Tejaswini Manjunath
Papers
1
Total Citations
2
H-Index
1
About
Tejaswini Manjunath is a roboticist and artificial intelligence researcher whose work sits at the intersection of hierarchical reinforcement learning, multi-goal navigation, and sim-to-real transfer. Her most-cited paper, “ReProHRL: Towards Multi-Goal Navigation in the Real World using Hierarchical Agents” (2023), tackles a fundamental challenge in robotics: enabling agents to learn effective policies in real-world environments with sparse rewards and multiple objectives. By proposing a hierarchical framework that decomposes complex navigation tasks into manageable sub-goals, Manjunath’s work bridges the gap between simulation training and real-world deployment—a critical step toward practical, autonomous systems. Her research is particularly notable for addressing the failure modes of standard RL algorithms in sparse-reward settings, offering a pathway for robots to operate reliably outside controlled labs. With 2 citations in its early publication stage, this work signals growing interest in her approach to scalable, multi-goal navigation. Manjunath’s contributions are shaping the future of embodied AI, where robots must navigate unstructured, goal-rich environments with efficiency and adaptability.
Research Focus
Key Achievements
Top Papers
- 1