Shaohua Lv
Papers
2
Total Citations
23
H-Index
2
About
Shaohua Lv is a researcher advancing the frontiers of intelligent robotics and autonomous systems, with key contributions in multi-robot coordination and safe navigation. His work addresses two critical challenges in modern robotics: optimizing task allocation in complex environments and ensuring safety in learning-based navigation. In his highly cited 2022 paper (18 citations), Lv models multi-robot task assignment in intelligent warehouses as an open-path multi-depot asymmetric traveling salesman problem (OP-MATSP), developing a two-objective integer linear programming model that significantly improves efficiency in real-world logistics. Complementing this, his 2021 work on deep safe reinforcement learning tackles the pressing issue of safety in end-to-end mapless navigation, introducing a constrained RL algorithm that enables robots to navigate without pre-existing maps while minimizing risky behaviors. Lv’s research bridges theoretical optimization and practical deployment, offering scalable solutions for warehouse automation and autonomous mobile robots. His work is particularly notable for integrating safety constraints directly into learning frameworks—a crucial step toward reliable real-world AI. With growing citation impact, Lv is establishing himself as a key voice in the intersection of operations research and safe reinforcement learning for robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2A Deep Safe Reinforcement Learning Approach for Mapless Navigation5 citations · 2021