PAVIA FERRARA TORINO PARMA ANCONA FIRENZE ROMA

Transcription

1 1

2 The ARGO Autonomous Vehicle Massimo Bertozzi 1, Alberto Broggi 2, and Alessandra Fascioli 1 1 Dipartimento di Ingegneria dell'informazione Universita di Parma, I PARMA, Italy 2 Dipartimento di Informatica e Sistemistica Universita di Pavia, I PAVIA, Italy Abstract. ARGO is a Lancia Thema passenger car equipped with a vision-based system that allows to extract road and environmental information for the automatic driving of the vehicle. By means of stereo vision, obstacles on the road are detected and localized, while the processing of a single monocular image allows to extract the road geometry in front of the vehicle and the position of the preceding vehicle. The system has been tested with a 6-days 2000-km long trip coverer in automatic mode. 1 The ARGO Vehicle ARGO is the experimental autonomous vehicle developed at the Dipartimento di Ingegneria dell'informazione of the University of Parma, Italy. It integrates the Fig. 1. The ARGO experimental vehicle: external and internal view main results of the research conducted over the last few years on architectures and AI techniques for vision based automatic road vehicles guidance.? This project was partially supported by CNR in the frame of PFT II and Madess II

3 ARGO, a Lancia Thema 2000 passenger car (gure 1), has been extensively tested thanks to a tour throughout Italy (the MilleMiglia in Automatico Tour) of more than 2000 km along Italian highways in real trac conditions. During this test the system drove itself for about 94% of the total trip. ARGO is equipped with a vision-based system that allows to extract road and environmental information from the acquired scene, and with dierent output devices used to test the automatic features. 1.1 The input Only passive sensors (cameras) are used on ARGO to sense the surrounding environment, since they oer the possibility to acquire data in a non-invasive way, namely without altering the environment. The vision system. The ARGO vehicle is equipped with a stereoscopic vision system consisting of two synchronized cameras able to acquire pairs of grey level images. The installed devices are small (3.2 cm 3.2 cm) low cost cameras featuring a 6.0 mm focal length and a 360 lines resolution which can receive the synchronism from an external signal. The cameras lie inside the car at the top corners of the windscreen, so that the longitudinal distance between the two cameras is maximum. The optical axes are parallel and, in order to handle also non at roads, part of the scene over the horizon is captured. The data acquisition system. Images are acquired by a PCI Matrox board, which is able to grab three pixel images simultaneously. The images are directly stored into the main memory of the host computer thanks to the use of DMA. The acquisition can be performed in real time, at a 25Hz rate in case of full frames or at a 50Hz rate in case of single eld acquisition. Since the processing is based on stereo vision, camera calibration plays a basic role for the success of the approach. It is divided in two steps. The rst part of the calibration process is an interactive step: a user selects a set of homologous points whose world coordinates are known to the system; this mapping is used to compute the calibration parameters. After the supervised phase, the computed calibration parameters have to be rened. The parameters tuning consists of an iterative procedure aimed at optimizing a error function. Furthermore, an I/O board is used to acquire information about the velocity of the vehicle, and other user data. 1.2 Output. The ARGO vehicle has autonomous steering capabilities: the result of the processing (position of obstacles and geometry of the road) is used to drive an actuator on the steering wheel. More precisely, the vehicle lateral oset, the vehicle yaw relative to the road centerline, the relative position of the vehicle ahead

4 and the upcoming road curvature, are combined to determine the vehicle future position a given distance ahead of the vehicle and the steering wheel is turned to head the vehicle toward a safe position. For debug purposes, the result of the processing is also fed to the driver through a set of output devices installed on-board of the vehicle. An acoustical device warns the driver in case dangerous conditions are detected. Moreover, a visual feedback is supplied to the driver by displaying the results both on an on-board monitor and on a led-based control panel. 1.3 Functionalities Thanks to the control panel the driver has the possibility to adjust the values of various parameters relative to the driving task and to select the functionality of the system. Manual Driving: the system monitors the driver activity; in case of dangerous situations the system warns the driver with acoustic and optic signals. Supervised Driving: in case of dangerous situations, the system takes the control of the vehicle in order to keep it in a safe condition. Automatic Driving: the system drives automatically, following the lane and localizing obstacles on the path; it is able to perform lane changes. 2 The "MilleMiglia in Automatico" Extensive Test In order to extensively test the vehicle under dierent trac situations, road environments, and weather conditions, a 2000 km journey was carried out in June During this test, ARGO drove itself autonomously along the Italian highway network, passing through at areas and hilly regions including viaducts and tunnels. The Italian road network is particularly suited for such an extensive test since it is characterized by quickly varying road scenarios which included changing weather conditions and a generally good amount of trac. The tour took place on highways and freeways, but the system proved to work also on suciently structured rural extraurban roads with no intersections. The analysis of the data collected during the tour allowed the computation of a number of statistics regarding system performance (see gure 2). In particular, for each stage of the tour the average and the maximum speed of the vehicle during automatic driving were computed. The average speed was strongly inuenced by the heavy trac conditions (especially on Torino, Milano and Roma's by-passes) and by the presence of toll stations, junctions, and road works. The automatic driving percentage and the maximum distance automatically driven show high values despite the presence of many tunnels (particularly during the Appennines routes Ancona-Roma and Firenze-Bologna) and of several stretches of road with absent or worn lane markings (Ferrara-Ancona and Ancona-Roma) or even no lane markings at all (Firenze-Bologna). It is fundamentally important to also note that some stages included passing through

5 toll stations and transiting in by-passes with heavy trac and frequent queues during which the system had to be switched o. TORINO PAVIA PARMA FERRARA FIRENZE ANCONA ROMA maximum distance in automatic [km] percentage of automatic driving maximum speed [km/h] average speed [km/h] kilometers Stage Date Departure Arrival 1 1 st June 1998 Parma Torino nd June 1998 Torino Pavia nd June 1998 Pavia Ferrara th June 1998 Ferrara Ancona th June 1998 Ancona Roma th June 1998 Roma Firenze th June 1998 Firenze Parma Fig. 2. MilleMiglia in Automatico: tour schedule, no-hands driving, and statistical data regarding system performance 3 Further Information A complete description of the vehicle prototype including technical details and images is available on-line at the following web address: while a description of the whole project, as well as comparisons with dierent other projects developed worldwide, has been included in the book "Automatic Vehicle Guidance: the Experience of the ARGO Autonomous Vehicle" [1]. References 1. A. Broggi, M. Bertozzi, A. Fascioli, and G. Conte. Automatic Vehicle Guidance: the Experience of the ARGO Autonomous Vehicle. World Scientic Co. Publisher, Singapore, April ISBN