Charles Averill

The University of Texas at Dallas

Papers

1

Total Citations

10

H-Index

1

About

Charles Averill is a robotics researcher whose work lies at the intersection of computer vision and autonomous manipulation, with a particular focus on enabling robots to understand and interact with unfamiliar objects in unstructured environments. His most cited contribution, "Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot Interaction" (2023, 10 citations), introduces a novel paradigm that moves beyond single-action segmentation methods. Instead of relying on a single grasp or push to isolate an object, Averill’s system leverages extended, iterative physical interactions—such as repeated grasping, pushing, and observing—to build a more robust and accurate segmentation model over time. This self-supervised approach allows robots to learn from their own actions without requiring extensive labeled datasets, a significant step toward generalizable robotic perception. By demonstrating that long-term interaction can improve segmentation of previously unseen objects, Averill’s work has implications for warehouse automation, home robotics, and any domain where robots must handle novel items. His research bridges the gap between active perception and lifelong learning, offering a practical pathway for robots to continuously refine their understanding of the world through direct experience.

Research Focus

Key Achievements

1
H-Index
1
Papers
10
Total Citations
10
Avg Citations/Paper
🏆 Most Cited Paper
Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot Interaction
10 citations · 2023
📈 Most Prolific Year: 2023 (1 Papers)
🤝 Key Collaborators: 8
🏛 Institutions: The University of Texas at Dallas

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago