Beiming Li
Papers
2
Total Citations
55
H-Index
2
About
Beiming Li is a robotics researcher at the forefront of autonomous aerial exploration, specializing in micro aerial vehicles (MAVs) operating under stringent size, weight, and power (SWaP) constraints. His work addresses the critical challenge of enabling small drones to efficiently and safely navigate unknown indoor environments where traditional sensors and computing are impractical. Li’s major contribution is the development of learning-based exploration frameworks that predict information gain and occupancy in unseen areas, allowing MAVs to make intelligent decisions about where to fly next. His seminal paper, “SEER: Safe Efficient Exploration for Aerial Robots using Learning to Predict Information Gain” (2023), has garnered 41 citations for its novel approach to balancing exploration efficiency with safety in cluttered spaces. Building on this, his 2024 work “Learning to Explore Indoor Environments using Autonomous Micro Aerial Vehicles” (14 citations) further refines these techniques, demonstrating how deep learning can overcome SWaP-induced mission time limits. Li’s research is pivotal for applications in search-and-rescue, infrastructure inspection, and environmental monitoring, where small, agile robots must operate autonomously for extended periods. His work stands out for its practical focus on real-world constraints, making autonomous exploration more robust and accessible.
Research Focus
Key Achievements
Top Papers
- 1
- 2