Lalitha Dabbiru

Papers

Total Citations

H-Index

About

Lalitha Dabbiru is a researcher at the forefront of autonomous systems and sensor data processing, with a particular focus on advancing neural network training methodologies. Her work addresses a critical bottleneck in autonomous vehicle development: the labor-intensive process of collecting and labeling large-scale training datasets. Dabbiru’s most cited paper, "Training of Neural Networks with Automated Labeling of Simulated Sensor Data" (2019), introduces an innovative approach that leverages simulated environments to automatically generate truth-labeled data for convolutional neural networks (CNNs). This contribution significantly reduces the time and cost associated with manual annotation while maintaining high training accuracy, enabling more efficient development of ground-vehicle autonomy systems. With 12 citations, this work has garnered attention from researchers seeking scalable solutions for sensor data training. Dabbiru’s research sits at the intersection of computer vision, simulation, and robotics, offering practical pathways to bridge the gap between simulated and real-world performance. Her achievements highlight a commitment to solving foundational challenges in autonomous perception, making her a notable voice in the ongoing evolution of intelligent transportation systems.