Research研究

Two questions guide my research我的研究围绕两个问题展开

How can a robot recreate the way people choose to touch? And where can tactile sensing make a practical difference?机器人能不能像人一样决定该怎么摸?触觉感知又能在哪些实际问题里派上用场?

Scientific question科学问题

How can a robot recreate the way people touch?机器人怎样复刻人的触摸?

Touch is an action, not just a sensor reading. I study how people choose speed and movement, then turn those choices into robotic exploration strategies.触摸不只是读取传感器,人会先决定用多快的速度、以什么动作去摸。我研究这些选择,再把它们变成机器人的探索策略。

01Published · Humanoids 2025已发表 · Humanoids 2025

Choosing touch speed from human perception从人的感知出发选择触摸速度

Do people change their preferred touch speed according to how a texture feels?面对不同的纹理感受,人会不会主动改变自己偏好的触摸速度?

I led a human study across natural textures, velocities and contact forces, then modelled how perceptual dimensions predict preferred exploration speed.我设计并完成了自然纹理、不同速度与接触力下的人体实验,再用感知维度预测人偏好的探索速度。

02Published · IROS 2025已发表 · IROS 2025

Choosing an exploratory movement选择合适的探索动作

Which interaction pattern gives a robot the clearest evidence about texture?滑动、旋转或组合动作,哪一种能让机器人获得更清楚的纹理信息?

I contributed equally to the study of six individual and compound movements with a neuromorphic tactile sensor. Sliding and rotating together produced the strongest result.我以共同一作身份比较了六种单独或组合动作。使用神经形态触觉传感器时,滑动加旋转取得了最好的识别结果。

03In preparation正在进行

Predicting how an unseen texture will feel预测未见纹理的感知维度

Can a robot infer the perceptual dimensions of a texture it has never encountered?面对训练中从未见过的纹理,机器人能不能预测人会从哪些维度感知它?

My current work connects human perceptual structure with robotic touch, with the aim of choosing human-like exploration behaviour for unfamiliar surfaces.我正在把人的纹理感知结构与机器人触觉联系起来,让机器人面对陌生表面时,也能选择更接近人的探索方式。

Applied question应用问题

Where can tactile sensing make a practical difference?触觉感知能在哪些实际问题里派上用场?

The second strand moves touch beyond controlled texture experiments. I am building systems for industrial inspection and exploring how tactile signals may support multimodal robot action.另一条主线把触觉带出受控的纹理实验。我正在做工业检测系统,也在探索触觉信号怎样进入多模态机器人的动作决策。

01Funded · in progress已获资助 · 正在进行

Tactile inspection for composite manufacturing用触觉检测复合材料缺陷

Can event-based touch detect surface defects in real time on a manufacturing line?事件驱动触觉能不能在制造流程中实时发现复合材料表面缺陷?

I led the seed project that established the experimental framework, co-authored the successful £150k follow-on proposal, and now lead tactile hardware development.我先以 PI 身份完成种子项目,建立实验框架;随后参与撰写并获批 15 万英镑后续项目,目前负责触觉硬件开发。

02Upcoming direction即将开展

Bringing touch into VTLA systems把触觉带进 VTLA 系统

How should tactile information change what a multimodal robot decides to do next?当机器人真正获得触觉后,这些信息应该怎样改变它下一步的动作?

This is an upcoming research direction. I am currently defining the problem and experimental path for bringing touch into multimodal perception and action selection.这是下一阶段的研究方向。我正在梳理问题与实验路径,探索触觉如何参与多模态感知和动作选择。

Research base研究环境

Where the work happens这些工作在哪里展开

Affiliation所属机构

School of Engineering Mathematics and Technology, University of Bristol

Bristol Robotics Laboratory · Dexterous Group

Supervision导师

  • Dr Benjamin Ward-Cherrier
  • Dr Martin Pearson

Funding资助

Fully funded by the China Scholarship Council and the University of Bristol博士阶段由国家留学基金委与布里斯托大学联合全额资助