Subhransu Mishra
Papers
1
Total Citations
10
H-Index
1
About
Subhransu Mishra is a robotics researcher whose work focuses on bridging the gap between simulation and real-world deployment for autonomous mobile robots. His key research areas include reinforcement learning, domain randomization, and robust control policy transfer. Mishra’s most notable contribution is his pioneering work on data-driven domain randomization, where he developed a method to use real robot motion trajectories to construct high-fidelity stochastic dynamics models. This approach enables the training of control policies in simulation that come with verifiable performance guarantees, directly addressing the notorious sim-to-real transfer problem. His landmark 2019 paper, "Using Data-Driven Domain Randomization to Transfer Robust Control Policies to Mobile Robots," has garnered 10 citations and demonstrated the technique’s effectiveness on a 1/5 scale agile ground robot. This work stands out for its practical, data-centric approach to creating robust policies that can be deployed with confidence. Mishra’s research is particularly valuable for students and engineers working on autonomous navigation, offering a principled pathway from simulation-based training to reliable real-world robot control.
Research Focus
Key Achievements
Top Papers
- 1