Claire Le Goues
Carnegie Mellon University, PA·Computer Science
Robots and autonomous systems, such as self-driving vehicles and drones, are becoming common in daily life, but making sure they behave safely is hard. Their software is often messy, and the real world they operate in is complex and unpredictable.
- Fields
Computer Science
Engineering
- Topics
robotic and autonomous systems
robotics software
software engineering
- Grants
- 1 known grant, through May 2027
What they work on
- Develop techniques to infer behavior models with physical attributes from robotic system code, APIs and configuration files, and check those models against component and system properties to detect faults that appear when parts are combined.
- Infer specifications from messy real-world field data such as camera images, compare them with simulation states, and synthesize missing simulation environments to reduce the gap between simulation and reality.
- Build techniques to assess how code, physical and environmental changes affect evolving robotic systems, and to correct and test them cost-effectively, evaluated through studies on real robotic systems.
More about the research
Simulations used to test them can also miss important features of reality. This collaborative project develops methods to find faults in these systems by analyzing both their code and the real-world data they encounter.
Why it matters
Faults in robotic and autonomous systems can endanger people. Better ways to detect faults in robot code and to make simulations more realistic could help developers build safer systems. These methods could also help developers update robotic systems more cheaply and reliably, improving public safety as such systems spread.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Juan Zhai
University of Massachusetts, MA·Computer Science·Early-career
Build a repository-level dataset linking natural-language documentation, formal behavioral specifications and code, with an automated pipeline for reproducible evaluation of specification accuracy.
Marcelo d'Amorim
North Carolina State University, NC·Computer Science
Improve the efficiency of simulation-based testing of autonomous driving systems by using risk signals from anomaly detectors during simulations to find infractions within a fixed time budget.
Dan Negrut
University of Wisconsin-Madison, WI·Engineering
Develop the mathematical foundations for differentiable robot simulators, which produce gradients so model parameters can be tuned automatically to match real-world robot behavior.
The school
Carnegie Mellon University: 28 labs on PI Pages, $505M a year on research, 346 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.