Carolina Parada
Papers
9
Total Citations
1,163
H-Index
6
About
Carolina Parada is a pioneering researcher at the intersection of robotics, machine learning, and human-robot interaction, whose work has fundamentally advanced how robots understand and act upon language-based instructions in real-world environments. Her most celebrated contributions include "Do As I Can, Not As I Say" (516 citations), which demonstrated how large language models can be grounded in physical robotic affordances to enable meaningful task execution, and the landmark RT-1 Robotics Transformer (512 citations), which showed that large-scale, diverse datasets could train robots capable of generalizing across hundreds of real-world manipulation tasks. These works helped establish the foundation model paradigm in robotics. Beyond task execution, Parada has explored expressive robot behaviors for natural human-robot coordination, human motion anticipation for safe robot navigation, and agile legged locomotion benchmarking through the Barkour framework. Her most recent contribution to the Gemini Robotics initiative signals her ongoing role in translating frontier AI capabilities into physically embodied systems. With research spanning navigation, locomotion, and socially intelligent robots, Parada represents a leading voice shaping how robots will perceive, reason, and collaborate alongside humans.
Research Focus
Key Achievements
Top Papers
- 1Do As I Can, Not As I Say: Grounding Language in Robotic Affordances516 citations · 2022
- 2RT-1: Robotics Transformer for Real-World Control at Scale512 citations · 2023
- 3Generative Expressive Robot Behaviors using Large Language Models49 citations · 2024
- 4RT-1: Robotics Transformer for Real-World Control at Scale38 citations · 2022
- 5Robots That Can See: Leveraging Human Pose for Trajectory Prediction25 citations · 2023
- 6Barkour: Benchmarking Animal-level Agility with Quadruped Robots13 citations · 2023
- 7
- 8Gemini Robotics: Bringing AI into the Physical World4 citations · 2025
- 9What Do Foundation Models have to Do With and For HRI?2 citations · 2024