Stephen Mylabathula
Papers
1
Total Citations
5
H-Index
1
About
Stephen Mylabathula is a robotics researcher specializing in long-term autonomy, dense mapping, and change detection for autonomous systems. His work addresses a fundamental challenge in robotics: enabling machines to maintain accurate, conflict-free environmental understanding over extended periods. Mylabathula’s most cited paper, “PlaneSDF-Based Change Detection for Long-Term Dense Mapping” (2022), introduces a novel method for detecting changes across multiple mapping sessions by leveraging plane-augmented signed distance functions. This contribution is critical for robots operating in dynamic environments, allowing them to distinguish between temporary and permanent scene alterations without requiring prior knowledge of the environment. While his citation count is still growing—reflecting the early stage of his career—his work has already been recognized for its potential to improve persistent robot operation in real-world settings. Mylabathula’s research sits at the intersection of computer vision, SLAM, and spatial reasoning, offering practical solutions for long-duration missions in logistics, inspection, and autonomous navigation. His focus on robust, session-agnostic mapping positions him as an emerging voice in the field of lifelong robotic perception.
Research Focus
Key Achievements
Top Papers
- 1PlaneSDF-Based Change Detection for Long-Term Dense Mapping5 citations · 2022