Sushil Bohara
Papers
1
Total Citations
2
H-Index
1
About
Sushil Bohara is a robotics researcher whose work focuses on advancing adaptive locomotion in legged robots through reinforcement learning. His key research area lies at the intersection of curiosity-driven exploration and control policy optimization for quadruped systems. In his most notable contribution, "CuriousRL: Curiosity-Driven Reinforcement Learning for Adaptive Locomotion in Quadruped Robots" (2024), Bohara addresses a critical limitation in standard Proximal Policy Optimization (PPO) algorithms—their restricted exploration ability. By integrating the Intrinsic Curiosity Module (ICM) with PPO, he demonstrates how intrinsic reward signals can significantly enhance learning efficiency, enabling robots to discover more robust and adaptive gaits in complex environments. This work has already garnered early citations, signaling its growing influence in the field. Bohara’s research bridges a key gap between deep reinforcement learning theory and practical robotic control, offering a pathway toward more autonomous and resilient quadruped platforms. His contributions are particularly relevant for applications in search-and-rescue, exploration, and unstructured terrain navigation, where adaptive locomotion is critical.
Research Focus
Key Achievements
Top Papers
- 1