# WANDR: Intention-guided Human Motion Generation

arXiv: https://arxiv.org/abs/2404.15383 · HTML: https://mlsanity.com/paper/2404.15383/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 49 references that are in the map.
- First posted on arXiv 23 Apr 2024.

## Builds on (most cited first, 30 of 32)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [GRAB: A Dataset of Whole-Body Human Grasping of Objects](https://mlsanity.com/paper/2008.11200/) (2020)
- [Learning joint reconstruction of hands and manipulated objects](https://mlsanity.com/paper/1904.05767/) (2019)
- [On human motion prediction using recurrent neural networks](https://mlsanity.com/paper/1705.02445/) (2017)
- [HuMoR: 3D Human Motion Model for Robust Pose Estimation](https://mlsanity.com/paper/2105.04668/) (2021)
- [ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation](https://mlsanity.com/paper/2204.13662/) (2022)
- [Stochastic Scene-Aware Motion Prediction](https://mlsanity.com/paper/2108.08284/) (2021)
- [Long-term Human Motion Prediction with Scene Context](https://mlsanity.com/paper/2007.03672/) (2020)
- [Character Controllers Using Motion VAEs](https://mlsanity.com/paper/2103.14274/) (2021)
- [Capturing and Inferring Dense Full-Body Human-Scene Contact](https://mlsanity.com/paper/2206.09553/) (2022)
- [GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping](https://mlsanity.com/paper/2112.11454/) (2021)
- [COUCH: Towards Controllable Human-Chair Interactions](https://mlsanity.com/paper/2205.00541/) (2022)
- [A Spatio-temporal Transformer for 3D Human Motion Prediction](https://mlsanity.com/paper/2004.08692/) (2020)
- [Synthesizing Diverse Human Motions in 3D Indoor Scenes](https://mlsanity.com/paper/2305.12411/) (2023)
- [Synthesizing Physical Character-Scene Interactions](https://mlsanity.com/paper/2302.00883/) (2023)
- [GIMO: Gaze-Informed Human Motion Prediction in Context](https://mlsanity.com/paper/2204.09443/) (2022)
- [CIRCLE: Capture In Rich Contextual Environments](https://mlsanity.com/paper/2303.17912/) (2023)
- [ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation](https://mlsanity.com/paper/2203.07706/) (2022)
- [Learning Human Motion Models for Long-term Predictions](https://mlsanity.com/paper/1704.02827/) (2017)
- [The Wanderings of Odysseus in 3D Scenes](https://mlsanity.com/paper/2112.09251/) (2021)
- [Physically Plausible Full-Body Hand-Object Interaction Synthesis](https://mlsanity.com/paper/2309.07907/) (2023)
- [Spatiotemporal Co-attention Recurrent Neural Networks for Human-Skeleton Motion Prediction](https://mlsanity.com/paper/1909.13245/) (2019)
- [Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions](https://mlsanity.com/paper/1912.10150/) (2019)
- [Generating Continual Human Motion in Diverse 3D Scenes](https://mlsanity.com/paper/2304.02061/) (2023)

## Built on by (most cited first, 26 of 26)

- [MaskControl: Spatio-Temporal Control for Masked Motion Synthesis](https://mlsanity.com/paper/2410.10780/) (2024)
- [ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation](https://mlsanity.com/paper/2503.13130/) (2025)
- [Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing](https://mlsanity.com/paper/2410.18977/) (2024)
- [PRIMAL: Physically Reactive and Interactive Motor Model for Avatar Learning](https://mlsanity.com/paper/2503.17544/) (2025)
- [SCENIC: Scene-aware Semantic Navigation with Instruction-guided Control](https://mlsanity.com/paper/2412.15664/) (2024)
- [Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment](https://mlsanity.com/paper/2503.17267/) (2025)
- [Progressive Human Motion Generation Based on Text and Few Motion Frames](https://mlsanity.com/paper/2503.13300/) (2025)
- [Motion Generation: A Survey of Generative Approaches and Benchmarks](https://mlsanity.com/paper/2507.05419/) (2025)
- [3D Whole-body Grasp Synthesis with Directional Controllability](https://mlsanity.com/paper/2408.16770/) (2024)
- [ProjFlow: Projection Sampling with Flow Matching for Zero-Shot Exact Spatial Motion Control](https://mlsanity.com/paper/2602.22742/) (2026)
- [Moving by Looking: Towards Vision-Driven Avatar Motion Generation](https://mlsanity.com/paper/2509.19259/) (2025)
- [MotionHiFlow: Text-to-motion via hierarchical flow matching](https://mlsanity.com/paper/2604.23264/) (2026)
- [SIGHT: Synthesizing Image-Text Conditioned and Geometry-Guided 3D Hand-Object Trajectories](https://mlsanity.com/paper/2503.22869/) (2025)
- [JAX-IK: Real-Time Inverse Kinematics for Generating Multi-Constrained Movements of Virtual Human Characters](https://mlsanity.com/paper/2507.00792/) (2025)
- [Grounding Intelligence in Movement](https://mlsanity.com/paper/2507.02771/) (2025)
- [ScanMove: Motion Prediction and Transfer for Unregistered Body Meshes](https://mlsanity.com/paper/2508.21095/) (2025)
- [Controllable Long-term Motion Generation with Extended Joint Targets](https://mlsanity.com/paper/2512.04487/) (2025)
- [Prime and Reach: Synthesising Body Motion for Gaze-Primed Object Reach](https://mlsanity.com/paper/2512.16456/) (2025)
- [FUSION: Full-Body Unified Motion Prior for Body and Hands via Diffusion](https://mlsanity.com/paper/2601.03959/) (2026)
- [3HANDS Dataset: Learning from Humans for Generating Naturalistic Handovers with Supernumerary Robotic Limbs](https://mlsanity.com/paper/2503.04635/) (2025)
- [One-shot Adaptation of Humanoid Whole-body Motion with Walking Priors](https://mlsanity.com/paper/2510.25241/) (2025)
- [A Survey of Body and Face Motion: Datasets, Performance Evaluation Metrics and Generative Techniques](https://mlsanity.com/paper/2512.09005/) (2025)
- [Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control](https://mlsanity.com/paper/2605.14935/) (2026)
- [DCGrasp: Distance-aware Controllable Grasp Generation](https://mlsanity.com/paper/2606.29924/) (2026)
- [Generative Embodied Multiple Behavior Control Systems for Human-like Agents](https://mlsanity.com/paper/2609.22691/) (2026)
- [Generative Interactions: Weaving Multiparty Human Motion with Bilevel Latent Dynamics](https://mlsanity.com/paper/2609.37708/) (2026)

## Abstract (arXiv)

Synthesizing natural human motions that enable a 3D human avatar to walk and reach for arbitrary goals in 3D space remains an unsolved problem with many applications. Existing methods (data-driven or using reinforcement learning) are limited in terms of generalization and motion naturalness. A primary obstacle is the scarcity of training data that combines locomotion with goal reaching. To address this, we introduce WANDR, a data-driven model that takes an avatar's initial pose and a goal's 3D position and generates natural human motions that place the end effector (wrist) on the goal location. To solve this, we introduce novel intention features that drive rich goal-oriented movement. Intention guides the agent to the goal, and interactively adapts the generation to novel situations without needing to define sub-goals or the entire motion path. Crucially, intention allows training on datasets that have goal-oriented motions as well as those that do not. WANDR is a conditional Variational Auto-Encoder (c-VAE), which we train using the AMASS and CIRCLE datasets. We evaluate our method extensively and demonstrate its ability to generate natural and long-term motions that reach 3D goals and generalize to unseen goal locations. Our models and code are available for research purposes at wandr.is.tue.mpg.de.