Kunpeng Yao

Lecturer (Assistant Professor) in Robotics

School of Computer Science · University of Leeds, United Kingdom

About

I develop methods for dexterous robotic manipulation. I also study human sensorimotor control to understand how humans acquire fine manipulation skills.

Read my University of Leeds profile

Research

Google Scholar

Recent Updates

All News

June 2026 Publication

Learning-from-demonstration literature study published

A one-year study of the learning-from-demonstration literature was published in IEEE Robotics & Automation Magazine.

↗

June 2026 Publication

Hand and wrist pose-retargeting paper presented at ICRA

Our optimization-based approach for hand-pose retargeting and wrist-pose estimation from a single RGB camera was presented at ICRA 2026.

↗

March 2026 Publication

Editorial on human-centred robotic hand research

An editorial on robotic hand design, analysis, control, and learning from human demonstration was published in Frontiers in Robotics and AI.

↗

February 2026 Grant

WUN project on bimanual assistive robots

The Worldwide Universities Network supported our international project on bimanual assistive robots for daily care, for which I serve as academic lead.

↗

January 2026 Media

Crawling robotic hand receives international media coverage

The detachable crawling robotic hand was featured by Euronews, the Financial Times, The New York Times, and Science News.

↗

Contact

For research, teaching, or collaboration enquiries, please contact me using my University of Leeds email address.

I welcome enquiries from motivated prospective PhD students whose interests align with my research.

Find my university email

Kunpeng Yao

About

Research

A detachable crawling robotic hand

DexFlow: A Unified Approach for Dexterous Hand Pose Retargeting and Interaction

Enhancing Dexterity in Confined Spaces: Real-Time Motion Planning for Multifingered In-Hand Manipulation

Differentiable Robot Neural Distance Function for Adaptive Grasp Synthesis on a Unified Robotic Arm-Hand System

Online active and dynamic object shape exploration with a multi-fingered robotic hand

Exploiting Kinematic Redundancy for Robotic Grasping of Multiple Objects

Benchmark for Bimanual Robotic Manipulation of Semi-Deformable Objects

Tactile-based active object discrimination and target object search in an unknown workspace

Tactile-based object center of mass exploration and discrimination

A Tactile-Based Framework for Active Object Learning and Discrimination using Multimodal Robotic Skin

Tactile-based manipulation of deformable objects with dynamic center of mass

Implicit Articulated Robot Morphology Modeling with Configuration Space Neural Signed Distance Functions

Enhancing Dexterity in Confined Spaces: Real-Time Motion Planning for Multifingered In-Hand Manipulation

Action Contextualization: Adaptive Task Planning and Action Tuning Using Large Language Models

ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning

Differentiable Robot Neural Distance Function for Adaptive Grasp Synthesis on a Unified Robotic Arm-Hand System

DexFlow: A Unified Approach for Dexterous Hand Pose Retargeting and Interaction

Transfer learning in robotics: An upcoming breakthrough? A review of promises and challenges

Action Contextualization: Adaptive Task Planning and Action Tuning Using Large Language Models

A Tactile-Based Framework for Active Object Learning and Discrimination using Multimodal Robotic Skin

An objective skill assessment framework for microsurgical anastomosis based on ALI scores

Force Synergies Within and Across the Two Hands in Bimanual Skill Acquisition

Hand pose selection in a bimanual fine-manipulation task

An inverse optimization approach to understand human acquisition of kinematic coordination in bimanual fine manipulation tasks

Surviving the Paper Deluge: A One-Year Study in Learning From Demonstration

Editorial: A human perspective on robotic hand design, analysis, control and beyond