MorphoGuard: A Morphology-Based Whole-Body Interactive Motion Controller

Chenjin Wang; Zheng Yan; Yanmin Zhou; Runjie Shen; Bin He

eess.SYApr 2, 2026

MorphoGuard: A Morphology-Based Whole-Body Interactive Motion Controller

Authors: Chenjin Wang, Zheng Yan, Yanmin Zhou, Runjie Shen, Bin He

Organizations: Shanghai Research Institute for Intelligent Autonomous Systems Shanghai 201210, China · College of Electronics and Information Engineering (Tongji University) Shanghai 201210, China

Abstract

Whole-body control (WBC) has demonstrated significant advantages in complex interactive movements of high-dimensional robotic systems. However, when a robot is required to handle dynamic multi-contact combinations along a single kinematic chain-such as pushing open a door with its elbow while grasping an object-it faces major obstacles in terms of complex contact representation and joint configuration coupling. To address this, we propose a new control approach that explicitly manages arbitrary contact combinations, aiming to endow robots with whole-body interactive capabilities. We develop a morphology-constrained WBC network (MorphoGuard)-which is trained on a self-constructed dual-arm physical and simulation platform. A series of model recommendation experiments are designed to systematically investigate the impact of backbone architecture, fusion strategy, and model scale on network performance. To evaluate the control performance, we adopt a multi-object interaction task as the benchmark, requiring the model to simultaneously manipulate multiple target objects to specified positions. Experimental results show that the proposed method achieves a contact point management error of approximately 1 cm, demonstrating its effectiveness in whole-body interactive control.

Figures & tables

Figure 1: Schematic of morphology-based whole-body motion control (MorphoGuard). (A) An example of a robot facing complex contact combinations in an unstructured environment. (B) MorphoGuard is tasked with learning a mapping from the entity morphology in the workspace to the configuration space. (C) MorphoGuard takes as input MPs that discretely represent the robot morphology and predicts the corresponding joint motion commands.

Figure 2: An overview of the MorphoGuard framework. The model consists of a MPs encoding module, an fusion module, and a joint command decoding module. The morphology encoding module encodes the current morphology and the target morphology into feature representations. The information fusion module integrates the encoded features to capture the relationship between the current and target morphologies. Finally, the joint command decoding module predicts the joint commands based on the fused features.

Figure 3: Simulation and physical platform used for data collection.

Architecture	Core Inductive Bias	Configuration	Params	FLOPs
MLP	Global Feature Combination	4-layer MLP, 512-512-256-128	1.5M	12M
CNN	Locality + Translation Invariance	ResNet-18	11M	1.8G
Transformer	Long-range Dependencies	6 layers, 4 heads, 512 dim	65M	3.2G
GNN	Graph Structure Propagation	4-layer GAT, 128 dim	0.8M	8M

Table 1: Architecture Comparison - Core Metrics Focus

Figure 4: Training and validation loss curves for different backbone architectures. The MLP backbone demonstrates the lowest validation loss, indicating superior generalization performance compared to CNN, Transformer, and GNN backbones.

Model Name	Params (M)	Backbone Config	FLOPs (G)	Inference Time (ms)
		(Layers $\times$ Width)		(batch=64)
small_5m	5.9	8 $\times$ 512	0.75	0.8–1.2
medium_10m	10.2	8 $\times$ 768	1.95	1.2–1.5
medium_25m	25.9	10 $\times$ 1024	3.95	4.5–6.5
large_50m	51.9	22 $\times$ 1024	6.64	7.5–10.5
large_100m	115.4	22 $\times$ 1536	15.05	18–25

Table 2: MLP Scaling Experiment: Model Architecture and Computational Efficiency

Model Size	Val Loss	Val Std	Rel Improvement (%)	p-value	Sig
Scale Small 5M	0.0292	0.0229	0.00	nan	ns
Scale Medium 10M	0.0178	0.0208	39.02	0.0204
Scale Medium 25M	0.0116	0.0151	60.27	0.0204
Scale Large 50M	0.0096	0.0127	67.18	0.0257
Scale Large 100M	0.0095	0.0120	67.50	0.0291
Scale Xlarge 200M	0.0104	0.0133	64.36	0.0234

Table 3: Model Scale Comparison Results

Fusion Method	Val Loss	Val Std	Rel Improvement (%)	p-value	Sig
Additive	0.0159	0.0211	0.00	—	—
Concat	0.0232	0.0248	-45.81	0.1112
Input Concat	0.0171	0.0230	-7.86	0.2473
Parallel Branch	0.0321	0.0218	-102.05	0.0407	$*$
Adaptive Norm	0.0178	0.0229	-11.90	0.1015

Table 4: Fusion Method Comparison Results

Figure 6: Test procedure and object trajectories for the sequential manipulation task. (A)sequential manipulation task. (B)simultaneous manipulation task.

Figure 7: Test results for the multi-object manipulation tasks. (A) Contact point error for the sequential manipulation task. (B) Contact point error for the simultaneous manipulation task.

Robotic Control

Robotic control studies how machines use sensing and computation to produce reliable movement and interaction in changing environments.

See all 584 papers

Interaction-Aware Whole-Body Control for Compliant Object Transport
Mar 4, 2026Hao Zhang, Yves Tseng, Ding Zhao +1Humanoid Robot Control Whole-Body Control
Department of Electrical Engineering, the University of Texas at Arlington, 76010 Arlington, USA · Department of Mechanical Engineering, Carnegie Mellon University, 15213 Pittsburgh, USA
Whole-Body Dexterity
Oct 15, 2026Conor Mc Gartoll, An Dang, Pranay Thangeda +5Whole-Body Robotic Manipulation Long-Horizon Robotic Manipulation
Amazon · University of California, San Diego · University of Michigan
ZeroWBC: Learning Natural Whole-Body Humanoid Interaction from Human Egocentric Data
Mar 10, 2026Haoran Yang, Jiacheng Bao, Yucheng Xin +5Human Motion Generation Whole-Body Control
University of Science and Technology of China · Shanghai AI Laboratory · Tsinghua University +2

Mar 4, 2026J/K move · Enter open · S save

Interaction-Aware Whole-Body Control for Compliant Object Transport

Hao Zhang, Yves Tseng, Ding Zhao, H. Eric Tseng

Department of Electrical Engineering, the University of Texas at Arlington, 76010 Arlington, USA · Department of Mechanical Engineering, Carnegie Mellon University, 15213 Pittsburgh, USA

Humanoid Robot Control Whole-Body Control Whole-Body Robotic Manipulation

Open paper AskPDF arXiv

Cooperative object transport in unstructured environments remains challenging for assistive humanoids because strong, time-varying interaction forces can make tracking-centric whole-body control unreliable, especially in close-contact support tasks. This paper proposes a bio-inspired, interaction-oriented whole-body control (IO-WBC) that functions as an artificial cerebellum - an adaptive motor agent that translates upstream (skill-level) commands into stable, physically consistent whole-body behavior under contact. This work structurally separates upper-body interaction execution from lower-body support control, enabling the robot to maintain balance while shaping force exchange in a tightly coupled robot-object system. A trajectory-optimized reference generator (RG) provides a kinematic prior, while a reinforcement learning (RL) policy governs body responses under heavy-load interactions and disturbances. The policy is trained in simulation with randomized payload mass/inertia and external perturbations, and deployed via asymmetric teacher-student distillation so that the student relies only on proprioceptive histories at runtime. Extensive experiments demonstrate that IO-WBC maintains stable whole-body behavior and physical interaction even when precise velocity tracking becomes infeasible, enabling compliant object transport across a wide range of scenarios.

Abstract

Robotic Control

Explore similar work

Interaction-Aware Whole-Body Control for Compliant Object Transport

Whole-Body Dexterity

ZeroWBC: Learning Natural Whole-Body Humanoid Interaction from Human Egocentric Data