Max Robotics — Global Service Robot Directory + US Certification

About

Jingnan Wang is pioneering the integration of tactile intelligence into robotic systems, with a focus on robotic manipulation, surgical palpation, and multimodal sensor fusion. Their work addresses critical challenges in how robots perceive and interact with physical environments through touch. Wang’s major contributions include developing the **Predict Tactile Grasp Outcomes Based on Attention and Low-Rank Fusion Network** (2024, 4 citations), which enhances grasp prediction accuracy by efficiently fusing multiple tactile modalities. They further advanced the field with **Multi-Branch Multi-Scale Channel Fusion Graph Convolutional Networks** (2025, 4 citations), introducing a novel transfer cost method for spatial-temporal adjacency matrix construction that significantly improves tactile recognition. In surgical applications, Wang’s **Dual Autoencoder-Based Joint Learning** (2025, 3 citations) enables precise depth classification of hard inclusions in soft tissue during robotic palpation, a critical capability for robot-assisted minimally invasive surgery. Their **TempTrans-MIL** framework (2025, 3 citations) provides a general approach to handling high-dimensional multimodal tactile time series data, advancing robotic manipulation classification. Wang’s research is distinguished by its systematic approach to extracting key features from complex tactile data and fusing information across modalities, directly addressing fundamental limitations in robotic tactile perception. Their work holds promise for enhancing both industrial automation and medical robotics.