Papers

5

Total Citations

95

H-Index

5

About

Tharindu Fernando is a researcher at the forefront of artificial intelligence, with a focus on computer vision, autonomous systems, and human-robot interaction. His work bridges the gap between machine perception and complex decision-making, particularly in dynamic environments. A key contribution is the development of *FactoFormer*, a factorized hyperspectral transformer that leverages self-supervised pretraining to extract rich spectral-spatial information from hyperspectral images, earning 30 citations and advancing remote sensing and environmental monitoring. In the realm of autonomous navigation, Fernando has pioneered deep inverse reinforcement learning methods that embed neighbourhood context to predict pedestrian motion over long time horizons (22 citations), enabling safer and more natural interactions between humans and machines. His research also explores learning temporal strategic relationships through generative adversarial imitation learning (20 citations), which models complex, multi-step human decision-making for long-term planning in autonomous systems. Earlier work includes fuzzy logic-based control for mobile robot target tracking in hostile environments (9 citations), demonstrating his sustained impact on robotics. With a portfolio of highly cited papers, Fernando’s contributions are shaping the future of intelligent, context-aware autonomous agents.

Research Focus

Key Achievements

5
H-Index
5
Papers
95
Total Citations
19
Avg Citations/Paper
🏆 Most Cited Paper
<i>FactoFormer:</i> Factorized Hyperspectral Transformers With Self-Supervised Pretraining
30 citations · 2023
📈 Most Prolific Year: 2018 (2 Papers)
🤝 Key Collaborators: 8
🏛 Institutions: Queensland University of Technology, University of Peradeniya

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago