Hanjaya Mandala
Papers
6
Total Citations
51
H-Index
3
About
Hanjaya Mandala is a robotics researcher whose work sits at the intersection of humanoid robotics, deep reinforcement learning, and autonomous navigation. His primary research areas include hierarchical reinforcement learning for complex manipulation tasks, dual-arm coordination in humanoid robots, and robust navigation in highly constrained environments. Mandala's most impactful contribution is his work on hierarchical deep reinforcement learning for adult-sized humanoid robots, enabling them to drag heavy objects—a challenging task requiring coordinated whole-body control. His paper on this topic has garnered 29 citations, reflecting its significance in the field. He has also made notable contributions to synchronous dual-arm manipulation, introducing a method that combines LiDAR-based 3D object tracking with Gaussian distribution for precise trajectory planning. Mandala's work on autonomous ground navigation was recognized through his participation in the second BARN Challenge at ICRA 2023, where his system demonstrated state-of-the-art performance in highly constrained spaces. Additionally, he has developed fast object detection algorithms for humanoid marathon robots, capable of running on low-performance CPUs. His recent research addresses the critical issue of high-frequency oscillations in continuous control policies, benchmarking methods to improve smoothness for real-world deployment.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Synchronous Dual-Arm Manipulation by Adult-Sized Humanoid Robot6 citations · 2020
- 4
- 5
- 6