Rekha Singhal
Papers
1
Total Citations
3
H-Index
1
About
Dr. Rekha Singhal’s research lies at the intersection of combinatorial optimisation, reinforcement learning, and hardware acceleration, with a particular focus on real-time industrial automation. Her most-cited work, “Performance improvement of reinforcement learning algorithms for online 3D bin packing using FPGA” (2022, 3 citations), tackles the notoriously difficult problem of packing rigid cuboid parcels arriving on a conveyor into a shipping bin—a task that demands both spatial reasoning and split-second decision-making. By integrating reinforcement learning with FPGA-based hardware acceleration, she has demonstrated how to achieve the low-latency, high-throughput performance required for robotic manipulators in logistics and warehousing. This contribution is especially notable for bridging the gap between theoretical RL algorithms and practical, real-world deployment constraints. Dr. Singhal’s work is a compelling example of how domain-specific hardware can unlock new efficiencies in classic optimisation challenges, making her a key figure for students and researchers interested in the future of automated packing, cyber-physical systems, and edge-AI for manufacturing.
Research Focus
Key Achievements
Top Papers
- 1