HOTICE: Whole-Body Humanoid Object Transportation in Cluttered Environments

Summary

Abstract Summary

Object transportation is a fundamental capability for humanoid robots operating in real-world, human-centric environments, yet existing methods struggle when clutter constrains free space around both the robot and its carried payload. We present HOTICE, a whole-body humanoid learning framework for transporting objects through such cluttered environments. First, we introduce Humanoid-Object Decoupled Potential Fields, which jointly encode collision-avoidance guidance for the robot and the carried object, enabling coordinated, obstacle-aware motion for both. Second, to address the large action space inherent to whole-body loco-manipulation, we design a dual-agent reinforcement learning architecture that decouples upper- and lower-body control while preserving whole-body coordination via shared state observations and rewards. To train a policy that generalizes across diverse cluttered scenes, we further employ a specialist-to-generalist distillation strategy, in which privileged teacher policies are distilled into a single deployable student policy. We evaluate HOTICE in MuJoCo simulation and on a real Unitree G1 humanoid, demonstrating effective and robust object transportation across cluttered scenarios for objects of varying shapes. Our results show that HOTICE reliably coordinates whole-body motion and object-aware collision avoidance, generalizing effectively to previously unseen cluttered environments while achieving strong performance in sim2real deployment.

Key Points

Object transportation is a fundamental capability for humanoid robots operating in real-world, human-centric environments, yet existing methods struggle when clutter constrains free space around both the robot and its carried payload.
We present HOTICE, a whole-body humanoid learning framework for transporting objects through such cluttered environments.
First, we introduce Humanoid-Object Decoupled Potential Fields, which jointly encode collision-avoidance guidance for the robot and the carried object, enabling coordinated, obstacle-aware motion for both.
Second, to address the large action space inherent to whole-body loco-manipulation, we design a dual-agent reinforcement learning architecture that decouples upper- and lower-body control while preserving whole-body coordination via shared state observations and rewards.
To train a policy that generalizes across diverse cluttered scenes, we further employ a specialist-to-generalist distillation strategy, in which privileged teacher policies are distilled into a single deployable student policy.

PROBLEM STATEMENT

We investigate a humanoid loco-manipulation object transportation setting.

Given a cluttered environment populated by obstacles of different types (side, ground, and overhead obstacles), the robot starts at a starting position $\mathbf{s}\in\mathbb{R}^{3}$ holding an object $\mathscr{O}$ and is required to transport $\mathscr{O}$ to a target position $\mathbf{g}\in\mathbb{R}^{3}$ without colliding with the obstacles $\mathscr{C}$. The object $\mathscr{O}$ can be of different shapes.

PROBLEM STATEMENT — HOTICE: Whole-Body Humanoid Object Transportation in Cluttered Environments — Fig. 2: Method Overview. HOTICE is composed of three main components. Humanoid-Object Decoupled Potential Fields (top left) : a Standard Guidance Field guides the robot’s head, pelvis, and feet, while an Object-Centric Guidance Field guides the carried object and the robot’s hands. Dual-Agent Learning Architecture (top right) : the whole-body control is split between an upper-body actor-critic and a lower-body actor-critic, each with its own body-specific reward set, but remain coordinated via unified state observations and shared whole-body rewards. Specialist-to-Generalist Training (bottom) : privileged teacher policies are trained across diverse procedurally generated and realistic scenes, then distilled via DAgger and RL fine-tuning into a single generalist student policy that is deployed on the real Unitree G1 humanoid robot.

Method

We present H umanoid O bject T ransportation I n C luttered E nvironments ( HOTICE ), an RL whole-body humanoid learning framework for transporting objects while avoiding collisions with diverse obstacles.

Experiments

We conduct extensive experiments in both simulation (Section V-A ) and the real world (Section V-B ) to validate the performance and generalizability of our proposed HOTICE . Main Experiments. We first investigate the effectiveness of our method in enabling humanoid robots to transport objects in cluttered scenes while avoiding collisions with complex obstacles.

Since no prior method directly addresses our problem setting, we assess the significance of our key contributions through ablations of HOTICE .

Experiments — HOTICE: Whole-Body Humanoid Object Transportation in Cluttered Environments — Fig. 4: Qualitative Results in Simulation. (A) - left comparison – The proposed decoupled potential fields enable HOTICE to more reliably avoid collisions during object transportation. (A) - right comparison – Our method is capable of maintaining the robot’s balance and stability under challenging obstacle conditions thanks to the dual-agent architecture. (B) – Our method effectively handles a wide variety of challenging procedurally generated scenes (upper row) and realistic indoor scenes (lower row) , without any scene-specific reward tuning.

Sources and Demonstrations

Figures are reproduced from Nguyen et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.