Sohan Rudra
PhD Candidate
Hesse, Germany
Summary
👤
SeniorSohan Rudra is a mathematician-turned-roboticist with nine years of research experience developing perception, planning, and navigation systems for real-world robots and autonomous vehicles. Currently a Research Associate at Technische Universität Darmstadt and a PhD student at the PEARL robot lab, he built scalable Object-Goal Navigation infrastructure at Google and formulated a weighted minimum-latency approach that achieved >80% success on real robots. His background blends rigorous math (MSc in Mathematics & Computing from IIT Kharagpur) with hands-on field work on LIDAR/IMU-equipped platforms, safe RL for driving, and multi-view geometry for scale-aware visual measurement. He also created memory-efficient attention mechanisms for transformer-like networks and has repeatedly turned theory into deployable pipelines that improved validation performance by double-digit percentages. Based in Darmstadt, he combines academic depth with practical systems engineering across simulation and hardware stacks.
9 years of coding experience
Github Skills (60)
algorithm10
simulation10
algorithms10
event-handling10
python10
mathematics10
sorting-algorithms10
ordinary-differential-equations9
reinforcement-learning9
ode9
machine-learning9
multi-agent9
machine-learning-algorithms9
self-driving-car9
scientific-machine-learning9
Programming languages (6)
Github contributions (5)
Santara/MADRaS
Dec 2019 - Oct 2020
Multi-Agent DRiving Simulator
Contributions:38 commits, 3 PRs, 3 pushes in 10 months
multi-agent
rudrasohan/Advanced-Numerical-Techniques
Jan 2019 - Apr 2019
Contributions:42 commits, 3 pushes in 3 months
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.