Tactile sensing is critical in advanced interactive systems by emulating the human sense of touch to detect stimuli. Vision-based tactile sensors are promising for providing multimodal capabilities and high robustness, yet existing technologies still have limitations in sensitivity, spatial resolution, and high computational demands of deep learning-based image processing. This paper presents a comprehensive approach combining a novel microstructure-based sensor design and efficient image processing, demonstrating that carefully engineered microstructures can significantly enhance performance while reducing computational load. Without traditional tracking markers, our sensor incorporates an surface with micromachined trenches, as an example of microstructures, which modulate light transmission and amplify the response to applied force. The amplified image features can be extracted by a ultra lightweight convolutional neural network to accurately inferring contact location, displacement, and applied force with high precision. Through theoretical analysis, we demonstrated that the micro trenches significantly amplified the visual effects of shape distortion. Using only a commercial webcam, the sensor system effectively detected forces below 5 mN, and achieved a millimetre-level single-point spatial resolution. Using a model with only one convolutional layer, a mean absolute error below 0.05 mm was achieved. Its soft sensor body allows seamless integration with soft robots, while its immunity to electrical crosstalk and interference guarantees reliability in complex human-machine environments.

翻译：触觉传感通过模拟人类触觉来检测刺激，在高级交互系统中至关重要。基于视觉的触觉传感器因具备多模态能力和高鲁棒性而前景广阔，但现有技术在灵敏度、空间分辨率以及基于深度学习的图像处理的高计算需求方面仍存在局限。本文提出了一种结合新型微结构传感器设计与高效图像处理的综合方法，证明精心设计的微结构能显著提升性能同时降低计算负荷。无需传统追踪标记，我们的传感器采用具有微加工沟槽的表面作为微结构示例，该结构可调制光传输并放大对外加力的响应。放大的图像特征可通过超轻量级卷积神经网络提取，从而高精度推断接触位置、位移及作用力。通过理论分析，我们证明了微沟槽能显著放大形变畸变的视觉效果。仅使用商用网络摄像头，该传感器系统即可有效检测低于5 mN的力，并实现毫米级单点空间分辨率。使用仅含单层卷积层的模型，平均绝对误差低于0.05毫米。其柔性传感本体可与软体机器人无缝集成，而对电串扰和干扰的免疫性保证了其在复杂人机环境中的可靠性。