Prakhar Dixit
Papers
1
Total Citations
2
H-Index
1
About
Prakhar Dixit is a robotics researcher whose work tackles one of the most persistent challenges in embodied AI: enabling robots to learn complex, multi-goal navigation in the real world. His primary research areas lie at the intersection of hierarchical reinforcement learning, sim-to-real transfer, and autonomous navigation. Dixit’s most notable contribution is the **ReProHRL** framework, which introduces a hierarchical agent architecture designed to overcome the notorious difficulties of sparse rewards and long-horizon tasks in physical environments. By decomposing complex navigation into high-level goal selection and low-level control, his approach allows robots to learn robust policies in simulation that can be effectively fine-tuned for real-world deployment. This work, published in 2023, has already garnered attention for its practical approach to bridging the simulation-to-reality gap. Dixit’s research is particularly significant for advancing the capabilities of mobile robots in unstructured settings, moving beyond controlled lab conditions toward truly autonomous operation in homes, warehouses, and other human-centric spaces. His contributions represent a meaningful step toward making reinforcement learning a viable tool for real-world robotic systems.
Research Focus
Key Achievements
Top Papers
- 1