Over the past five years, our team at the LESS LAB has made significant strides to develop more dependable autonomous systems, particularly those relying on machine learning. Here is a summary of this effort.
- Domain-Specific Abstractions for Multi-Dimensional Sensor Inputs: We extract meaningful entities and relationships from raw sensor data (like images or point clouds). This allows us to: a) Generating More Realistic and Diverse Inputs, b) Specifying and Assessing Higher-Level Properties.
- Type Systems for Detecting World Inconsistencies: We develop type systems that catch inconsistencies between system code semantics and the physical world.
- Verification Frameworks for Learned Components: We create frameworks that verify DNNs against a wide range of properties, including robustness and reachability, and that focus on the input distribution to generate more useful counterexamples and be more efficient.
- Testing frameworks that consider the Physical State , besides the cyber state, of the autonomous system to generate more cost-effective system tests.
This effort has helped to foster the growth of exceptional PhD students including: John Paul Ore (now at NCST), David Shriver (now at CMU-SEI), Carl Hildebrandt, Meriel Stein, Trey Woodlief, and Felipe Toledo. I am very thankful to them and to my close collaborator, Matthew B. Dwyer, whose brilliance and kindness have served me as a reference for almost two decades.