View Chapter

Chapter 62 — Intelligent Vehicles

Alberto Broggi, Alex Zelinsky, Ümit Özgüner and Christian Laugier

This chapter describes the emerging robotics application field of intelligent vehicles – motor vehicles that have autonomous functions and capabilities. The chapter is organized as follows. Section 62.1 provides a motivation for why the development of intelligent vehicles is important, a brief history of the field, and the potential benefits of the technology. Section 62.2 describes the technologies that enable intelligent vehicles to sense vehicle, environment, and driver state, work with digital maps and satellite navigation, and communicate with intelligent transportation infrastructure. Section 62.3 describes the challenges and solutions associated with road scene understanding – a key capability for all intelligent vehicles. Section 62.4 describes advanced driver assistance systems, which use the robotics and sensing technologies described earlier to create new safety and convenience systems for motor vehicles, such as collision avoidance, lane keeping, and parking assistance. Section 62.5 describes driver monitoring technologies that are being developed to mitigate driver fatigue, inattention, and impairment. Section 62.6 describes fully autonomous intelligent vehicles systems that have been developed and deployed. The chapter is concluded in Sect. 62.7 with a discussion of future prospects, while Sect. 62.8 provides references to further reading and additional resources.

PROUD2013 - Inside VisLab's driverless car

Author  Alberto Broggi

Video ID : 178

This video shows the internal and external view of what happened during the PROUD2013 driverlesscar test in downtown Parma, Italy, on July 12, 2013. It also displays the internal status of the vehicle plus some vehicle data (speed, steering angle, and some perception results like pedestrian detection, roundabout merging alert, freeway merging alert, traffic light sensing, etc.). More info available from www.vislab.it/proud.

VIAC: The VisLab Intercontinental Autonomous Challenge

Author  Alberto Broggi

Video ID : 179

This is the official presentation of the VisLab Intercontinental Autonomous Challenge, the longest ever trip undertaken with driverless vehicles, from Italy to China. Four electric vehicles left Parma (Italy) on July 26, 2010, and arrived in Shanghai on Oct 28, 2010, after 3 months of driving and more than 15,000 km. Check www.viac.vislab.it for details.

Motion prediction using the Bayesian-occupancy-filter approach (Inria)

Author  Christian Laugier, E-Motion Team

Video ID : 420

This video illustrates the prediction capabilities of the Bayesian-occupancy-filter approach which is able to maintain an updated record and estimate of the relatives positions and velocities of an autonomous vehicle and of a detected-and-tracked moving obstacle (e.g., a pedestrian in the video). The approach still works despite temporary obstructions. The method has been patented in, and commercialized since, 2005. More details in [62.60].

Cybercars and the city of tomorrow

Author  Christian Laugier, Michel Parent, Inria Multimedia

Video ID : 429

The video presents an overview of the CityMobil European Project and of the related concept of cybercars.

Bayesian Embedded Perception in Inria/Toyota instrumented platform

Author  Christian Laugier, E-Motion Team

Video ID : 566

This video illustrates the concept of “Embedded Bayesian Perception”, which has been developed by Inria and implemented on the Inria/Toyota experimental Lexus vehicle. The objective is to improve the robustness of the on-board perception system of the vehicle, by appropriately fusing the data provided by several heterogeneous sensors. The system has been developed as a key component of an electronic co-pilot, designed for the purpose of detecting dangerous driving situations a few seconds ahead. The approach relies on the concept of the “Bayesian Occupancy Filter” developed by the Inria E-Motion Team. More technical details can be found in [62.25].

Inria/Ligier automated parallel-parking demo in an open parking area

Author  Christian Laugier, Igor Paromtchik

Video ID : 567

This video shows a pioneer demonstration of the concept of "autonomous parallel parking" on the early Inria/Ligier autonomous vehicle (1996). The approach does not require any prior model of the parking area. The car is controlled using information coming from inexpensive, on-board sensors, and motion control decisions (including parking maneuvers) are taken online according to the state of the sensed environment. Public demonstrations of the systems have been performed during several publicized and scientific events (including during three days at the IEEE/RSJ IROS 1997 Conference). More technical details can be found in [62.89].

Collision avoidance at blind intersections using V2V and intention / expectation approach (Inria & Renault)

Author  Christian Laugier, Stephanie Lefevre

Video ID : 822

This video shows how collisions can be avoided at a blind intersection, by using vehicle-to-vehicle communications and by comparing the inferred intentions of drivers and their expected behaviors. More details can be found in [62.26].

Lane tracking

Author  Alex Zelinsky

Video ID : 836

This video demonstrates robust lane tracking under variable conditions, e.g., rain and poor lighting. The system uses a particle-filter-based approach to achieve robustness.

Speed-sign detection

Author  Alberto Broggi, Alexander Zelinsky, Ümit Ozgüner, Christian Laugier

Video ID : 838

This video demonstrates robust speed-sign extraction under variable conditions, i.e., day and night. The system uses the unique radial symmetry detector to achieve robustness.

Pedestrian detection

Author  Alberto Broggi, Alexander Zelinsky, Ümit Ozgüner, Christian Laugier

Video ID : 839

This video demonstrates pedestrian detection using stereo vision to achieve robustness.