Cael Fitch

Purdue University West Lafayette

Papers

1

Total Citations

3

H-Index

1

About

Cael Fitch is a researcher pushing the boundaries of tactile sensing for robotics, with a focus on data-efficient learning and generalization. Their key research area centers on developing compact, transferable representations of tactile data—a critical challenge for enabling robots to interact with unfamiliar objects. Fitch’s major contribution is the UniT framework, introduced in their 2025 paper, which leverages VQGAN to learn a discrete latent space from tactile images of a single, simple object. This approach achieves remarkable zero-shot generalization to unseen objects, dramatically reducing the need for extensive training data. Though early in its citation trajectory, UniT has already garnered 3 citations, signaling its potential impact on the field. Fitch’s work addresses a fundamental bottleneck in tactile sensing: the high cost of data collection. By showing that a single object can suffice for robust representation learning, they open doors for scalable, real-world robotic manipulation. This innovative approach positions Fitch as a rising voice in embodied AI, with implications for everything from industrial automation to assistive robotics. Their research promises to make tactile intelligence more practical and accessible.

Research Focus

Key Achievements

1
H-Index
1
Papers
3
Total Citations
3
Avg Citations/Paper
🏆 Most Cited Paper
UniT: Data Efficient Tactile Representation With Generalization to Unseen Objects
3 citations · 2025
📈 Most Prolific Year: 2025 (1 Papers)
🤝 Key Collaborators: 7
🏛 Institutions: Purdue University West Lafayette

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago