Priyabrata Saha
Papers
2
Total Citations
54
H-Index
2
About
Priyabrata Saha is a researcher at the forefront of autonomous systems, specializing in sensor fusion, resource-efficient robotics, and deep neural network control. His work addresses the critical challenge of balancing accuracy with computational and energy constraints in autonomous mobile systems. Saha’s most impactful contribution is his 2021 paper on “Task-Driven RGB-Lidar Fusion for Object Tracking in Resource-Efficient Autonomous Systems,” which has garnered 51 citations. This work introduces a novel framework that selectively fuses data from multiple sensors—such as Lidar, RGB, and Radar—based on task requirements, significantly reducing resource consumption without compromising tracking performance. In addition, Saha has explored the application of deep neural networks for control, as seen in his 2022 paper on “Learning Deep Neural Network Controller for Path Following of Unicycle Robots,” which demonstrates a DNN-based controller capable of learning complex path-following behaviors without initialization or supervision. This work, though newer, highlights his innovative approach to autonomous navigation. Saha’s research is pivotal for developing next-generation autonomous vehicles and robots that are both intelligent and efficient, making him a rising voice in the field of resource-aware autonomy.
Research Focus
Key Achievements
Top Papers
- 1
- 2