Andrea Bajcsy is an Assistant Professor in the Robotics Institute at Carnegie Mellon University where she leads the Interactive and Trustworthy Robotics Lab (Intent Lab). She broadly works at the intersection of robotics, machine learning, control theory, and human-AI interaction. Prior to joining CMU, Andrea received her Ph.D. in Electrical Engineering & Computer Science from University of California, Berkeley in 2022. She is the recipient of the DARPA Young Faculty Award (2025), NSF CAREER Award (2025), Amazon Research Award (2025), Google Research Scholar Award (2024), Finalist for Best Paper Award of the IEEE RAS Technical Committee on Robot Control (2024), Rising Stars in EECS Award (2021), Honorable Mention for the T-RO Best Paper Award (2020), and the NSF Graduate Research Fellowship (2016).
Talk Title: How to Control a Robot You Didn’t Train
Abstract:
Robot foundation models (FMs) are rapidly becoming accessible: with modest compute, anyone can download a pretrained model and deploy it on a robot in a home or business “zero-shot”. But deploying a robot FM today often feels like operating a black box: you inherit a model’s capabilities but also its biases and failure modes without fully understanding where they came from. This makes it difficult to predict what a robot can and cannot do and whether it will behave safely and reliably in novel situations. In this talk, I will discuss my group’s work on controlling robot foundation models that we did not train ourselves. Specifically, I will describe a spectrum of control mechanisms that operate on a model’s inputs (e.g., natural language), internals (e.g., the generative process), and outputs (e.g., safety filters) to steer behavior toward safe, aligned, and high-performing outcomes while preserving the broad capabilities acquired during pretraining. Throughout the talk, I will present examples spanning both visuomotor policies and world models, with applications in robotic manipulation.
RPL Summer School 2026 