<?xml version="1.0" encoding="utf-8"?><feed xmlns="http://www.w3.org/2005/Atom" ><generator uri="https://jekyllrb.com/" version="4.2.2">Jekyll</generator><link href="http://imtianyuli.com/feed.xml" rel="self" type="application/atom+xml" /><link href="http://imtianyuli.com/" rel="alternate" type="text/html" /><updated>2026-02-03T10:35:50-05:00</updated><id>http://imtianyuli.com/feed.xml</id><title type="html">🤖</title><subtitle>I envision a future where robots are not only capable, but also intuitive, adaptive, and safe.</subtitle><author><name>Tianyu Li (李天宇)</name></author><entry><title type="html">Flow with the Force Field: Learning 3D Compliant Flow Matching Policies from Force and Demonstration-Guided Simulation Data</title><link href="http://imtianyuli.com/publications/2025/09/15/pub-flow-force.html" rel="alternate" type="text/html" title="Flow with the Force Field: Learning 3D Compliant Flow Matching Policies from Force and Demonstration-Guided Simulation Data" /><published>2025-09-15T00:00:00-04:00</published><updated>2025-09-15T00:00:00-04:00</updated><id>http://imtianyuli.com/publications/2025/09/15/pub-flow-force</id><content type="html" xml:base="http://imtianyuli.com/publications/2025/09/15/pub-flow-force.html"><![CDATA[<h2 id="coming-soon">Coming Soon</h2>]]></content><author><name>Tianyu Li (李天宇)</name></author><category term="publications" /><summary type="html"><![CDATA[We introduce a framework for generating force-informed data in simulation, instantiated by a single human demonstration, and show how coupling with a compliant policy improves the performance of a visuomotor policy learned from synthetic data.]]></summary></entry><entry><title type="html">VLMgineer: Vision Language Models as Robotic Toolsmiths</title><link href="http://imtianyuli.com/publications/2025/09/10/pub-vlmgineer.html" rel="alternate" type="text/html" title="VLMgineer: Vision Language Models as Robotic Toolsmiths" /><published>2025-09-10T00:00:00-04:00</published><updated>2025-09-10T00:00:00-04:00</updated><id>http://imtianyuli.com/publications/2025/09/10/pub-vlmgineer</id><content type="html" xml:base="http://imtianyuli.com/publications/2025/09/10/pub-vlmgineer.html"><![CDATA[<h2 id="coming-soon">Coming Soon</h2>]]></content><author><name>Tianyu Li (李天宇)</name></author><category term="publications" /><summary type="html"><![CDATA[We introduce VLMgineer, a novel VLM-driven evolutionary framework that automatically co-design tools and actions to solve robotics task.]]></summary></entry><entry><title type="html">VPP-TC: Viability-Preserving Passive Torque Control</title><link href="http://imtianyuli.com/publications/2025/08/14/pub-vpp.html" rel="alternate" type="text/html" title="VPP-TC: Viability-Preserving Passive Torque Control" /><published>2025-08-14T00:00:00-04:00</published><updated>2025-08-14T00:00:00-04:00</updated><id>http://imtianyuli.com/publications/2025/08/14/pub-vpp</id><content type="html" xml:base="http://imtianyuli.com/publications/2025/08/14/pub-vpp.html"><![CDATA[<h2 id="coming-soon">Coming Soon</h2>]]></content><author><name>Tianyu Li (李天宇)</name></author><category term="publications" /><summary type="html"><![CDATA[A quadratic programming-based control framework enforces viability theory constructed constraints on a passive controller tracking a dynamical system, ensuring the robot states remain within the safe set in an infinite time horizon.]]></summary></entry><entry><title type="html">Elastic Motion Policy: An Adaptive Dynamical System for Robust and Efficient One-Shot Imitation Learning</title><link href="http://imtianyuli.com/publications/2025/03/13/pub-emp.html" rel="alternate" type="text/html" title="Elastic Motion Policy: An Adaptive Dynamical System for Robust and Efficient One-Shot Imitation Learning" /><published>2025-03-13T00:00:00-04:00</published><updated>2025-03-13T00:00:00-04:00</updated><id>http://imtianyuli.com/publications/2025/03/13/pub-emp</id><content type="html" xml:base="http://imtianyuli.com/publications/2025/03/13/pub-emp.html"><![CDATA[<h2 id="coming-soon">Coming Soon</h2>]]></content><author><name>Tianyu Li (李天宇)</name></author><category term="publications" /><summary type="html"><![CDATA[A one-shot stable imitation learning framework that allows robots to adjust their behavior based on the scene change while respecting the task specification.]]></summary></entry><entry><title type="html">MORF: Magnetic Origami Reprogramming and Folding System for Repeatably Reconfigurable Structures with Fold Angle Control</title><link href="http://imtianyuli.com/publications/2025/03/10/pub-morf.html" rel="alternate" type="text/html" title="MORF: Magnetic Origami Reprogramming and Folding System for Repeatably Reconfigurable Structures with Fold Angle Control" /><published>2025-03-10T00:00:00-04:00</published><updated>2025-03-10T00:00:00-04:00</updated><id>http://imtianyuli.com/publications/2025/03/10/pub-morf</id><content type="html" xml:base="http://imtianyuli.com/publications/2025/03/10/pub-morf.html"><![CDATA[<h2 id="coming-soon">Coming Soon</h2>]]></content><author><name>Tianyu Li (李天宇)</name></author><category term="publications" /><summary type="html"><![CDATA[We introduce MORF, a magnetic origami system enabling repeatedly reprogrammable, rigid structures ideal for adaptive robotic tools.]]></summary></entry><entry><title type="html">Out-of-Distribution Recovery with Object-Centric Keypoint Inverse Policy For Visuomotor Imitation Learning</title><link href="http://imtianyuli.com/publications/2023/09/01/pub-ocr.html" rel="alternate" type="text/html" title="Out-of-Distribution Recovery with Object-Centric Keypoint Inverse Policy For Visuomotor Imitation Learning" /><published>2023-09-01T00:00:00-04:00</published><updated>2023-09-01T00:00:00-04:00</updated><id>http://imtianyuli.com/publications/2023/09/01/pub-ocr</id><content type="html" xml:base="http://imtianyuli.com/publications/2023/09/01/pub-ocr.html"><![CDATA[<h2 id="coming-soon">Coming Soon</h2>]]></content><author><name>Tianyu Li (李天宇)</name></author><category term="publications" /><summary type="html"><![CDATA[A vision-based object-centric recovery policy framework that guides the system back to the training distribution in OOD situations without relying on extra data]]></summary></entry><entry><title type="html">Constrained Passive Interaction Control: Leveraging Passivity and Safety for Robot Manipulators</title><link href="http://imtianyuli.com/publications/2023/08/30/pub-passive-control.html" rel="alternate" type="text/html" title="Constrained Passive Interaction Control: Leveraging Passivity and Safety for Robot Manipulators" /><published>2023-08-30T00:00:00-04:00</published><updated>2023-08-30T00:00:00-04:00</updated><id>http://imtianyuli.com/publications/2023/08/30/pub-passive-control</id><content type="html" xml:base="http://imtianyuli.com/publications/2023/08/30/pub-passive-control.html"><![CDATA[<h2 id="coming-soon">Coming Soon</h2>]]></content><author><name>Tianyu Li (李天宇)</name></author><category term="publications" /><summary type="html"><![CDATA[A novel control architecture that allows a torque-controlled robot to guarantee safety constraints such as kinematic limits, self-collisions, external collisions and singularities and is passive only when feasible]]></summary></entry><entry><title type="html">Learning Safe and Stable Motion Plans with Neural Ordinary Differential Equations</title><link href="http://imtianyuli.com/publications/2023/08/29/pub-node.html" rel="alternate" type="text/html" title="Learning Safe and Stable Motion Plans with Neural Ordinary Differential Equations" /><published>2023-08-29T00:00:00-04:00</published><updated>2023-08-29T00:00:00-04:00</updated><id>http://imtianyuli.com/publications/2023/08/29/pub-node</id><content type="html" xml:base="http://imtianyuli.com/publications/2023/08/29/pub-node.html"><![CDATA[<h2 id="coming-soon">Coming Soon</h2>]]></content><author><name>Tianyu Li (李天宇)</name></author><category term="publications" /><summary type="html"><![CDATA[This approach learns a motion plan with Neural Ordinary Differential Equations while guaranteeing stability and safety with Control Lyapunov Functions and Control Barrier Functions]]></summary></entry><entry><title type="html">Constraint-Aware Intent Estimation for Dynamic Human-Robot Object Co-Manipulation</title><link href="http://imtianyuli.com/publications/2023/08/28/pub-intent-capability.html" rel="alternate" type="text/html" title="Constraint-Aware Intent Estimation for Dynamic Human-Robot Object Co-Manipulation" /><published>2023-08-28T00:00:00-04:00</published><updated>2023-08-28T00:00:00-04:00</updated><id>http://imtianyuli.com/publications/2023/08/28/pub-intent-capability</id><content type="html" xml:base="http://imtianyuli.com/publications/2023/08/28/pub-intent-capability.html"><![CDATA[<h2 id="coming-soon">Coming Soon</h2>]]></content><author><name>Tianyu Li (李天宇)</name></author><category term="publications" /><summary type="html"><![CDATA[A dynamical system based representation for intent estimation with constraints in human robot co-manipulation tasks]]></summary></entry><entry><title type="html">Task Generalization with Stability Guarantees via Elastic Dynamical System Motion Policies</title><link href="http://imtianyuli.com/publications/2023/08/27/pub-elastic-ds.html" rel="alternate" type="text/html" title="Task Generalization with Stability Guarantees via Elastic Dynamical System Motion Policies" /><published>2023-08-27T00:00:00-04:00</published><updated>2023-08-27T00:00:00-04:00</updated><id>http://imtianyuli.com/publications/2023/08/27/pub-elastic-ds</id><content type="html" xml:base="http://imtianyuli.com/publications/2023/08/27/pub-elastic-ds.html"><![CDATA[<h2 id="coming-soon">Coming Soon</h2>]]></content><author><name>Tianyu Li (李天宇)</name></author><category term="publications" /><summary type="html"><![CDATA[A dynamical system based motion policy LfD method with stability guarantees that can generalize to new task configurations without new demonstrations]]></summary></entry></feed>