Papers
1
Total Citations
2
H-Index
1
About
Laksh Nanwani is a researcher at the forefront of embodied AI and vision-language navigation, with a focus on bridging the gap between 3D spatial understanding and natural language instructions. His key contributions center on developing semantic mapping frameworks that enable robots to interpret and navigate complex environments through human-like reasoning. Nanwani’s most cited work, “Open-set 3D semantic instance maps for vision language navigation – O3D-SIM” (2024), builds on his earlier foundational paper “Instance-level semantic maps for vision language navigation” (SI Maps, 2023, presented at IEEE). Together, these works introduce a novel approach that moves beyond closed-set object recognition, allowing agents to form open-set, instance-level semantic maps of their surroundings. This innovation empowers robots to understand object relationships and respond to language queries—such as “find the red mug near the laptop”—with unprecedented accuracy. While still early in his career, Nanwani’s research has already garnered attention for its potential to transform autonomous navigation in unstructured environments. His work represents a critical step toward creating AI systems that can perceive, reason, and act in the physical world as intuitively as humans do.
Research Focus
Key Achievements
Top Papers
- 1