To content
Fakultät für Informatik
Student Project 613

ACC++ Domain-Specific Languages for Autonomous Driving

Winter 2017/18 to Sommer 2018

Motivation

The automotive industry is working at full speed on the development of autonomous driving functions. A major challenge in the development of autonomous driving functions or fully autonomous vehicles is assurance, i.e., documenting safety for the user. However, there are often semantic gaps between requirements and standards (in natural language and/or state machines), specifications (through block diagrams), and the implementation of a function. These gaps make it difficult to reason about the safety of a system. In addition, not all situations in which an autonomous system must later function are known at development time.

Toolchain

For the previously mentioned (so far partly informal) formats for the description of requirements for ACCs, a modeling environment designed for engineers in the automotive industry shall be realized using the Cinco Meta Tooling Suite. Cinco is a tool based on the Eclipse Modeling Framework (EMF), with which specialized Eclipse-based modeling environments (RCP) for modeling languages can be generated very easily from metamodel descriptions of these languages. The work of the project group will be evaluated in a simulation environment and on model vehicles (1:10), each using a technology stack that is also used in the automotive industry: Virtual Test Drive will be used as the simulation environment. ADTF is to be used on the model vehicles.

Goal

The core objective is a complete human–robot interaction pipeline: a human passes the ball; the robot detects and tracks it, positions itself appropriately, and executes a controlled, targeted shot on goal.

The central challenge is the real-time integration of perception, modeling, motion prediction, and physical execution on the new robot platform.