Physics-Based Dexterous Manipulations with Estimated Hand Poses and Residual Reinforcement Learning

• URL: http://arxiv.org/abs/2008.03285v1
• Date: Fri, 7 Aug 2020 17:34:28 GMT
• Title: Physics-Based Dexterous Manipulations with Estimated Hand Poses and Residual Reinforcement Learning
• Authors: Guillermo Garcia-Hernando and Edward Johns and Tae-Kyun Kim
• Abstract summary: We learn a model that maps noisy input hand poses to target virtual poses. The agent is trained in a residual setting by using a model-free hybrid RL+IL approach. We test our framework in two applications that use hand pose estimates for dexterous manipulations: hand-object interactions in VR and hand-object motion reconstruction in-the-wild.
• Score: 52.37106940303246
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dexterous manipulation of objects in virtual environments with our bare hands, by using only a depth sensor and a state-of-the-art 3D hand pose estimator (HPE), is challenging. While virtual environments are ruled by physics, e.g. object weights and surface frictions, the absence of force feedback makes the task challenging, as even slight inaccuracies on finger tips or contact points from HPE may make the interactions fail. Prior arts simply generate contact forces in the direction of the fingers' closures, when finger joints penetrate virtual objects. Although useful for simple grasping scenarios, they cannot be applied to dexterous manipulations such as in-hand manipulation. Existing reinforcement learning (RL) and imitation learning (IL) approaches train agents that learn skills by using task-specific rewards, without considering any online user input. In this work, we propose to learn a model that maps noisy input hand poses to target virtual poses, which introduces the needed contacts to accomplish the tasks on a physics simulator. The agent is trained in a residual setting by using a model-free hybrid RL+IL approach. A 3D hand pose estimation reward is introduced leading to an improvement on HPE accuracy when the physics-guided corrected target poses are remapped to the input space. As the model corrects HPE errors by applying minor but crucial joint displacements for contacts, this helps to keep the generated motion visually close to the user input. Since HPE sequences performing successful virtual interactions do not exist, a data generation scheme to train and evaluate the system is proposed. We test our framework in two applications that use hand pose estimates for dexterous manipulations: hand-object interactions in VR and hand-object motion reconstruction in-the-wild.

Related papers

• Hand-Object Interaction Controller (HOIC): Deep Reinforcement Learning for Reconstructing Interactions with Physics [12.443255379595278]
  We reconstruct hand manipulating motion with a single RGBD camera by a novel deep reinforcement learning method. We propose object compensation control which establishes direct object control to make the network training more stable. By leveraging the compensation force and torque, we seamlessly upgrade the simple point contact model to a more physical-plausible surface contact model.
  arXiv  Detail & Related papers  (2024-05-04T14:32:13Z)
• Neural feels with neural fields: Visuo-tactile perception for in-hand manipulation [57.60490773016364]
  We combine vision and touch sensing on a multi-fingered hand to estimate an object's pose and shape during in-hand manipulation. Our method, NeuralFeels, encodes object geometry by learning a neural field online and jointly tracks it by optimizing a pose graph problem. Our results demonstrate that touch, at the very least, refines and, at the very best, disambiguates visual estimates during in-hand manipulation.
  arXiv  Detail & Related papers  (2023-12-20T22:36:37Z)
• Learning Explicit Contact for Implicit Reconstruction of Hand-held Objects from Monocular Images [59.49985837246644]
  We show how to model contacts in an explicit way to benefit the implicit reconstruction of hand-held objects. In the first part, we propose a new subtask of directly estimating 3D hand-object contacts from a single image. In the second part, we introduce a novel method to diffuse estimated contact states from the hand mesh surface to nearby 3D space.
  arXiv  Detail & Related papers  (2023-05-31T17:59:26Z)
• Reconfigurable Data Glove for Reconstructing Physical and Virtual Grasps [100.72245315180433]
  We present a reconfigurable data glove design to capture different modes of human hand-object interactions. The glove operates in three modes for various downstream tasks with distinct features. We evaluate the system's three modes by (i) recording hand gestures and associated forces, (ii) improving manipulation fluency in VR, and (iii) producing realistic simulation effects of various tool uses.
  arXiv  Detail & Related papers  (2023-01-14T05:35:50Z)
• Towards unconstrained joint hand-object reconstruction from RGB videos [81.97694449736414]
  Reconstructing hand-object manipulations holds a great potential for robotics and learning from human demonstrations. We first propose a learning-free fitting approach for hand-object reconstruction which can seamlessly handle two-hand object interactions.
  arXiv  Detail & Related papers  (2021-08-16T12:26:34Z)
• UNOC: Understanding Occlusion for Embodied Presence in Virtual Reality [12.349749717823736]
  In this paper, we propose a new data-driven framework for inside-out body tracking. We first collect a large-scale motion capture dataset with both body and finger motions. We then simulate the occlusion patterns in head-mounted camera views on the captured ground truth using a ray casting algorithm and learn a deep neural network to infer the occluded body parts.
  arXiv  Detail & Related papers  (2020-11-12T09:31:09Z)
• Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction [137.28465645405655]
  HANDS'19 is a challenge to evaluate the abilities of current 3D hand pose estimators (HPEs) to interpolate and extrapolate the poses of a training set. We show that the accuracy of state-of-the-art methods can drop, and that they fail mostly on poses absent from the training set.
  arXiv  Detail & Related papers  (2020-03-30T19:28:13Z)

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.