Faraz Shamshirdar
Papers
6
Total Citations
38
H-Index
4
About
Faraz Shamshirdar is a robotics researcher whose work bridges computer vision, autonomous navigation, and humanoid robotics. His primary research areas include visual teach-and-repeat (VTR) systems for unmanned aerial vehicles (UAVs), semantic object detection for robust navigation, and inter-robot interaction. Shamshirdar’s most significant contribution is pioneering the use of sparse semantic object features—rather than traditional visual landmarks—for UAV visual teach-and-repeat. His 2018 papers (12 and 8 citations) demonstrate that CNN-based object detectors can provide repeatable, robust features for autonomous UAV navigation, enabling reliable path following in challenging environments where conventional methods fail. This work has implications for long-term autonomous flight in GPS-denied areas. Earlier, Shamshirdar contributed to humanoid robotics through the AUT-UofM Joint Team, advancing toward the 2050 Humanoid League roadmap. He also explored inter-humanoid robot detection and person recognition via soft biometrics, addressing challenges in collaborative robotics. With a growing citation record and a focus on practical, real-world applications, Shamshirdar’s research is shaping the future of autonomous systems and robot teamwork.
Research Focus
Key Achievements
Top Papers
- 1
- 2UAV Visual Teach and Repeat Using Only Semantic Object Features8 citations · 2018
- 3
- 4
- 5
- 6Improving person recognition by weight adaptation of soft biometrics3 citations · 2016