Nehchal Jindal
Papers
1
Total Citations
18
H-Index
1
About
Nehchal Jindal is a roboticist whose research lies at the intersection of autonomous navigation, manipulation, and reinforcement learning. His most influential work tackles the challenging problem of Navigation Among Movable Obstacles (NAMO), where a robot must not only plan a path but also physically rearrange its environment. In a landmark 2016 paper, Jindal introduced the first planner capable of handling under-specified object dynamics on a real robot, bridging a critical gap between simulation and the physical world. By leveraging recent advances in reinforcement learning—specifically, learning dynamic constraints from interaction—his approach enabled robots to reason about which objects could be safely pushed or moved, and how. This work, which has garnered 18 citations, represents a significant step toward making robots truly autonomous in cluttered, human-centric spaces. Jindal’s contributions have been recognized for their practical impact, demonstrating that learned models can effectively replace hand-crafted heuristics in complex, real-world scenarios. His research continues to inspire new approaches in mobile manipulation and adaptive planning, making him a notable figure in the growing field of learning-based robotics.
Research Focus
Key Achievements
Top Papers
- 1Navigation Among Movable Obstacles with learned dynamic constraints18 citations · 2016