Papers
3
Total Citations
66
H-Index
2
About
S Phaniteja is a robotics researcher whose work focuses on the intersection of deep reinforcement learning and humanoid robot control, with a particular emphasis on dynamic stability and coordinated motion planning. Their most significant contribution is the development of a deep reinforcement learning approach for dynamically stable inverse kinematics (IK) in humanoid robots, a breakthrough that addresses the critical challenge of maintaining balance during real-time motion. This foundational work, published in 2017, has accumulated 58 citations and demonstrates a practical methodology for generating joint-space trajectories that ensure stable configurations—a vital capability for humanoid robots that are inherently prone to losing balance. Phaniteja has also advanced the field of multi-limb coordination, proposing a faster, online motion planning strategy for dual-arm reachability tasks in humanoids with articulated torsos. This work tackles the complexity of coordinating multiple limbs simultaneously, moving beyond traditional offline planning methods. Through these contributions, Phaniteja has established a reputation for developing computationally efficient, learning-based solutions that enable humanoid robots to perform complex, dynamically stable movements in real time, making their research highly relevant for students and researchers working on legged locomotion, manipulation, and robot learning.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3