Saumya Saksena
Robotics Engineer at Navya Mobility
Paris, Ile-de-France
Summary
👤
Senior🎓
Top SchoolSaumya Saksena is a Robotics R&D Engineer based in Paris with eight years of experience designing perception and embedded AI systems for autonomous platforms. Currently at Navya Mobility, he focuses on building safety-first perception algorithms for self-driving vehicles, drawing on prior work at ams OSRAM where he delivered real-time neural networks for 3D depth, light estimation and physiological sensing on low-power devices. His background spans end-to-end robotics stacks—from SLAM and semantic segmentation for service robots to EEG- and sensor-driven control of UAVs—combined with hands-on hardware integration and deployment. Saumya has driven cross-functional projects, shipped production-ready pipelines, and is an inventor on multiple patent filings, reflecting a practical bent for turning research into robust products. Notably, his work blends classic signal-processing and morphological techniques with modern deep learning to solve safety-critical perception problems under resource constraints.
9 years of coding experience
6 years of employment as a software developer
Master of Science - MS, Systems and Control, 7.8/10, Master of Science - MS, Systems and Control, 7.8/10 at University of TwenteBITS Pilani, Birla Institute of Technology and Science
English, Hindi, French
Github Skills (97)
opencv10
python10
deep-learning10
coco10
depth-estimation10
convolutional-neural-networks10
image-enhancement10
ml10
aerial-image-detection10
torchvision10
neural-network10
object-detection10
computer-vision10
transfer-learning10
autonomous-robots10
Programming languages (6)
Github contributions (5)
dronefreak/dji-tello-collision-avoidance-pydnet
May 2019 - Dec 2021
Real-time monocular depth estimation for DJI Tello drone collision avoidance. Modern TF2.x implementation with webcam support, comprehensive tests, and autonomous navigation. PyDNet-based with MiDaS support.
Contributions:5 commits, 8 PRs, 17 pushes in 2 years 8 months
depth-estimationtellodronewebcamdji-tellocomputer-vision
dronefreak/dji-tello-object-detection-segmentation
May 2019 - Dec 2021
Modern instance segmentation for DJI Tello drones with YOLOv8/Detectron2. Real-time performance, modular design, autonomous tracking.
Contributions:7 commits, 14 PRs, 19 pushes in 2 years 8 months
detectroninstance-segmentationtellodroneyolov8aerial-robotics
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.