Reasoning About Emergent Behaviors at Runtime

Name: Caio Batista de Melo
Chair: Nikil Dutt

Date: May 23, 2023

Time: 2:00 PM

Location: DBH 4011

Committee: Fadi Kurdahi, Tony Givargis

Title: Reasoning About Emergent Behaviors at Runtime

Abstract:

As Autonomous Vehicles (AVs) become more common in the market, the development of new technologies and solutions for them advances quickly. However, there still are safety concerns regarding the increasing presence of AVs on public roads. For example, the Cali- fornia Department of Motor Vehicles reported an approximate average of 3 disengagement events for each AV under test in 2021 and 1 event for every 1,500 driven miles. Considering that a vehicle drives, on average, 15,000 miles per year, an AV would have ten such incidents annually. With this in mind, work needs to be done to enable AVs to handle unexpected sit- uations (i.e., emergent behaviors) that can arise while driving, increasing the safety for both humans and AVs on the road. This dissertation discusses possible approaches to improve the detection and reasoning of emergent behaviors at runtime.

First, it describes SAFER, a framework to monitor individual systems using runtime verifica- tion alongside machine learning anomaly detection to detect emergent behaviors at runtime. SAFER achieves an average F1-score of 83% over four different example systems, showcas- ing its efficacy to be on par with related work while being applicable to different classes of applications. Next, it discusses DRIVE, a framework for monitoring collective systems that can work together to find global anomalies that affect collective safety by identifying violations in local properties. Throughout a state-of-the-art inspired truck platooning case study, DRIVE can detect all safety property violations, with most queries resolved under 1 ms and a maximum latency of 11 ms per query, demonstrating its promise. Lastly, it presents LOCoCAT, a low-overhead framework for emergent behavior reasoning to classify anomaly types based on vehicular data. LOCoCAT achieves an F1-score of up to 99.16% within the first 50 ms of the anomaly, allowing the system to react quickly. These three techniques can be combined to allow future AVs to operate more safely on the road.

Short Bio:

Caio Batista del Melo is a Ph.D. candidate at the Computer Science Department of the University of California, Irvine, where he works with Prof. Nikil Dutt on the Information Processing Factory project. His research focuses on emergent behaviors and fault detection of systems. From a big-picture view, he explored how we can enable self-driving vehicles to detect unexpected situations and decide how to best react to them. Prior to joining UCI, he attended the University of Brasília, in Brazil, where he got a B.Sc. and an M.Sc. in Computer Science. While at UnB, he worked with Prof. Genaína Rodrigues researching dependable distributed systems, more specifically, implied scenarios.