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

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。

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。

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。

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, independently wrote 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；随后独立完成 15 万英镑项目申请并获批，目前负责触觉硬件研发。

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？

I built a dual-Franka leader–follower system with UMI grippers, fine-tuned π0.5-DROID on eight H100 GPUs, and deployed local inference on an RTX 5090.我搭建了由两台 Franka Panda 与 UMI 夹爪组成的主从遥操系统，使用 8 张 H100 微调 π0.5-DROID，并在本地 RTX 5090 上完成推理部署。