Papers
2
Total Citations
5
H-Index
2
About
Ki Deng’s research focuses on the intersection of reinforcement learning and autonomous robotics, with key contributions in mapless navigation and battery management for warehouse automation. In their influential 2022 work on mapless navigation, Deng introduced a novel encoding method that integrates local obstacle maps with reinforcement learning, effectively overcoming the “local minima” challenges that plague end-to-end training in indoor environments. This approach has garnered 3 citations and offers a practical path toward more robust, sensor-efficient robot movement. Complementing this, Deng’s research on battery management for warehouse robots—also published in 2022—formulated the battery scheduling problem as a Markov Decision Process and applied average-reward deep reinforcement learning to optimize AGV operations. With 2 citations, this work directly addresses real-world throughput bottlenecks in automated warehouses. Together, Deng’s contributions demonstrate a clear commitment to bridging theoretical RL advances with tangible robotic applications, making their work particularly relevant for students and researchers exploring intelligent navigation and resource optimization in logistics.
Research Focus
Key Achievements
Top Papers
- 1
- 2