-
Formal Verification of End-to-End Learning in Cyber-Physical Systems: Progress and Challenges
Autonomous systems – such as self-driving cars, autonomous drones, and a...
read it
-
Reinforcement Learning in Conflicting Environments for Autonomous Vehicles
In this work, we investigate the application of Reinforcement Learning t...
read it
-
Longitudinal Analysis of the Applicability of Program Repair on Past Commits
The applicability of program repair in the real world is a little resear...
read it
-
Automatic Software Repair: a Bibliography
This article presents a survey on automatic software repair. Automatic s...
read it
-
NeVer 2.0: Learning, Verification and Repair of Deep Neural Networks
In this work, we present an early prototype of NeVer 2.0, a new system f...
read it
-
Bounded Exhaustive Search of Alloy Specification Repairs
The rising popularity of declarative languages and the hard to debug nat...
read it
-
Metareasoning in Modular Software Systems: On-the-Fly Configuration using Reinforcement Learning with Rich Contextual Representations
Assemblies of modular subsystems are being pressed into service to perfo...
read it
Using Taint Analysis and Reinforcement Learning (TARL) to Repair Autonomous Robot Software
It is important to be able to establish formal performance bounds for autonomous systems. However, formal verification techniques require a model of the environment in which the system operates; a challenge for autonomous systems, especially those expected to operate over longer timescales. This paper describes work in progress to automate the monitor and repair of ROS-based autonomous robot software written for an a-priori partially known and possibly incorrect environment model. A taint analysis method is used to automatically extract the data-flow sequence from input topic to publish topic, and instrument that code. A unique reinforcement learning approximation of MDP utility is calculated, an empirical and non-invasive characterization of the inherent objectives of the software designers. By comparing off-line (a-priori) utility with on-line (deployed system) utility, we show, using a small but real ROS example, that it's possible to monitor a performance criterion and relate violations of the criterion to parts of the software. The software is then patched using automated software repair techniques and evaluated against the original off-line utility.
READ FULL TEXT
Comments
There are no comments yet.