OnBodyAI - Why the Next AI Needs a Body

Michael Beigl

cs.HCOct 15, 2026

OnBodyAI - Why the Next AI Needs a Body

Authors: Michael Beigl

Organizations: Karlsruhe Institute of Technology (KIT), Germany

Abstract

The next AI will not win by knowing more about the world. It will win because it knows you: because it lives on your body, works for you and answers to you. That is what the term OnBodyAI stands for. It describes what happens when large language models are given a body, and what research and industry need to make that happen. This article is based on my talk in the Industrial Panel at UbiComp/ISWC 2026 in Shanghai (October 13, 2026) and follows its ten key statements.

Embodied AI

Embodied AI studies agents that perceive, reason, and act through bodies in physical or simulated environments.

See all 255 papers

Know Your Body: A Harness for Direct and Self-Improving Robot Control with VLMs
Sep 22, 2026Zeyu Lou, Yanhong Zeng, Yong Wang +1VLMs for Robotics Large Language Model-Based Robot Planning
Nanjing University · Ant Group · Zhejiang University
AI Must Embrace Specialization via Superhuman Adaptable Intelligence
Feb 27, 2026Judah Goldfeder, Philippe Wyder, Yann LeCun +1Artificial General Intelligence
Columbia University, New York, NY, USA · Distyl, New York, NY, USA · New York University, New York, NY, USA
Embodied AI in Action: Insights from SAE World Congress 2026 on Safety, Trust, Robotics, and Real-World Deployment
May 11, 2026Jan-Mou Li, Paul Schmitt, Wei Tong +4AI Governance Trust in AI

Sep 22, 2026J/K move · Enter open · S save

Know Your Body: A Harness for Direct and Self-Improving Robot Control with VLMs

Zeyu Lou, Yanhong Zeng, Yong Wang, Chenyang Si

Nanjing University · Ant Group · Zhejiang University

VLMs for Robotics Large Language Model-Based Robot Planning Continual Robot Learning

Open paper AskPDF arXiv

A general-purpose vision-language model can understand a task goal without knowing how a particular robot's motion and functional parts produce the intended effect. We introduce KnowBody, a harness that makes these action-relevant body relations explicit, queryable, and revisable while keeping the model weights frozen. Initialized from one off-task trajectory, a partial body model guides action selection and the interpretation of past interactions. New evidence refines the model, and knowledge dependent on revised body estimates is rechecked before reuse. Across 32 fixed-budget trials on four real-robot tasks, initialized KnowBody achieves 75% completion versus 25% for the native harness and requires fewer planner rounds on successful trials in tasks completed by both. With persistent updates enabled, planner rounds decrease by 29-53% from the first to the fifth recorded success.

Abstract

Embodied AI

Explore similar work

Know Your Body: A Harness for Direct and Self-Improving Robot Control with VLMs

AI Must Embrace Specialization via Superhuman Adaptable Intelligence

Embodied AI in Action: Insights from SAE World Congress 2026 on Safety, Trust, Robotics, and Real-World Deployment