Papers
7
Total Citations
110
H-Index
4
About
Long Qin’s research sits at the intersection of autonomous navigation, multi-robot systems, and artificial intelligence, with a focus on enabling robots to operate safely and intelligently in complex, dynamic environments. Her most impactful contribution is the development of novel Deep Reinforcement Learning algorithms for robot navigation. Her 2019 paper on the MK-A3C algorithm, which integrates memory and knowledge into the Asynchronous Advantage Actor-Critic framework, has garnered 70 citations and demonstrates a powerful method for continuous control in unknown spaces with moving obstacles. She further advanced this field with the JPS-IA3C hierarchical framework, combining path planning with adaptive motion control. Beyond reinforcement learning, Qin has made foundational contributions to swarm robotics, notably a potential field control algorithm for forming and maintaining 2D shapes while avoiding collisions. Her work on grid-based distance maps and Generalized Voronoi Diagrams provides critical tools for efficient spatial representation and path planning, addressing both metric and topological information for mobile robots. Most recently, she has extended her expertise to Vision and Language Navigation, exploring self-organizing memory architectures to improve long-horizon planning in embodied agents.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Formation Control of Robotic Swarm Using Bounded Artificial Forces9 citations · 2013
- 4Speed Optimization for Incremental Updating of Grid-Based Distance Maps5 citations · 2019
- 5
- 6
- 7