# DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References

arXiv: https://arxiv.org/abs/2502.09614 · HTML: https://mlsanity.com/paper/2502.09614/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 35 of its 41 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 30 of 35)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [GRAB: A Dataset of Whole-Body Human Grasping of Objects](https://mlsanity.com/paper/2008.11200/) (2020)
- [Perpetual Humanoid Control for Real-time Simulated Avatars](https://mlsanity.com/paper/2305.06456/) (2023)
- [DexMV: Imitation Learning for Dexterous Manipulation from Human Videos](https://mlsanity.com/paper/2108.05877/) (2021)
- [DART: Noise Injection for Robust Imitation Learning](https://mlsanity.com/paper/1703.09327/) (2017)
- [A System for General In-Hand Object Re-Orientation](https://mlsanity.com/paper/2111.03043/) (2021)
- [UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy](https://mlsanity.com/paper/2303.00938/) (2023)
- [Universal Humanoid Motion Representations for Physics-Based Control](https://mlsanity.com/paper/2310.04582/) (2023)
- [D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions](https://mlsanity.com/paper/2112.03028/) (2021)
- [Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes](https://mlsanity.com/paper/2211.11744/) (2022)
- [Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control](https://mlsanity.com/paper/2401.16889/) (2024)
- [TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding](https://mlsanity.com/paper/2401.08399/) (2024)
- [LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning](https://mlsanity.com/paper/2309.06440/) (2023)
- [PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction](https://mlsanity.com/paper/2312.04393/) (2023)
- [DTC: Deep Tracking Control](https://mlsanity.com/paper/2309.15462/) (2023)
- [ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation](https://mlsanity.com/paper/2309.03891/) (2023)
- [Learning Generalizable Dexterous Manipulation from Human Grasp Affordance](https://mlsanity.com/paper/2204.02320/) (2022)
- [Global Planning for Contact-Rich Manipulation via Local Smoothing of Quasi-dynamic Contact Models](https://mlsanity.com/paper/2206.10787/) (2022)
- [Omnigrasp: Grasping Diverse Objects with Simulated Humanoids](https://mlsanity.com/paper/2407.11385/) (2024)
- [Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning](https://mlsanity.com/paper/1805.11240/) (2018)
- [Hand-Object Interaction Pretraining from Videos](https://mlsanity.com/paper/2409.08273/) (2024)
- [Learning Dexterous Manipulation for a Soft Robotic Hand from Human Demonstration](https://mlsanity.com/paper/1603.06348/) (2016)
- [ViViDex: Learning Vision-based Dexterous Manipulation from Human Videos](https://mlsanity.com/paper/2404.15709/) (2024)

## Built on by (most cited first, 17 of 17)

- [DexVLG: Dexterous Vision-Language-Grasp Model at Scale](https://mlsanity.com/paper/2507.02747/) (2025)
- [DemoDiffusion: One-Shot Human Imitation using pre-trained Diffusion Policy](https://mlsanity.com/paper/2506.20668/) (2025)
- [Dex4D: Task-Agnostic Point Track Policy for Zero-Shot Dexterous Manipulation](https://mlsanity.com/paper/2602.15828/) (2026)
- [Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference-Scoped Exploration](https://mlsanity.com/paper/2509.09671/) (2025)
- [DexMan: Learning Bimanual Dexterous Manipulation from Human and Generated Videos](https://mlsanity.com/paper/2510.08475/) (2025)
- [Scaffolding Dexterous Manipulation with Vision-Language Models](https://mlsanity.com/paper/2506.19212/) (2025)
- [FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation](https://mlsanity.com/paper/2602.13444/) (2026)
- [TopoRetarget: Interaction-Preserving Retargeting for Dexterous Manipulation](https://mlsanity.com/paper/2606.16272/) (2026)
- [Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration](https://mlsanity.com/paper/2607.00033/) (2026)
- [LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition](https://mlsanity.com/paper/2606.11628/) (2026)
- [PAM: A Pose-Appearance-Motion Engine for Sim-to-Real HOI Video Generation](https://mlsanity.com/paper/2603.22193/) (2026)
- [Learning Adaptive Dexterous Grasping from Single Demonstrations](https://mlsanity.com/paper/2503.20208/) (2025)
- [Tele-Catch: Adaptive Teleoperation for Dexterous Dynamic 3D Object Catching](https://mlsanity.com/paper/2603.28427/) (2026)
- [DexTaG: Tactile-as-Guidance in Reinforcement Learning for Dexterous Manipulation](https://mlsanity.com/paper/2609.33882/) (2026)
- [DexPolicy: Scheduled Exploration for Trajectory-Guided Dexterous Manipulation](https://mlsanity.com/paper/2610.00360/) (2026)
- [GOTT: Object-centric Dexterous Manipulation with a Reusable Cross-Embodiment Primitive](https://mlsanity.com/paper/2610.03861/) (2026)
- [DexMimic: A Generalist Dexterous Hand-Object Tracking Policy via Value-Guided Reset Allocation](https://mlsanity.com/paper/2610.19089/) (2026)

## Abstract (arXiv)

We address the challenge of developing a generalizable neural tracking controller for dexterous manipulation from human references. This controller aims to manage a dexterous robot hand to manipulate diverse objects for various purposes defined by kinematic human-object interactions. Developing such a controller is complicated by the intricate contact dynamics of dexterous manipulation and the need for adaptivity, generalizability, and robustness. Current reinforcement learning and trajectory optimization methods often fall short due to their dependence on task-specific rewards or precise system models. We introduce an approach that curates large-scale successful robot tracking demonstrations, comprising pairs of human references and robot actions, to train a neural controller. Utilizing a data flywheel, we iteratively enhance the controller's performance, as well as the number and quality of successful tracking demonstrations. We exploit available tracking demonstrations and carefully integrate reinforcement learning and imitation learning to boost the controller's performance in dynamic environments. At the same time, to obtain high-quality tracking demonstrations, we individually optimize per-trajectory tracking by leveraging the learned tracking controller in a homotopy optimization method. The homotopy optimization, mimicking chain-of-thought, aids in solving challenging trajectory tracking problems to increase demonstration diversity. We showcase our success by training a generalizable neural controller and evaluating it in both simulation and real world. Our method achieves over a 10% improvement in success rates compared to leading baselines. The project website with animated results is available at https://meowuu7.github.io/DexTrack/.