Shuran Song
Shuran Song studies how robots learn to perceive and manipulate objects. Her work includes adapting learned behavior to deformable objects and new physical conditions. Song coauthored Iterative Residual Policy with Cheng Chi and three Toyota Research Institute colleagues. The method learns how action changes affect an observed trajectory, then adapts actions to reach a goal. The RSS 2022 conference gave the Best Paper Award to Iterative Residual Policy.
- Now at
- Stanford University
- Works
- 166
- Citations
- 25,811
- h-index
- 49
Publication numbers from OpenAlex, as of 14 October 2026.
Timeline
-
2022
Learning through changes in motion
Song coauthored Iterative Residual Policy with Cheng Chi and three Toyota Research Institute colleagues. The method learns how action changes affect an observed trajectory, then adapts actions to reach a goal.
-
2022
Shared best-paper award
The RSS 2022 conference gave the Best Paper Award to Iterative Residual Policy.
-
2025
Open robot hardware
Song coauthored ToddlerBot, an open-source humanoid platform compatible with machine-learning research, at CoRL 2025. The project is credited to Haochen Shi, Weizhuo Wang, Song and C. Karen Liu.
-
As of October 2026
Robotics and Embodied AI Lab
Song is an associate professor at Stanford and leads its Robotics and Embodied AI Lab. The group studies perception and manipulation learned from physical interactions.
Sources and credits
Photo: shurans.github.io; creator not stated. License: Not stated by source. Source: shurans.github.io. Cropped to a square and resized. Ask us to remove or replace this photo.