Michael Darms

Obstacle Detection and Tracking for the Urban Challenge

This paper describes the obstacle detection and tracking algorithms developed for Boss, which is Carnegie Mellon University s winning entry in the 2007 DARPA Urban Challenge. We describe the tracking subsystem and show how it functions in the context of the larger perception system. The tracking subsystem gives the robot the ability to understand complex scenarios of urban driving to safely operate in the proximity of other vehicles. The tracking system fuses sensor data from more than a dozen sensors with additional information about the environment to generate a coherent situational model. A novel multiple-model approach is used to track the objects based on the quality of the sensor data. Finally, the architecture of the tracking subsystem explicitly abstracts each of the levels of processing. The subsystem can easily be extended by adding new sensors and validation algorithms.

Autonomous Driving in Traffic: Boss and the Urban Challenge

The DARPA Urban Challenge was a competition to develop autonomous vehicles capable of safely, reliably and robustly driving in traffic. In this article we introduce Boss, the autonomous vehicle that won the challenge. Boss is complex artificially intelligent software system embodied in a 2007 Chevy Tahoe. To navigate safely, the vehicle builds a model of the world around it in real time. This model is used to generate safe routes and motion plans in both on roads and in unstructured zones. An essential part of Boss’ success stems from its ability to safely handle both abnormal situations and system glitches.

Detection, prediction, and avoidance of dynamic obstacles in urban environments

We present an approach for robust detection, prediction, and avoidance of dynamic obstacles in urban environments. After detecting a dynamic obstacle, our approach exploits structure in the environment where possible to generate a set of likely hypotheses for the future behavior of the obstacle and efficiently incorporates these hypotheses into the planning process to produce safe actions. The techniques presented are very general and can be used with a wide range of sensors and planning algorithms. We present results from an implementation on an autonomous passenger vehicle that has traveled thousands of miles in populated urban environments and won first place in the DARPA Urban Challenge.

Classification and tracking of dynamic objects with multiple sensors for autonomous driving in urban environments

Future driver assistance systems are likely to use a multisensor approach with heterogeneous sensors for tracking dynamic objects around the vehicle. The quality and type of data available for a data fusion algorithm depends heavily on the sensors detecting an object. This article presents a general framework which allows the use sensor specific advantages while abstracting the specific details of a sensor. Different tracking models are used depending on the current set of sensors detecting the object. A sensor independent algorithm for classifying objects regarding their current and past movement state is presented. The described architecture and algorithms have been successfully implemented in Tartan racingpsilas autonomous vehicle for the urban grand challenge. Results are presented and discussed.

Map based road boundary estimation

Knowledge about the road shape is a key element for driver assistance systems which support the driver in complex scenarios like construction sites. Systems only using information derived from lane markings reach a limit here. The paper presents an approach to estimate road boundaries based on static objects bounding the road. A map based environment description and an interpretation algorithm identifying the road boundaries in the map are used. Two approaches are presented for estimating the map, one based on a radar sensor, one on a mono video camera. Besides that two fusion approaches are described. The estimated boundaries are independent of road markings and as such can be used as orthogonal information with respect to detected markings. Results of practical tests using the estimated road boundaries for a lane keeping system are presented.

Data Fusion Strategies in Advanced Driver Assistance Systems

Data fusion plays a central role in more and more automotive applications, especially for driver assistance systems. On the one hand the process of data fusion combines data and information to estimate or predict states of observed objects. On the other hand data fusion introduces abstraction layers for data description and allows building more flexible and modular systems. The data fusion process can be divided into a low-level processing (tracking and object discrimination) and a high level processing (situation assessment). High level processing becomes more and more the focus of current research as different assistance applications will be combined into one comprehensive assistance system. Different levels/strategies for data fusion can be distinguished: Fusion on raw data level, fusion on feature level and fusion on decision level. All fusion strategies can be found in current driver assistance implementations. The paper gives an overview of the different fusion strategies and shows their application in current driver assistance systems. For low level processing a raw data fusion approach in a stereo video system is described, as an example for feature level fusion the fusion of radar and camera data for tracking is explained. As an example for a high level fusion algorithm an approach for a situation assessment based on multiple sensors is given. The paper describes practical realizations of these examples and points out their potential to further increase traffic safety with reasonably low cost for the overall system.

An Assistance System for Construction-Sites

Abstract The contribution describes an assistance system, which supports the driver with lateral functions in construction-sites. This system is based on short-range radar sensors for side observation. The observation ahead of the vehicle is based on 77Ghz long range radar and a mono camera. From the camera images, a 3D reconstruction is computed. The result is fused with data of the imaging radar sensor ARS300 using a so-called “Occupancy Grid” approach. Based on this, road boundaries are determined. The contribution shows further how road boundaries can be determined from this grid information. Together with dynamic objects and roadway markings, a current right and left delimitation of the allowed driving corridor is determined and a desired path for the ego vehicle is computed. For the lateral support, a lane centring function is combined with a loose lateral guidance called “virtual wall”. The “virtual wall” function is described in detail and the resulting performance in a test construction-site with truck dummy vehicle is shown.

Fusion umfelderfassender Sensoren

Es existieren Fahrerassistenzsysteme, die ausschlieslich auf Einzelsensorlosungen aufbauen. Als Beispiel lassen sich die Anwendungen Adaptive Cruise Control, die z. B. mit einem Radar- oder einem Lasersensor arbeitet, und Lane Departure Warning nennen, welche zumeist auf Videosensorik basiert.