actor-Critic Maps for Manipulation (HACMan), a reinforcement learning approach for 6D non-prehensile manipulation of objects. We evaluate HACMan on a 6D object pose alignment task in both simulation and in the real world. Compared to alternative action representations, HACMan achieves a success rate more than three times higher than the best baseline.
• Score: 29.01984677695523
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Manipulating objects without grasping them is an essential component of human dexterity, referred to as non-prehensile manipulation. Non-prehensile manipulation may enable more complex interactions with the objects, but also presents challenges in reasoning about gripper-object interactions. In this work, we introduce Hybrid Actor-Critic Maps for Manipulation (HACMan), a reinforcement learning approach for 6D non-prehensile manipulation of objects using point cloud observations. HACMan proposes a temporally-abstracted and spatially-grounded object-centric action representation that consists of selecting a contact location from the object point cloud and a set of motion parameters describing how the robot will move after making contact. We modify an existing off-policy RL algorithm to learn in this hybrid discrete-continuous action representation. We evaluate HACMan on a 6D object pose alignment task in both simulation and in the real world. On the hardest version of our task, with randomized initial poses, randomized 6D goals, and diverse object categories, our policy demonstrates strong generalization to unseen object categories without a performance drop, achieving an 89% success rate on unseen objects in simulation and 50% success rate with zero-shot transfer in the real world. Compared to alternative action representations, HACMan achieves a success rate more than three times higher than the best baseline. With zero-shot sim2real transfer, our policy can successfully manipulate unseen objects in the real world for challenging non-planar goals, using dynamic and contact-rich non-prehensile skills. Videos can be found on the project website: https://hacman-2023.github.io.

Related papers

• EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting [95.44545809256473]
  We introduce EgoGaussian, the first method capable of simultaneously reconstructing 3D scenes and tracking 3D object motion from RGB egocentric input alone. Our approach employs a clip-level online learning pipeline that leverages the dynamic nature of human activities.
  arXiv  Detail & Related papers  (2024-06-28T10:39:36Z)
• Uncertainty-aware Active Learning of NeRF-based Object Models for Robot Manipulators using Visual and Re-orientation Actions [8.059133373836913]
  This paper presents an approach that enables a robot to rapidly learn the complete 3D model of a given object for manipulation in unfamiliar orientations. We use an ensemble of partially constructed NeRF models to quantify model uncertainty to determine the next action. Our approach determines when and how to grasp and re-orient an object given its partial NeRF model and re-estimates the object pose to rectify misalignments introduced during the interaction.
  arXiv  Detail & Related papers  (2024-04-02T10:15:06Z)
• RPMArt: Towards Robust Perception and Manipulation for Articulated Objects [56.73978941406907]
  It is essential that robots can exhibit robust perception and manipulation for articulated objects in real-world robotic applications. 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.
  arXiv  Detail & Related papers  (2024-03-24T05:55:39Z)
• 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)
• H-SAUR: Hypothesize, Simulate, Act, Update, and Repeat for Understanding Object Articulations from Interactions [62.510951695174604]
  "Hypothesize, Simulate, Act, Update, and Repeat" (H-SAUR) is a probabilistic generative framework that generates hypotheses about how objects articulate given input observations. We show that the proposed model significantly outperforms the current state-of-the-art articulated object manipulation framework. We further improve the test-time efficiency of H-SAUR by integrating a learned prior from learning-based vision models.
  arXiv  Detail & Related papers  (2022-10-22T18:39:33Z)
• Object Manipulation via Visual Target Localization [64.05939029132394]
  Training agents to manipulate objects, poses many challenges. We propose an approach that explores the environment in search for target objects, computes their 3D coordinates once they are located, and then continues to estimate their 3D locations even when the objects are not visible. Our evaluations show a massive 3x improvement in success rate over a model that has access to the same sensory suite.
  arXiv  Detail & Related papers  (2022-03-15T17:59:01Z)
• A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects [25.428781562909606]
  We present a framework for solving long-horizon planning problems involving manipulation of rigid objects. Our method plans in the space of object subgoals and frees the planner from reasoning about robot-object interaction dynamics.
  arXiv  Detail & Related papers  (2020-11-16T18:59:33Z)
• Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds [62.013872787987054]
  We propose a new method for learning closed-loop control policies for 6D grasping. Our policy takes a segmented point cloud of an object from an egocentric camera as input, and outputs continuous 6D control actions of the robot gripper for grasping the object.
  arXiv  Detail & Related papers  (2020-10-02T07:42:00Z)
• Hindsight for Foresight: Unsupervised Structured Dynamics Models from Physical Interaction [24.72947291987545]
  Key challenge for an agent learning to interact with the world is to reason about physical properties of objects. We propose a novel approach for modeling the dynamics of a robot's interactions directly from unlabeled 3D point clouds and images.
  arXiv  Detail & Related papers  (2020-08-02T11:04:49Z)

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.