2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

6th Workshop on Planning, Perception and Navigation for Intelligent Vehicles

Full Day Workshop, Salon 12

September 14th, 2014, Chicago, USA

Registration, Proceedings

Contact : Professor Philippe Martinet
IRCCyN-CNRS Laboratory, Ecole Centrale de Nantes,
1 rue de la Noë
44321 Nantes Cedex 03, France
Phone: +33 237406975, Fax: +33 237406934,
Email: Philippe.Martinet@irccyn.ec-nantes.fr,
Home page: http://www.irccyn.ec-nantes.fr/~martinet


Professor Philippe Martinet, IRCCyN-CNRS Laboratory, Ecole Centrale de Nantes, 1 rue de la Noë, 44321 Nantes Cedex 03, France, Phone: +33 237406975, Fax: +33 237406930, Email: Philippe.Martinet@irccyn.ec-nantes.fr,
Home page: http://www.irccyn.ec-nantes.fr/~martinet

Research Director Christian Laugier, INRIA, Emotion project, INRIA Rhône-Alpes, 655 Avenue de l'Europe, 38334 Saint Ismier Cedex, France, Phone: +33 4 7661 5222, Fax : +33 4 7661 5477, Email: Christian.Laugier@inrialpes.fr,
Home page: http://emotion.inrialpes.fr/laugier

Professor Urbano Nunes, Department of Electrical and Computer Engineering of the Faculty of Sciences and Technology of University of Coimbra, 3030-290 Coimbra, Portugal, GABINETE 3A.10, Phone: +351 239 796 287, Fax: +351 239 406 672, Email: urbano@deec.uc.pt,
Home page: http://www.isr.uc.pt/~urbano

Professor Christoph Stiller, , Institut für Mess- und Regelungstechnik, Karlsruher Institut für Technologie (KIT), Engler-Bunte-Ring 21, Gebäude: 40.32, 76131 Karlsruhe, Germany, Phone: +49 721 608-42325 Fax: +49 721 661874, Email: stiller@kit edu
Home page: http://www.mrt.kit.edu/mitarbeiter_stiller.php

General Scope

The purpose of this workshop is to discuss topics related to the challenging problems of autonomous navigation and of driving assistance in open and dynamic environments. Technologies related to application fields such as unmanned outdoor vehicles or intelligent road vehicles will be considered from both the theoretical and technological point of views. Several research questions located on the cutting edge of the state of the art will be addressed. Among the many application areas that robotics is addressing, transportation of people and goods seem to be a domain that will dramatically benefit from intelligent automation. Fully automatic driving is emerging as the approach to dramatically improve efficiency while at the same time leading to the goal of zero fatalities. This workshop will address robotics technologies, which are at the very core of this major shift in the automobile paradigm. Technologies related to this area, such as autonomous outdoor vehicles, achievements, challenges and open questions would be presented.

Main Topics

  • Road scene understanding
  • Lane detection and lane keeping
  • Pedestrian and vehicle detection
  • Detection, tracking and classification
  • Feature extraction and feature selection
  • Cooperative techniques
  • Collision prediction and avoidance
  • Advanced driver assistance systems
  • Environment perception, vehicle localization and autonomous navigation
  • Real-time perception and sensor fusion
  • SLAM in dynamic environments
  • Mapping and maps for navigation
  • Real-time motion planning in dynamic environments
  • Human-Robot Interaction
  • Behavior modeling and learning
  • Robust sensor-based 3D reconstruction
  • Modeling and Control of mobile robot
  • International Program Committee

  • Philippe Bonnifait (Heudiasyc, UTC, France)
  • Alberto Broggi (VisLab, Parma University, Italy)
  • Paul Furgale (ETH Zurich, Switzerland)
  • Zhencheng Hu, (Kumamoto University, Japan)
  • Javier Ibanez-Guzman (Renault, France)
  • Christian Laugier (Emotion, INRIA, France)
  • Philippe Martinet (IRCCYN, Ecole Centrale de Nantes, France)
  • Urbano Nunes (Coimbra University, Portugal),
  • Anya Petrovskaya (Stanford University, USA)
  • Cedric Pradalier (GeorgiaTech Lorraine, France)
  • Christoph Stiller (Karlsruhe Institute of Technology, Germany)
  • Rafael Toledo Moreo (Universidad Politécnica de Cartagena, Spain)
  • Sebastian Thrun (Stanford University, USA)
  • Ming Yang (SJTU Shanghai, China)
  • Young-Woo SEO (CMU, USA)
  • Final program

    Introduction to the workshop 8:20

    Session I: Localization & mapping 8:30


    Chairman: C. Stiller (KIT, Germany)
    • Title: Automated driving in urban environments: car sharing distribution system and Parking Valet as canonical use-cases 8:30
      Keynote speaker: Fawzy Nashashibi (INRIA, Rocquencourt, France) 35min + 5min questions


      Abstract: In September 2014, the French high authorities announced the creation of an ambitious plan to support the industrialization of France around 34 challenging industrial domains. Among these topics: “robotics” and “vehicles with automated driving”. This initiative is part of an international effort to develop automated driving before 2020. Automated driving in urban environments is particularly very challenging because of the technical challenges and legal limitations. In the meanwhile business models are limited due to these obstacles. In these conditions the automated distribution of a car-sharing system and a “Parking valet” system seem to be interesting use-cases because of the constrained environments in which vehicle navigation is performed while private areas as well as segregated lanes can offer a good solution to remove the legal barriers. From a pure technical point of view, “automated car-sharing distribution system” and “Parking valet” are interesting applications where different automated navigation functions and intelligent mobility concepts cohabit in order to provide a practical service to different end users. This talk will tackle the technical requirements to realize such services. Platooning, automated parking, accurate localization and environments mapping are among the automated functions to integrate. We will describe these advanced functions and their integration in this very specific framework. A first prototyping of such systems on automated vehicles will be presented as well as future developments and perspectives.

    • Title: An Iterative Graph Optimization Approach for 2D SLAM 9:10
      Authors: He Zhang, Guoliang Liu, and Zifeng Hou 17min + 3min questions

      Presentation, Paper

      Abstract: The-state-of-the-art graph optimization method can robustly converge into a solution with minimum overall error for the graph structure. Nevertheless, when a biased edge (erroneous transformation with high certainty information matrix or verse vice) exists, the optimal solution can produce the large deviation because of error propagation produced by the biased edge. In order to solve this problem, this paper proposed an iterative graph optimization approach for 2D SLAM. In each iteration, we optimize the graph using a standard nonlinear method and then rebuild the structure of the graph. To maintain the information in the ”good” (well estimated) edges and update the information in the ”bad” (biased estimated) edges, we strictly reconstruct the graph structure by considering the scancorrelation score and the marginal covariance. In addition, we heuristically detect the loop-closure and recalculate the transformations in edges by a marginal covariance inferred interpolation algorithm. This iterative process stops when the total square error over the graph varies little or the number of iterations exceeds a predefined constant. The experiments show that the proposed method is more robust and accurate than the previous methods when the biased edges exist.

    • Title: Appearance-based Localization across Seasons in a Metric Map 9:30
      Authors: Chris Beall, Frank Dellaert 17min + 3min questions

      Presentation, Paper

      Abstract: In this paper we address the problem of appearance-based long-term outdoor localization across sea-sons. This is a dif?cult task due to the changing appearance of visual landmarks across seasons and time of day. Our approach operates based on the premise that combining visual landmarks observed at different times of the year into a single metric map will yield better localization results than a map created from a single sequence alone. We integrate stereo imagery collected at two different times of the year into a unified 3D map, and use this as the basis for localization. A landmark visibility prediction framework is utilized to efficiently retrieve a small subset of landmarks and their feature descriptors from a database of millions of landmarks. The proposed approach is experimentally validated on a challenging sequence collected a year earlier.

    • Title: High Precision 6DOF Vehicle Navigation in Urban Environments using a Low-cost Single-frequency GPS Receiver 9:50
      Authors: Sheng Zhao; Yiming Chen, Jay A. Farrell 17min + 3min questions


      Abstract: Many advanced driver assistance systems (ADAS) demand for high precision navigation in urban environments. Traditional high precision dual-frequency RTK GPS receivers are too expensive for the low-cost, massive produced consumergrade applications. On the other hand, many potential applications will become feasible as the high precision navigation solution becomes affordable using low-cost sensors. Hence, this paper proposed a high precision global navigation system using the low-cost single frequency GPS receiver and MEMS inertial measurement unit (IMU), with the application in GPS challenged urban environments. By utilizing a sliding-window smoothing estimator, we are able to demonstrate reliable decimeter positioning accuracy in the presence of severe mutlipath errors and intermittent GPS signal receptions. To the best of the authors’ knowledge, this is the first literature report of a high performance sliding window smoothing estimator on tightly coupled Differential-GPS/IMU using L1-only measurements in a GPS-challenged urban environment.

    Coffee Break 10:10

    Session II: Perception and Situation Awareness 10:30
    Chairman: C. Laugier (INRIA, France)
    • Title: Situation Perception and Prediction for Autonomous Driving 10:30
      Keynote speaker: Chritoph Stiller (KIT, Karlsruhe, Germany) 35min + 5min questions
      Co-Authors: Julius Ziegler, Markus Schreiber, Philipp Bender


      Abstract: Vehicle environment perception and to prediction of potential motion of relevant traffic participants is a crucial task for autonomous driving. The contribution of this presentation includes the following aspects. First, we extend the current state of the art in robotic vehicles that require expensive on-roof sensors and GNSS navigation. Instead, we propose signal processing methods that enable us to restrict ourselves to close-to-market sensor configurations. Dominated by vision sensors, we outline vehicle environment perception and scene prediction that enables us to automatically navigate through everyday's traffic. Methods for 3D visual machine perception based mono- and binocular video sensors are presented. The contribution of prior knowledge from digital maps is elaborated as well as its curse in case of erroneous information. Real-time automated decision-making and trajectory planning methods are outlined. Trajectory planning is not only conducted for our ego-trajectory, but we argue that planning of trajectories of other traffic participants is crucial for safe navigation. Extensive results of automated driving are shown in real world scenarios from our AnnieWAY vehicle, the winner of the 2011 Grand Cooperative Driving Challenge, and from the Bertha vehicle that drove autonomously on the Bertha Benz memorial route from Mannheim to Pforzheim through a highly populated area of Germany.

    • Title: Detection and Tracking of the Vanishing Point on a Horizon for Automotive Applications 11:10
      Authors: Young-Woo Seo, Ragunathan Rajkumar 17min + 3min questions

      Presentation, Paper

      Abstract: In advanced driver assistance systems and autonomous driving vehicles, many computer vision applications rely on knowing the location of the vanishing point on a horizon. The horizontal vanishing point’s location provides important information about driving environments, such as the instantaneous driving direction of roadway, sampling regions of the drivable regions’ image features, and the search direction of moving objects. To detect the vanishing point, many existing methods work frame-by-frame. Their outputs may look desirable in that frame. Over a series of frames, however, the detected locations are inconsistent, yielding unreliable information about roadway structure. This paper presents a novel algorithm that, using line segments, detects vanishing points in urban scenes and, using Extended Kalman Filter (EKF), tracks them over frames to smooth out the trajectory of the horizontal vanishing point. The study demonstrates both the practicality of the detection method and the effectiveness of our tracking method, through experiments carried out using hundreds of urban scene images.

    • Title: Robot Navigation Using Radio Signal in Wireless Sensor Networks 11:30
      Authors: Ju Wang, Mohammad M Tabanjeh, Tariq Qazi, Brian Bennett, Cesar Flores-Montoya, Eric Glover, Meesha Rashidi 17min + 3min questions

      Presentation, Paper

      Abstract: We investigate a wireless sensor locating and navigation method to navigate a land robot in a Wireless Sensor Network (WSN) to perform maintainance works. Our proposed method is based on distributed RF sensing with the aid of directional antenna. Our method only require partial and coarse RF profiling of the interested area. Another advantage is that it does not require knowledge of the locations of the beacon nodes. In 2D navigation, the directional RSS measurements allow us to achieve location accuracy beyond the grid resolution of the partial RF profile. The robot is able to navigate within 2 feet from the target sensor in

    Lunch break 11:50

    Session III: Interactive session 13:30
    Chairman: P. Martinet (IRCCyN, France)
    • Title: Task and motion plannig for Selective Weed Conrol using a Team of Autonmous Vehicles
      Authors: I.A. Hameed, A. la Cour-Harbo, K.D. Hansen


      Abstract: Conventional agricultural fields are sprayed uniformly to control weeds, insects, and diseases. To reduce expenses, produce a higher and healthy yield and to create a more environmentally friendly farm, chemicals should only be applied to the right place and exactly with the right amount. In this article, a task and motion planning for a team of autonomous vehicles to reduce chemicals in farming is presented. Field data are collected by a small unmanned helicopters equipped with a range of sensors, including multispectral and thermal cameras. Data collected are transmitted to a ground station, which analyses the data and triggers aerial and ground-based vehicles to start close inspection and plant treatment in specified areas. A complete trajectory is generated to enable ground-based vehicle to visit infested areas and start chemical/mechanical weed treatment.

    • Title: Remaining Range Indicator System for Electric Vehicle
      Authors: R. Potarusov, I. Kobersy, J.-P. Lebacque


      Abstract: This paper presents a Breadth-First Search-based Indicator System for remaining range estimation and representation in battery electric vehicle driving range indicators. The representation enables detailed illustration of electric vehicle’s “distance to empty”. To build up a remaining range graph the Breadth-First Search (BFS) algorithm is coupled with a simple electric energy consumption model taking into account the driver-desired speed, road data in a near horizon (route network topology, legal speed, grade and grip), ambient temperature, headwind speed and state of charge of electric battery. The presented study focuses on investigation of the effect of the ambient temperature variations on the vehicle remaining range. Simulation results clearly show an increased energy requirement at low temperature resulting in a reduction of the vehicle range.

    • Title: Landmark Discovery for Single-View Cross-Season Localization
      Authors: Ando Masatoshi, Chokushi Yuuto, Tanaka Kanji


      Abstract: We tackle a challenging task of single-view crossseason localization. The main problem we face is how to obtain discriminative and compact visual landmarks, which are necessary to cope with changes in appearance in an environment. We address this issue by proposing the use of raw image matching, a known best discriminative method for scene matching, which is contrastive to popular bag-of-words methods which rely on vector quantized visual features. A direct implementation of raw image matching can be time / space intractable due to the high dimensionality of raw image data. We propose to exploit raw image matching, not for the direct matching between query and database images, but for mining an available visual experience to find discriminative visual landmarks. The result is a bounding box -based scene descriptor that crops the mined landmark objects with respect to the visual experience. We develop a practical localization system, by employing both efficient and reliable subsystems for raw image matching, including RANSAC geometric verification, common pattern discovery, and approximate near neighbor search. Experimental results show that our proposed framework tends to produce stable localization results despite the fact that our scene descriptor is significantly space / time efficient.

    • Title: Obstacle Detection and Avoidance from an Automated Guided Vehicle
      Authors: Roger Bostelman, Will Shackleford, Geraldine Cheok


      Abstract: Current automated guided vehicle (AGV) technology typically provides material handling flow along single or dual opposing-flow lanes in manufacturing and distribution facilities. An AGV stops for most any obstacle that may be in its path which then halts other AGVs behind it until the obstacle is removed. An alternative to serial AGV flow is to provide parallel flow in particular areas, such as buffer zones and appropriate lanes where a stopped AGV can be passed by other AGVs. This paper describes two obstacle detection and avoidance (ODA) methods developed and tested. These methods will allow current off-the-shelf AGVs to advance towards unstructured environment navigation.

    • Title: Frontier Based Exploration with Task Cancellation
      Authors: P.G.C.N. Senarathne, Danwei Wang


      Abstract: Classical frontier based exploration strategies operate by iteratively selecting the next best sensing location myopically and moving to the specified location, until the entire environment is explored. And it does not consider the new information added to the map through continuous observations by the robot along the way to a selected location. This can sometimes lead to redundant traversal by the robot, such as traveling towards a dead-end when the nearby area is already mapped. In this work, we augment the classical frontier based exploration strategy to include a probabilistic decision step that decides whether further motion on the planned path is desirable or not. If the motion is not desirable, it is interrupted and a new sensing location is selected as the next sensing task. Experiments were conducted using a Pioneer 3AT robot to explore an indoor environment and is demonstrated that the proposed method on average is capable of exploring environments more efficiently.

    • Title: A Pareto Front-Based Multiobjective Path Planning Algorithm
      Authors: Alexander Lavin


      Abstract: Path planning is one of the most vital elements of mobile robotics. With a priori knowledge of the environment, global path planning provides a collision-free route through the workspace. The global path plan can be calculated with a variety of informed search algorithms, most notably the A* search method, guaranteed to deliver a complete and optimal solution that minimizes the path cost. Path planning optimization typically looks to minimize the distance traversed from start to goal, but many mobile robot applications call for additional path planning objectives, presenting a multiobjective optimization (MOO) problem. Past studies have applied genetic algorithms to MOO path planning problems, but these may have the disadvantages of computational complexity and suboptimal solutions. Alternatively, the algorithm in this paper approaches MOO path planning with the use of Pareto fronts, or finding non-dominated solutions. The algorithm presented incorporates Pareto optimality into every step of A* search, thus it is named A*-PO. Results of simulations show A*-PO outperformed several variations of the standard A* algorithm for MOO path planning. A planetary exploration rover case study was added to demonstrate the viability of A*-PO in a real-world application.

    Session IV: Navigation, Control, Planning 14:30
    Chairman: F. Nashashibi (INRIA, France)
    • Title: Formulation, Calibration, and Uses of Constrained Kinematic Models for WMRs 14:30
      Keynote speaker: Alonzo Kelly (Robotics Institute, CMU, Pittsburgh, Pennsylvania, USA) 35min + 5min questions
      Co-Author: Neal Seegmiller

      Presentation, Paper

      Abstract: Recent work on wheeled mobile robot modeling enables a purely kinematic representation of such effects as suspension, wheel slip, and terrain following contact. Such models are relevant to high speed on-road or rough terrain off-road situations and they present compelling advantages in terms of higher estimation and prediction accuracies for less computation, or both. This talk will show results for how such models can be calibrated on-line in real time and how they can be used to improve solutions to state estimation, adaptive control, predictive control, trajectory generation, and motion planning.

    • Title: Modified flatbed tow truck model for stable and safe platooning in presences of lags, communication and sensing delays 15:10
      Authors: A. Ali, G. Garcia, P. Martinet 17min + 3min questions

      Presentation, Paper

      Abstract: Many ideas have been proposed to reduce traffic congestion problems. One of the proposed ideas is driving in platoon. Constant spacing policy is the most important policy. It increases traffic density, but it has been proved that the platoon becomes un stable even for small communication delays. Driving with constant time headway between vehicle is also well known policy and robust control law but the inter-vehicle distances are very large. We have proposed a modification for the constant time headway policy. This modification reduces the inter-vehicle distances largely using only one information shared between all vehicle. In this work we propose an additional modification of our control law. This modification makes our control law similar to classical constant spacing policy, using only the same shared information. This modification improves the stability of the platoon.We proved the robustness of the control law in presence of parasitic actuating lags, sensing and communication delays. This prove can be also used for proving the stability of classical spacing policy in presence of all previous delays, contrary to what have been proved in some papers in the literatures.

    • Title: Global Robot Ego-localization Combining Image Retrieval and HMM-based Filtering 15:30
      Authors: Cedric Le Barz, Nicolas Thome, Matthieu Cord, Stephane Herbin, Martial Sanfourche 17min + 3min questions

      Presentation, Paper

      Abstract: This paper addresses the problem of global visual ego-localization of a robot equipped with a monocular camera that has to navigate autonomously in an urban environment. The robot has access to a database of geo-referenced images of its environment and to the outputs of an odometric system (Inertial Measurement Unit or visual odometry). The goal of the approach described and evaluated in this paper is to exploit a Hidden Markov Model (HMM) to combine the localization estimates provided by the odometric system and the visual similarities between acquired images and the geo-localized image database. It is shown that the use of spatial and temporal constraints reduces the mean localization error from 16 m to 4 m over a 11 km path evaluated on the Google Pittsburgh dataset when compared to an image based method alone.

    Coffee break 15:50

    Panel Session: Towards driverless vehicles ? 16:20
    Chairman: C. Laugier


    • Abstract: The purpose of this panel session is to discuss the hot topics of "Advanced Driving Assistance Systems" and of "Driverless Vehicles". All the related Technical, Socio-economic and Legal issues will be addressed and discussed.
      Participant: Seiichi Mita (Toyota Technological Institute Nagoya, Japan)
      Participant: Fawzi Nashashibi (INRIA, France) Presentation
      Participant: Christoph Stiller (KIT, Germany)

    Closing 17:00
    Author Information

      Format of the paper: Papers should be prepared according to the IROS14 final camera ready format and should be 4 to 6 pages long. The detailed information on the paper format is available from the IROS14 page. http://www.iros2014.org/contributing/instructions-for-authors. Papers must be sent to Philippe Martinet by email at Philippe.Martinet@irccyn.ec-nantes.fr

      Important dates (preliminary)

      • Deadline for Paper submission: May 31 th -Postpone to June 12th), 2014
      • Acceptance with review comments: June 15th, 2014
      • Deadline for final paper submission: June 30th, 12am at last, 2014

      Talk information

      • Invited talk: 40 min (35 min talk, 5 min question)
      • Other talk: 20 min (17 min talk, 3 min question)

      Interactive session

      • Interactive and open session: 1h00

    Previous workshops

      Previously, several workshops were organized in the near same field. The 1st edition PPNIV'07 of this workshop was held in Roma during ICRA'07 (around 60 attendees), the second PPNIV'08 was in Nice during IROS'08 (more than 90 registered people), the third PPNIV'09 was in Saint-Louis (around 70 attendees) during IROS'09, the fourth edition PPNIV'12 was in Vilamoura (over 95 attendees) during IROS'12, and the fifth edition PPNIV'13 was in Tokyo (over 135 attendees) during IROS'13.
      In parallel, we have also organized SNODE'07 in San Diego during IROS'07 (around 80 attendees), SNODE'09 in Kobe during ICRA'09 (around 70 attendees), and RITS'10 in Anchrorage during ICRA'10 (around 35 attendees), and the last one PNAVHE11 in San Francisco during the last IROS11 (around 50 attendees).

      Special issues have been published in IEEE Transaction on ITS (Car and ITS applications, September 2009), and in IEEE-RAS Magazine (Perception and Navigation for Autonomous Vehicles, March 2014). We are preparing a new special issue on Perception and Planning for Autonomous Vehicles in ITS Magazine.


      Proceedings: The workshop proceedings will be published within the IROS Workshop/Tutorial CDROM and electronically as a pdf file.

      Special issue: Selected papers will be considered for a special issue in the IEEE Intelligent Transportation Systems Magazine in connection with this workshop. We will issue an open call, submissions will go through a separate peer review process.