Live
Black Hat USADark ReadingBlack Hat AsiaAI BusinessAnthropic Found Emotion Circuits Inside Claude. They're Causing It to Blackmail People.DEV CommunityUnderstanding Transformers Part 1: How Transformers Understand Word OrderDEV CommunityI built an iOS app at 50 using AI tools. Here's what actually workedDEV CommunityIQVIA (IQV) Launches IQVIA.ai Unified Agentic AI Platform with Nvidia - Yahoo Finance SingaporeGNews AI agenticDesign Cost-Optimized Compute SolutionsDEV CommunityCodeClone b4: from CLI tool to a real review surface for VS Code, Claude Desktop, and CodexDEV CommunityHow to Publish a Power BI Report and Embed it into a Website.DEV CommunityKVerify: A Two-Year Journey to Get Validation RightDEV CommunityHow I Used Swarm Intelligence to Catch a Race Condition Before It Hit ProductionDEV CommunityDark Dish Lab: A Cursed Recipe GeneratorDEV CommunityUpload Large Folders to Cloudflare R2DEV Community10x Genomics (TXG) Is Up 14.6% After Analyst Upgrade Highlights AI-Scale Spatial Genomics Initiative - simplywall.stGNews AI genomicsBlack Hat USADark ReadingBlack Hat AsiaAI BusinessAnthropic Found Emotion Circuits Inside Claude. They're Causing It to Blackmail People.DEV CommunityUnderstanding Transformers Part 1: How Transformers Understand Word OrderDEV CommunityI built an iOS app at 50 using AI tools. Here's what actually workedDEV CommunityIQVIA (IQV) Launches IQVIA.ai Unified Agentic AI Platform with Nvidia - Yahoo Finance SingaporeGNews AI agenticDesign Cost-Optimized Compute SolutionsDEV CommunityCodeClone b4: from CLI tool to a real review surface for VS Code, Claude Desktop, and CodexDEV CommunityHow to Publish a Power BI Report and Embed it into a Website.DEV CommunityKVerify: A Two-Year Journey to Get Validation RightDEV CommunityHow I Used Swarm Intelligence to Catch a Race Condition Before It Hit ProductionDEV CommunityDark Dish Lab: A Cursed Recipe GeneratorDEV CommunityUpload Large Folders to Cloudflare R2DEV Community10x Genomics (TXG) Is Up 14.6% After Analyst Upgrade Highlights AI-Scale Spatial Genomics Initiative - simplywall.stGNews AI genomics
AI NEWS HUBbyEIGENVECTOREigenvector

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

arXiv cs.ROby [Submitted on 2 Apr 2026]April 3, 20262 min read1 views
Source Quiz

arXiv:2604.01517v1 Announce Type: cross 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 r

View PDF HTML (experimental)

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.

Subjects:

Systems and Control (eess.SY); Robotics (cs.RO)

Cite as: arXiv:2604.01517 [eess.SY]

(or arXiv:2604.01517v1 [eess.SY] for this version)

https://doi.org/10.48550/arXiv.2604.01517

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Chengjin Wang [view email] [v1] Thu, 2 Apr 2026 01:13:29 UTC (2,866 KB)

Was this article helpful?

Sign in to highlight and annotate this article

AI
Ask AI about this article
Powered by Eigenvector · full article context loaded
Ready

Conversation starters

Ask anything about this article…

Daily AI Digest

Get the top 5 AI stories delivered to your inbox every morning.

Knowledge Map

Knowledge Map
TopicsEntitiesSource
MorphoGuard…modelbenchmarkannounceplatformarxivarXiv cs.RO

Connected Articles — Knowledge Graph

This article is connected to other articles through shared AI topics and tags.

Knowledge Graph100 articles · 139 connections
Scroll to zoom · drag to pan · click to open

Discussion

Sign in to join the discussion

No comments yet — be the first to share your thoughts!