# HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model

arXiv: https://arxiv.org/abs/2602.11758 · HTML: https://mlsanity.com/paper/2602.11758/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Humanoid and legged locomotion world models, one of 11 directions in World models.
- Builds on 19 of its 78 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Placed in

- World models / [Humanoid and legged locomotion world models](https://mlsanity.com/wm/humanoid-and-legged-locomotion-world-models/)

## Builds on (most cited first, 19 of 19)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion](https://mlsanity.com/paper/2508.08241/) (2025)
- [SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control](https://mlsanity.com/paper/2511.07820/) (2025)
- [Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning](https://mlsanity.com/paper/2408.14472/) (2024)
- [Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics](https://mlsanity.com/paper/2501.10100/) (2025)
- [THOR: Text to Human-Object Interaction Diffusion via Relation Intervention](https://mlsanity.com/paper/2403.11208/) (2024)
- [TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System](https://mlsanity.com/paper/2511.02832/) (2025)
- [LeVERB: Humanoid Whole-Body Control with Latent Vision-Language Instruction](https://mlsanity.com/paper/2506.13751/) (2025)
- [WholeBodyVLA: Towards Unified Latent VLA for Whole-Body Loco-Manipulation Control](https://mlsanity.com/paper/2512.11047/) (2025)
- [Hierarchical World Models as Visual Whole-Body Humanoid Controllers](https://mlsanity.com/paper/2405.18418/) (2024)
- [World Model-based Perception for Visual Legged Locomotion](https://mlsanity.com/paper/2409.16784/) (2024)
- [Object-Centric World Model for Language-Guided Manipulation](https://mlsanity.com/paper/2503.06170/) (2025)
- [DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusion](https://mlsanity.com/paper/2509.14353/) (2025)
- [Learning Humanoid Locomotion with World Model Reconstruction](https://mlsanity.com/paper/2502.16230/) (2025)
- [Learning Interactive World Model for Object-Centric Reinforcement Learning](https://mlsanity.com/paper/2511.02225/) (2025)
- [Ego-Vision World Model for Humanoid Contact Planning](https://mlsanity.com/paper/2510.11682/) (2025)

## Built on by (most cited first, 4 of 4)

- [SplitAdapter: Load-Aware Humanoid Loco-Manipulation via Factorized Adaptation](https://mlsanity.com/paper/2606.03297/) (2026)
- [Self-Evolving AI for Humanoids: Mechanisms, Safety, and Evaluation of Post-Deployment Self-Improvement](https://mlsanity.com/paper/2609.13236/) (2026)
- [LUCID: Latent-Skill Unified Control via Imagined Dynamics for Long-Horizon Humanoid Loco-Manipulation](https://mlsanity.com/paper/2608.07746/) (2026)
- [Humanoid Rickshaw Pulling: Whole-Body Locomotion under Coupled Wheeled Loads](https://mlsanity.com/paper/2610.04238/) (2026)

## Abstract (arXiv)

Humanoid robots show promise for complex whole-body tasks in unstructured environments. Although Human-Object Interaction (HOI) has advanced, most methods focus on fully actuated objects rigidly coupled to the robot, ignoring underactuated objects with independent dynamics and non-holonomic constraints. These introduce control challenges from coupling forces and occlusions. We present HAIC, a unified framework for robust interaction across diverse object dynamics without external state estimation. Our key contribution is a dynamics predictor that estimates high-order object states (velocity, acceleration) solely from proprioceptive history. These predictions are projected onto static geometric priors to form a spatially grounded dynamic occupancy map, enabling the policy to infer collision boundaries and contact affordances in blind spots. We use asymmetric fine-tuning, where a world model continuously adapts to the student policy's exploration, ensuring robust state estimation under distribution shifts. Experiments on a humanoid robot show HAIC achieves high success rates in agile tasks (skateboarding, cart pushing/pulling under various loads) by proactively compensating for inertial perturbations, and also masters multi-object long-horizon tasks like carrying a box across varied terrain by predicting the dynamics of multiple objects.