scispace - formally typeset

Proceedings ArticleDOI

Design and implementation of driving control system for autonomous vehicle

20 Nov 2014-pp 22-28

TL;DR: The design of driving control system, including both longitudinal and lateral controls, for the Kuafu-II autonomous vehicle is described, which integrates several typical and yet efficient controllers to significantly reduce the system sensitivity to these parameters.
Abstract: The control system design that is responsible for the path tracking and driving safety, is one of the most important technologies for autonomous vehicle. This paper describes the design of driving control system, including both longitudinal and lateral controls, for the Kuafu-II autonomous vehicle. Compared with most of previous works that inevitably require a large amount of parameters, the presented control system design integrates several typical and yet efficient controllers to significantly reduce the system sensitivity to these parameters, and hence is able to achieve the system robustness under diversified circumstances. The effectiveness of presented control system design has been extensively evaluated under simulation and vehicle test on road.
Citations
More filters

Journal ArticleDOI
Bi-ke Chen1, Chen Gong1, Jian Yang1Institutions (1)
TL;DR: This paper designs an “importance-aware loss” (IAL) that specifically emphasizes the critical objects for autonomous driving and derives the forward and backward propagation rules for IAL and applies them to four typical deep neural networks for realizing SS in an intelligent driving system.
Abstract: Semantic segmentation (SS) partitions an image into several coherent semantically meaningful parts and classifies each part into one of the pre-determined classes. In this paper, we argue that the existing SS methods cannot be reliably applied to autonomous driving system as they ignore the different importance levels of distinct classes for safe driving. For example, pedestrian, car, and bicyclist in the scene are much more important than sky and building when driving a car, so their segmentations should be as accurate as possible. To incorporate the importance information possessed by various object classes, this paper designs an “importance-aware loss” (IAL) that specifically emphasizes the critical objects for autonomous driving. The IAL operates under a hierarchical structure and the classes with different importance are located in different levels so that they are assigned distinct weights. Furthermore, we derive the forward and backward propagation rules for IAL and apply them to four typical deep neural networks for realizing SS in an intelligent driving system. The experiments on CamVid and Cityscapes data sets reveal that, by employing the proposed loss function, the existing deep learning models, including FCN, SegNet, ENet, and ERFNet, are able to consistently obtain the improved segmentation results on the pre-defined important classes for safe driving.

42 citations


Cites background from "Design and implementation of drivin..."

  • ...However, we argue that the SS associated with autonomous driving system [3] is quite different from the conventional SS problems....

    [...]

  • ...We find that the outputs of these models are generally stable under α ∈ [1, 3] and λ ∈ [0....

    [...]


Journal ArticleDOI
Wenhao Zong1, Changzhu Zhang1, Zhuping Wang1, Jin Zhu1  +1 moreInstitutions (1)
18 Apr 2018-IEEE Access
TL;DR: A practical framework of hardware and software is proposed to reveal the external configuration and internal mechanism of an autonomous vehicle—a typical intelligent system and the performance of project cocktail is proven to be considerably better in terms of transmission delay and throughput.
Abstract: Architecture design is one of the most important problems for an intelligent system. In this paper, a practical framework of hardware and software is proposed to reveal the external configuration and internal mechanism of an autonomous vehicle—a typical intelligent system. The main contributions of this paper are as follows. First, we compare the advantages and disadvantages of three typical sensor plans and introduce a general autopilot for a vehicle. Second, we introduce a software architecture for an autonomous vehicle. The perception and planning performances are improved with the help of two inner loops of simultaneous localization and mapping. An algorithm to enlarge the detection range of the sensors is proposed by adding an inner loop to the perception system. A practical feedback to restrain mutations of two adjacent planning periods is also realized by the other inner loop. Third, a cross-platform virtual server (named project cocktail) for data transmission and exchange is presented in detail. Through comparisons with the robot operating system, the performance of project cocktail is proven to be considerably better in terms of transmission delay and throughput. Finally, a report on an autonomous driving test implemented using the proposed architecture is presented, which shows the effectiveness, flexibility, stability, and low-cost of the overall autonomous driving system.

27 citations


Cites methods from "Design and implementation of drivin..."

  • ...For example, Xi’an Jiao Tong University [7], [8], Shanghai Jiaotong University [9], Tsinghua University [10], National University of Defense Technology [11], [12] designed their vehicles with LiDARs, Radar, GPS, cameras and other vehicle sensors....

    [...]


Book ChapterDOI
Astrid Rupp1, Michael StolzInstitutions (1)
01 Jan 2017-
TL;DR: This survey focuses on trajectory tracking controllers of advanced driver assistance functions for comfortable and safe automated driving on highways, including essentially PID control, fuzzy control, optimal state feedback controllers, sliding mode control, and model predictive control.
Abstract: This survey focuses on trajectory tracking controllers of advanced driver assistance functions for comfortable and safe automated driving on highways. A short introduction to today’s driver assistance functions and their control objectives is given. Different control schemes that have been proposed during the past few years are discussed, including essentially PID control, fuzzy control, optimal state feedback controllers, sliding mode control, and model predictive control. The separation of longitudinal and lateral dynamics as well as their combination is tackled. In addition to the control design for assistance functions, this work lists prominent controllers of autonomous vehicle prototypes. A simulation of a highway scenario compares the performance of the different control approaches.

27 citations


Proceedings ArticleDOI
03 Jul 2017-
TL;DR: This paper explores the longitudinal control problem of an autonomous car in legal speed range and develops a longitudinal controller that does not rely on vehicle identification parameters, while being capable of tracking the speed profile with comfort acceleration.
Abstract: This paper explores the longitudinal control problem of an autonomous car in legal speed range. The goal is to develop a longitudinal controller that does not rely on vehicle identification parameters, while being capable of tracking the speed profile with comfort acceleration. A modification of a Model Reference Adaptive Control (MRAC) technique found in literature has been deeply studied and implemented, by setting the proper initial conditions for the target application. The proposed architecture is capable of controlling a vehicle whose parameters are known approximately. A CarSim-Simulink joint simulation verifies the feasibility of the proposed strategy and evaluates performances of vehicles at low and high dynamics conditions.

11 citations


Cites background or methods from "Design and implementation of drivin..."

  • ...[6] successfully implemented a Model Reference Adaptive Controller (MRAC) in a real vehicle application....

    [...]

  • ...As suggested by [8] and [6], we will derive a differential equation for the error depending on the adjustable parameters....

    [...]

  • ...Considering the modelling assumptions took in this paper, the first order linear differential equation (12) presented by [6] is explained in detail....

    [...]

  • ...Since the authors of [6] showed the general performances of their autonomous vehicle and they did not give a clear insight about the potential of this technique, nor a clear range of parameter variation for which it guarantees robustness, we decided to analyze their control architecture providing a theoretical foundation of this technique....

    [...]

  • ...A block diagram of the MRAC architecture for the longitudinal dynamics control as proposed in [6] is shown in Fig....

    [...]


Journal ArticleDOI
Hadi Sazgar1, Shahram Azadi1, Reza Kazemi1Institutions (1)
01 Feb 2020-
TL;DR: The purpose of this research is to develop an advanced driver assistance system for the integrated longitudinal and lateral guidance of vehicles in critical high-speed lane change manoeuvres and the proposed trajectory planning method works effectively.
Abstract: The purpose of this research is to develop an advanced driver assistance system for the integrated longitudinal and lateral guidance of vehicles in critical high-speed lane change manoeuvres. The s...

2 citations


References
More filters

Journal ArticleDOI
TL;DR: The robot Stanley, which won the 2005 DARPA Grand Challenge, was developed for high‐speed desert driving without manual intervention and relied predominately on state‐of‐the‐art artificial intelligence technologies, such as machine learning and probabilistic reasoning.
Abstract: This article describes the robot Stanley, which won the 2005 DARPA Grand Challenge. Stanley was developed for high-speed desert driving without human intervention. The robot’s software system relied predominately on state-of-the-art AI technologies, such as machine learning and probabilistic reasoning. This article describes the major components of this architecture, and discusses the results of the Grand Challenge race.

1,851 citations


Chris Urmson1, Joshua Anhalt1, Drew Bagnell1, Christopher R. Baker1  +38 moreInstitutions (5)
01 Jan 2009-
TL;DR: This dissertation aims to provide a history of web exceptionalism from 1989 to 2002, a period chosen in order to explore its roots as well as specific cases up to and including the year in which descriptions of “Web 2.0” began to circulate.
Abstract: Boss is an autonomous vehicle that uses on-board sensors (global positioning system, lasers, radars, and cameras) to track other vehicles, detect static obstacles, and localize itself relative to a road model. A three-layer planning system combines mission, behavioral, and motion planning to drive in urban environments. The mission planning layer considers which street to take to achieve a mission goal. The behavioral layer determines when to change lanes and precedence at intersections and performs error recovery maneuvers. The motion planning layer selects actions to avoid obstacles while making progress toward local goals. The system was developed from the ground up to address the requirements of the DARPA Urban Challenge using a spiral system development process with a heavy emphasis on regular, regressive system testing. During the National Qualification Event and the 85-km Urban Challenge Final Event, Boss demonstrated some of its capabilities, qualifying first and winning the challenge. © 2008 Wiley Periodicals, Inc.

1,052 citations


"Design and implementation of drivin..." refers background in this paper

  • ...In general, the autonomous vehicle integrates environment perception, planning and automatic driving modules [3], [4], [5]....

    [...]


Journal ArticleDOI
Abstract: This article describes vehicle control issues that must be faced in designing a fully automated highway system (AHS). In particular, requirements for a control system architecture as well as issues of lateral and longitudinal "platoon" control are addressed. Interest in AHS is clearly expanding at a rapid pace due to the ever-increasing problems of freeway congestion and the potential for a technological solution. The approach described is based on five years of research as part of the California PATH program. >

412 citations


Book
23 Oct 2007-
Abstract: The DARPA Grand Challenge was a landmark in the field of robotics: a race by autonomous vehicles through 132 miles of rough, cross-country Nevada terrain that showcased exciting and unprecedented capabilities in robotic perception, navigation, and control. The event took place in October 2005, and drew teams of competitors from academia and industry, and many garage hobbyists. This book presents fifteen technical papers that are written at a level that makes them easily accessible to a broad technical audience, describing the technology behind most of the robotic vehicles that participated in this famous race. The papers describe each team's driverless vehicle, race strategy, and insights. As a whole, they present the state of the art in autonomous vehicle technology, and offer a glimpse of future technology for tomorrows driverless cars. This book will serve as an authoritative, archival source for the DARPA Grand Challenge and a must have for robotics students and researchers, since it describes the state of the art in perception, planning and control.

246 citations


"Design and implementation of drivin..." refers background in this paper

  • ...In the DARPA Grand Challenge [1] and Urban Challenge [2] held in 2004, 2005 and 2007 respectively, hundreds of teams from around the world have participated to compete and demonstrate their technology achievement on autonomous vehicle....

    [...]

  • ...For the lateral controller, an effective and simply steering control law, which used by the Stanley, the winner of the DARPA Grand Challenge, is shown as: δ(t) = e2(t) + arctan ke1(t) vx(t) (9) where e1(t) denotes the cross-track error, e2(t) the orientation error, and k is the gain parameter, which determines the convergence rate....

    [...]


BookDOI
01 Jan 2009-
TL;DR: This volume, edited by Martin Buehler, Karl Iagnemma and Sanjiv Singh, presents a unique and comprehensive collection of the scientific results obtained by finalist teams that participated in the DARPA Urban Challenge in November 2007, in the mock city environment of the George Air Force base in Victorville, California.
Abstract: This volume, edited by Martin Buehler, Karl Iagnemma and Sanjiv Singh, presents a unique and comprehensive collection of the scientific results obtained by finalist teams that participated in the DARPA Urban Challenge in November 2007, in the mock city environment of the George Air Force base in Victorville, California. This book is the companion of a previous volume by the same editors which was devoted to the Grand Challenge, which took place in the Nevada desert during October 2005, and was the second in the series of autonomous vehicle races sponsored by DARPA. The Urban Challenge demonstrated how cutting-edge perception, control, and motion planning techniques can allow intelligent autonomous vehicles not only to travel significant distances in off-road terrain, but also to operate in urban scenarios. Beyond the value for future military applications--which motivated DARPA to sponsor the race--the expected impact in the commercial sector for automotive manufacturers is equally, if not more, important: autonomous sensing and control constitute key technologies for vehicles of the future, and might help save thousands of lives that are now lost in traffic accidents. As with the previous STAR volume, the original papers collected in this book were initially published in special issues of the Journal of Field Robotics. Our series is proud to collect them in an archival publication as a special STAR volume!

234 citations


"Design and implementation of drivin..." refers background in this paper

  • ...In the DARPA Grand Challenge [1] and Urban Challenge [2] held in 2004, 2005 and 2007 respectively, hundreds of teams from around the world have participated to compete and demonstrate their technology achievement on autonomous vehicle....

    [...]


Performance
Metrics
No. of citations received by the Paper in previous years
YearCitations
20211
20204
20192
20182
20172