Florence Tsang
Papers
2
Total Citations
6
H-Index
2
About
Florence Tsang is a robotics researcher whose work focuses on enabling mobile robots to navigate more intelligently in uncertain, changing environments. Her key research area lies at the intersection of motion planning and machine learning, specifically developing algorithms that allow robots to learn from repeated task executions. Tsang’s major contribution is the creation of learning-based motion policies that leverage historical navigation data to improve future performance, rather than relying solely on reactive, online replanning. Her papers, including "Learning Motion Planning Policies in Uncertain Environments through Repeated Task Executions" (2019) and "LAMP: Learning a Motion Policy to Repeatedly Navigate in an Uncertain Environment" (2021), each with 3 citations, introduce frameworks that exploit hidden structure in environmental changes. This approach is particularly valuable for applications like warehouse logistics or service robotics, where robots traverse the same routes under varying conditions. By bridging the gap between reactive planning and experience-driven adaptation, Tsang’s work offers a practical path toward more efficient, autonomous navigation in real-world settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2