LASIGE Talks are fortnightly/monthly events to publicize recently distinguished publications or ongoing cutting-edge work by researchers from the research centre, consolidating the scientific culture of the LASIGE community.

Speakers: Suhail Sherif (LASIGE) and Paulo Canelas (LASIGE, CMU)
Date: November 27, 2024, 11h45
Where: C6.3.27

Program:
11:45 Suhail Sherif
12:05 Paulo Canelas
12:25 Q&A + Break for snacks & coffee

Talk 1: WAYS TO SUCCESSFULY FAIL AT SOLVING PUZZLES
Speaker: Suhail Sherif
Many fundamental questions in theoretical computer science are about the properties of puzzles: Is there an efficient way to solve these puzzles? If they’re not solvable, is there an efficient way to prove that? Is there even always a short proof? What techniques do we have to prove such things? The last couple of questions are the basis for a very active field of research called Proof Complexity.
For most of this talk we will take an introductory look at these questions. Following that we will look at the technique of using Semidefinite Programs, where it might be easier to find proofs but where the proofs might become weaker. This is based on work with Pavel Dvořák and Bruno Loff. Suhail Sherif’s research falls in the ToC research line.

Talk 2: IS IT A BUG? UNDERSTANDING PHYSICAL UNIT MISMATCHES IN ROBOT SOFTWARE
Speaker: Paulo Canelas
Robot software is abundant with variables that represent real-world physical units (e.g., meters, seconds). Operations over different units (e.g., adding meters and seconds) may be incorrect and can lead to dangerous system misbehaviors; manually detecting such mistakes is challenging. Current software analysis techniques identify such mismatches using dimensional analysis rules and ROS-specific assumptions to analyze the source code. However, these ignore the fact that physical unit mismatches in robotics code are often intentional (e.g., when operating a differential drive robot), resulting in false positive bug reports that impede robotics developer trust and productivity.
In this work, we study how developers introduce physical unit mismatches by manually inspecting 180 errors detected by the software analysis technique, Phys. We identify three types of physical unit mismatches and present a taxonomy of eight high-level categories of how these errors manifest. We find that developers often make unforced and paradigmatic physical unit mismatches through differential drives, small angle approximations, and controls. We draw insights on current development to inform future research to better detect, categorize, and address meaningful physical unit mismatches. Paulo Canelas’ research falls in the RSS research line.