Marcelo d'Amorim
North Carolina State University, NC·Computer Science
Self-driving cars must be thoroughly tested before they go on public roads, but testing them in real traffic is slow, limited and can be unsafe. Instead, developers plug their autonomous driving systems (ADS) into high-fidelity simulators and run test drives along routes with static and moving obstacles.
- Fields
Computer Science
Engineering
- Topics
autonomous driving systems
self-driving cars
autonomous vehicles
- Grants
- 1 known grant, through Jun 2027
What they work on
- 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.
- Reduce duplicate infraction reports by using semantic information embedded in parts of a simulation to group and deduplicate failures found by testing tools.
- Increase the realism of simulated driving tests, for example beyond a single self-driving vehicle, by incorporating real-life data and human input.
More about the research
This project asks how simulation-based testing can find more real safety failures, faster and more realistically.
Why it matters
Better simulation testing could help developers catch safety problems in self-driving software before deployment, without the cost and danger of large-scale road testing. Finding more distinct, realistic failures within limited testing time could contribute to safer autonomous vehicles and road safety.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Somil Bansal
Stanford University, CA·Engineering·Early-career
Develop training techniques that make machine-learning perception policies robust by construction, so camera-based controllers stay safe in new situations.
Claire Le Goues
Carnegie Mellon University, PA·Computer Science
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.
Jaime Fernández Fisac
Princeton University, NJ·Engineering·Early-career
Develop a framework based on dynamic game theory in which a robot guarantees safety against the worst case within an Operational Design Domain (ODD), the conditions designers or regulators say it must handle, while modeling how agents gain information over time.
The school
North Carolina State University: 40 labs on PI Pages, $717M a year on research, 603 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.