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

arXiv: https://arxiv.org/abs/2008.03285 · HTML: https://mlsanity.com/paper/2008.03285/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2020.

## Built on by (most cited first, 30 of 37)

- [DexMV: Imitation Learning for Dexterous Manipulation from Human Videos](https://mlsanity.com/paper/2108.05877/) (2021)
- [GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping](https://mlsanity.com/paper/2112.11454/) (2021)
- [Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time](https://mlsanity.com/paper/2106.05266/) (2021)
- [D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions](https://mlsanity.com/paper/2112.03028/) (2021)
- [From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperation](https://mlsanity.com/paper/2204.12490/) (2022)
- [PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction](https://mlsanity.com/paper/2312.04393/) (2023)
- [ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning](https://mlsanity.com/paper/2503.21860/) (2025)
- [DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions](https://mlsanity.com/paper/2403.17827/) (2024)
- [ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation](https://mlsanity.com/paper/2309.03891/) (2023)
- [Physically Plausible Full-Body Hand-Object Interaction Synthesis](https://mlsanity.com/paper/2309.07907/) (2023)
- [Zero-Shot Robot Manipulation from Passive Human Videos](https://mlsanity.com/paper/2302.02011/) (2023)
- [Learning Continuous Grasping Function with a Dexterous Hand from Human Demonstrations](https://mlsanity.com/paper/2207.05053/) (2022)
- [InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion](https://mlsanity.com/paper/2403.17422/) (2024)
- [GRIP: Generating Interaction Poses Using Spatial Cues and Latent Consistency](https://mlsanity.com/paper/2308.11617/) (2023)
- [A Survey on Physics Informed Reinforcement Learning: Review and Open Problems](https://mlsanity.com/paper/2309.01909/) (2023)
- [DexTransfer: Real World Multi-fingered Dexterous Grasping with Minimal Human Demonstrations](https://mlsanity.com/paper/2209.14284/) (2022)
- [Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation](https://mlsanity.com/paper/2303.04991/) (2023)
- [Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation](https://mlsanity.com/paper/2403.04381/) (2024)
- [Tracking and Reconstructing Hand Object Interactions from Point Cloud Sequences in the Wild](https://mlsanity.com/paper/2209.12009/) (2022)
- [Dense Hand-Object(HO) GraspNet with Full Grasping Taxonomy and Dynamics](https://mlsanity.com/paper/2409.04033/) (2024)
- [SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis](https://mlsanity.com/paper/2412.20104/) (2024)
- [One-Shot Imitation under Mismatched Execution](https://mlsanity.com/paper/2409.06615/) (2024)
- [Learning by Watching: A Review of Video-based Learning Approaches for Robot Manipulation](https://mlsanity.com/paper/2402.07127/) (2024)
- [Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping](https://mlsanity.com/paper/2410.02475/) (2024)
- [DexMan: Learning Bimanual Dexterous Manipulation from Human and Generated Videos](https://mlsanity.com/paper/2510.08475/) (2025)
- [PianoMime: Learning a Generalist, Dexterous Piano Player from Internet Demonstrations](https://mlsanity.com/paper/2407.18178/) (2024)
- [DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation](https://mlsanity.com/paper/2310.07206/) (2023)
- [HandDGP: Camera-Space Hand Mesh Prediction with Differentiable Global Positioning](https://mlsanity.com/paper/2407.15844/) (2024)
- [Learning to Transfer In-Hand Manipulations Using a Greedy Shape Curriculum](https://mlsanity.com/paper/2303.12726/) (2023)
- [Single-View Scene Point Cloud Human Grasp Generation](https://mlsanity.com/paper/2404.15815/) (2024)

## Abstract (arXiv)

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.