Papers
2
Total Citations
7
H-Index
2
About
Runsheng Wang is a researcher at the intersection of tactile sensing and reliable hardware acceleration for deep learning. His work addresses two critical frontiers in robotics and autonomous systems: high-speed tactile perception and the dependability of neural network accelerators. In tactile sensing, Wang pioneered the use of MEMS microphones as fast vibration sensors, demonstrating a novel multi-feature extraction and super-resolution technique that simultaneously classifies texture, estimates contact position, and measures velocity. This approach leverages the inherent speed of microphones to enable rapid detection of contact and slip onset—a vital capability for dexterous robotic manipulation. His work in this area has already garnered early citations, signaling its potential impact on the field. Complementing this, Wang’s research on reliability-enhanced accelerator dataflow optimization (READ) tackles a pressing challenge for safety-critical applications like autonomous driving. By identifying and mitigating critical input patterns that cause computational errors, his work improves the robustness of deep learning accelerators fabricated in advanced technology nodes. This dual focus on sensing and computation positions Wang as a rising contributor to the development of more capable and trustworthy autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2