Iman Soltani
Papers
2
Total Citations
10
H-Index
2
About
Iman Soltani is a rising researcher at the intersection of robotics, computer vision, and embodied AI, with a focus on enabling autonomous systems to perceive and act in complex, unstructured environments. Their work bridges the gap between human-inspired navigation and dexterous robotic manipulation. Soltani’s first highly cited paper, “Hierarchical End-to-End Autonomous Navigation Through Few-Shot Waypoint Detection” (2024, 6 citations), introduces a novel framework that leverages few-shot learning to detect waypoints from minimal human-like instructions, mimicking how humans navigate using salient landmarks. This work advances the goal of creating robots that can follow concise, natural commands. In their second notable contribution, “Active Vision Might Be All You Need: Exploring Active Vision in Bimanual Robotic Manipulation” (2025, 4 citations), Soltani challenges the static camera paradigm in imitation learning, demonstrating that active, movable cameras can significantly reduce occlusion and expand the field of view during high-precision bimanual tasks. This work has immediate implications for manufacturing and assistive robotics. Despite being early in their career, Soltani’s research is already garnering attention for its innovative integration of hierarchical learning, active perception, and human-inspired strategies, marking them as a promising voice in next-generation autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2