# TaskNPoint: How to Teach Your Humanoid to Hit a Backhand in Minutes

arXiv: https://arxiv.org/abs/2606.26215 · HTML: https://mlsanity.com/paper/2606.26215/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 45 of its 57 references that are in the map.
- First posted on arXiv 24 Jun 2026.

## Builds on (most cited first, 30 of 45)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans](https://mlsanity.com/paper/2012.15838/) (2020)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [Learning 3D Human Dynamics from Video](https://mlsanity.com/paper/1812.01601/) (2018)
- [BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion](https://mlsanity.com/paper/2508.08241/) (2025)
- [Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video](https://mlsanity.com/paper/2011.08627/) (2020)
- [World-Grounded Human Motion Recovery via Gravity-View Coordinates](https://mlsanity.com/paper/2409.06662/) (2024)
- [Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning](https://mlsanity.com/paper/2304.13653/) (2023)
- [Universal Humanoid Motion Representations for Physics-Based Control](https://mlsanity.com/paper/2310.04582/) (2023)
- [SimPoE: Simulated Character Control for 3D Human Pose Estimation](https://mlsanity.com/paper/2104.00683/) (2021)
- [TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos](https://mlsanity.com/paper/2403.17346/) (2024)
- [2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning](https://mlsanity.com/paper/1802.09232/) (2018)
- [Learning Motion Priors for 4D Human Body Capture in 3D Scenes](https://mlsanity.com/paper/2108.10399/) (2021)
- [Expressive Whole-Body 3D Gaussian Avatar](https://mlsanity.com/paper/2407.21686/) (2024)
- [Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking](https://mlsanity.com/paper/2510.02252/) (2025)
- [OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction](https://mlsanity.com/paper/2509.26633/) (2025)
- [Visual Imitation Enables Contextual Humanoid Control](https://mlsanity.com/paper/2505.03729/) (2025)
- [GENMO: A GENeralist Model for Human MOtion](https://mlsanity.com/paper/2505.01425/) (2025)
- [BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds](https://mlsanity.com/paper/2502.10363/) (2025)
- [TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System](https://mlsanity.com/paper/2511.02832/) (2025)
- [D&D: Learning Human Dynamics from Dynamic Camera](https://mlsanity.com/paper/2209.08790/) (2022)
- [HDMI: Learning Interactive Humanoid Whole-Body Control from Human Videos](https://mlsanity.com/paper/2509.16757/) (2025)
- [HITTER: A HumanoId Table TEnnis Robot via Hierarchical Planning and Learning](https://mlsanity.com/paper/2508.21043/) (2025)
- [On the Benefits of 3D Pose and Tracking for Human Action Recognition](https://mlsanity.com/paper/2304.01199/) (2023)
- [SkillMimic: Learning Basketball Interaction Skills from Demonstrations](https://mlsanity.com/paper/2408.15270/) (2024)
- [SMPLOlympics: Sports Environments for Physically Simulated Humanoids](https://mlsanity.com/paper/2407.00187/) (2024)

## Abstract (arXiv)

How do we learn to hit a tennis backhand? Not from a thousand hours of tennis tournaments on TV - we work with a coach and practice. We argue this is also the right recipe for teaching dynamic skills to humanoid robots. This follows from a structural property of dynamic skills: the outcome is decided by a short, crucial portion of the trajectory - for a backhand, the ~20cm of racket travel around ball contact. Getting this interaction window right requires coordinating the whole motion, so that control, physics, and morphology act in concert. Learning thus reduces to mastering a handful of distinct actions and, for each, practicing until the window comes out right. To this end, we introduce TaskNPoint, a training protocol which makes the coach-learner division of labor explicit. The human coach contributes four inputs: a discrete set of skills (e.g. different shots), one demonstration per skill, identification of the interaction window, and the goal. Learning in a physically realistic simulation environment fills in each action trajectory and provides robustness to unmodeled events. Crucially, randomized target sampling during training lets a single demonstration generalize zero-shot to unseen goal locations. We test this approach on a Unitree G1 humanoid that hits forehands and backhands against balls thrown by a human, kicks incoming soccer balls, and picks and places boxes from novel locations. We find that learning is successful from short human video demonstrations and under an hour of training on a single GPU, with no per-task reward tuning.