2014 IEEE International Conference on Robotics and Automation

ICRA14 Workshop on Modelling, Estimation, Perception and Control of All Terrain Mobile Robots

Full Day Workshop, Track T11, Room 425, 8:25-17:30

June 1st, 2014, Hong-Kong, China

Workshop Proceedings

Contact : Professor Philippe Martinet
IRCCyN-CNRS Laboratory, Ecole Centrale de Nantes,
Email: Philippe.Martinet@irccyn.ec-nantes.fr,
Home page: http://www.irccyn.ec-nantes.fr/~martinet

Final program

Introduction to the workshop 8:25

Session I: Enhanced mobility & Modeling 8:30
Chairman: Kasuya Yoshida (Tohoku University, Japan)

  • Invited Talk: Genya Ishigami (Dept. of Mechanical Engineering, Keio University, Japan)
    Invited Talk: Rough Terrain Mobility: key issues and approaches for dynamics simulation of rough terrain mobile robot
    Keynote speaker: Genya Ishigami (Dept. of Mechanical Engineering, Keio University, Japan) 35min + 5min questions
    Presentation Video1, Video2, Video3, Video4, Video5, Video6, Video7, Video8, Video9, Video10, Video11, Video12, Video13

    Abstract: Rough-terrain mobile robots are always subject to complicated dynamic interaction between their running gears (tire, wheel, or track) and ground. A well-defined mechanics for the robot-terrain interaction is of importance to the following technical aspects of the mobile robot: (1) mobility analysis such as slope traversability or obstacle crossing; (2) robot navigation, planning, and traction control; and (3) design of vehicle dimensions, suspension, and actuators. This presentation focuses on a topic related to a dynamics simulation of rough-terrain mobile robot using wheel contact mechanics. An overview of research and development of the dynamics simulation are described along with its application to mobility analysis, control, and design. In the presentation, typical issues and key approaches towards a next generation of dynamics simulation tools for rough-terrain mobile robot are also discussed.

  • Regular Talk: Analyzing the Impact of Learning Inputs on Near-to-Far Terrain Traversability Estimation 9:10
    Authors: K. Ho, T. Peynot and S. Sukkarieh 15min + 3min questions
    Paper, Presentation

    Abstract: With the increasing need to adapt to new environments, data-driven approaches have been developed to estimate terrain traversability by learning the roverís response on the terrain based on experience. Multiple learning inputs are often used to adequately describe the various aspects of terrain traversability. In a complex learning framework, it can be difficult to identify the relevance of each learning input to the resulting estimate. This paper addresses the suitability of each learning input by systematically analyzing the impact of each input on the estimate. Sensitivity Analysis (SA) methods provide a means to measure the contribution of each learning input to the estimate variability. Using a variance-based SA method, we characterize how the prediction changes as one or more of the input changes, and also quantify the prediction uncertainty as attributed from each of the inputs in the framework of dependent inputs. We propose an approach built on Analysis of Variance (ANOVA) decomposition to examine the prediction made in a near-to-far learning framework based on multi-task GP regression. We demonstrate the approach by analyzing the impact of driving speed and terrain geometry on the prediction of the roverís attitude and chassis configuration in a Marsanalogue terrain using our prototype rover Mawson.

  • Regular Talk: Terrain mapping with a pan and tilt stereo camera for locomotion on a quadruped robot 9:28
    Authors: S. Bazeille, M. Camurri, J. Ortiz, I. Havoutis, D. G. Caldwell, and C. Semini 15min + 3min questions
    Paper, Presentation Video1, Video2, Video3

    Abstract: Legged robots are expected to have superior mobility on rough terrain than wheeled robots. The main reason is that legged locomotion is more adaptable to a wide range of terrain types as the robot can decompose its path into a sequence of footholds and can use different locomotion strategies. In order to accomplish most of the locomotion tasks the robot requires high level control (i.e., to adjust the locomotion parameters and to choose optimal footholds) which depends on real-time localization and accurate terrain mapping. In this paper, we propose a SLAM solution using a pan and tilt stereo camera mounted on an hydraulically actuated quadruped robot that builds a map and keeps track of the robotís position. Since the computation needs to be carried out on board and the robot is subject to considerable motion during its locomotion (regular vibrations, impacts or slippages), we developed a dedicated implementation based on fast stereo depth computation, GPU based map building and mechanical motion compensation. Combined with a foothold planning framework presented in our previous work [1], this localization and mapping ability allows to perform locomotion in a fully planned manner. Successful results of foothold planning with our quadruped robot show the effectiveness of our method.

Session II: Perception in outdoor environment (1/2) 9:46
Chairman: Juan I. Nieto (University of Sydney, Australia)
  • Invited Talk: Paul Furgale (ETH Zurich, Switzerland)
    Invited Talk: There and back again: Dealing with highly-dynamic scenes and long-term change during topological/metric route following 9:46
    Keynote speaker: Paul Furgale (ETH Zurich, Switzerland) 35min + 5min questions
    Co-authors: P. KrŁsi, F. Pomerleau, U. Schwesinger, F. Colas, and R. Siegwart

    Abstract: Topological/metric route following, also called teach and repeat (T&R), enables long-range autonomous navigation even without globally consistent localization. This renders T&R ideal for applications where a global positioning system may not be available, such as navigation through street canyons or forests in search and rescue, reconnaissance in underground structures, surveillance, or planetary exploration. This Talk will present our efforts to develop a T&R system suitable for long-term robot autonomy in highly dynamic, unstructured environments. We use the fast iterative closest point (ICP) algorithms from libpointmatcher (https://github.com/ethz-asl/libpointmatcher) to build a T&R system based on a spinning laser range finder. The system deals with dynamic elements in two ways. First, we employ a system-compliant local motion planner to react to dynamic elements in the scene during route following. Second, the system infers the static or dynamic state of each 3D point in the environment based on repeated observations. The velocity of each dynamic point is estimated without requiring object models or explicit clustering of the points. At any time, the system is able to produce a most-likely representation of underlying static scene geometry. By storing the time history of velocities, we can infer the dominant motion patterns within the map. The result is an online mapping and localization system specifically designed to enable long-term autonomy within highly dynamic environments. We validate the approach using data collected around the campus of ETH Zurich over seven months and at an outdoor 3D test site in Thun, Switzerland.

  • Coffee Break 10:26-10:50

  • Regular Talk: Monocular Vision: A Real-Time Perception Toolkit for Mobile Robots in Outdoor Environments 10:50
    Authors: A. Miranda Neto, A. C. Victorino and J. V. Ferreira 15min + 3min questions
    Paper, Presentation Video1, Video2, Video3, Video4, Video5, Video6, Video7, Video8, Video9

    Abstract: Many applications for control of autonomous platform are being developed and some important aspects are: (a) the estimation of drivable image area and (b) the excess of information, frequently redundant, that imposes a great computational cost in data processing. In this way, we have proposed (i) a robust algorithm for detecting the horizon line to generate (ii) the navigable area. It permits to investigate dynamically only a small portion of the image (road) ahead of the vehicle. Moreover, taking into account the temporal coherence between consecutive frames, we also have proposed a set of tools based on Pearsonís Correlation Coefficient: (iii) a discarding criteria methodology applied as (iv) a dynamic power management solution; (v) an environment observer method which selects automatically only the regions-of-interest; and taking place in the obstacle avoidance context, (vi) a method for collision risk estimation for vehicles in dynamic and unknown environments. Applying the PCC to these tasks has not been done yet, making the concepts unique. All these solutions have been evaluated.

  • Regular Talk: Multiplicative Extended Kalman Filter based on Visual Data for Attitude Estimation 11:08
    Authors: A. Seba, A. El Hadri, L. Benziane, A. Benallegue 15min + 3min questions
    Paper, Presentation

    Abstract: A method for rigid body attitude estimation based on a new feature-tracking algorithm and a Multiplicative Extended Kalman Filter (MEKF) is proposed and developed. The new feature-tracking algorithm allows us to detect and to track the image features (points and lines). This algorithm is able to cancel the drift due to a prediction error accumulation when a long sequence of images is used. Indeed, in this algorithm we have added a correction of the prediction given by optical flow features, using criterion based on Euclidean distance only in the predicted search area. Thus, the extracted points and lines are used as visual data measurements, which enable us to estimate attitude when they are fused with gyros measurements using MEKF. Simulation results has been presented to show the effectiveness of the applied method.

  • Regular Talk: Gradient Based Multi-modal Sensor Calibration 11:26
    Authors: Z. Taylor and J. Nieto 15min + 3min questions
    Paper, Presentation

    Abstract: This paper presents an evaluation of a new metric for registering two sensors of different modality. The metric operates by aligning gradients present in the two sensorsí outputs. This metric is used to find the parameters between the sensors that minimizes the misalignment of the gradients. The metric can be applied to a wide range of problems and has been successfully demonstrated on the extrinsic calibration of two different lidar-camera systems as well as the alignment of IR and RGB images. Unlike many previous techniques, this method requires no markers to be placed in the scene and can operate on a single scan from each sensor.

Lunch 11:44-13:00

Session II: Perception in outdoor environment (2/2) 13:00
Chairman: Juan I. Nieto (University of Sydney, Australia)
  • Invited Talk: Alberto Elfes (CSIRO, Australia)
    Invited Talk: Multi-Modal Robot Perception and Augmented World Models 13:00
    Keynote speaker: Alberto Elfes (Autonomous Systems Lab, CSIRO) 35min + 5min questions

    Abstract: There are tight interrelations between the mobility capabilities of a robotic platform, the exterioceptive sensors it uses, the world models it builds from these sensors, and the tasks that the platform is designed to execute. To date, the primary sources used by mobile robots to learn about their environment have been range sensors. These are used to build static 2D, 2.5D or 3D maps or dynamic 4D world models, which in turn are used for navigation or manipulation. However, as robots are deployed in increasingly more demanding missions in complex natural or artificial environments, they require richer world models with information beyond the spatial structure of their surroundings. This talk will discuss our work in using multiple sensor modalities, including lidar, RGB, thermal, hyperspectral and haptics, to build multi-property augmented world models (AWMs) for a variety of robot platforms and missions. These AWMs range from simple superposition of spatiotemporally registered sensor streams to multi-modal sensor fusion and to active models where inferences in one sensor stream are used to analyze and make inferences in other sensor streams. Results will be shown from domains that include exploration and documentation of natural and cultural sites, as well as in situ sensing for agricultural, environmental and industrial applications.

  • Regular Talk: Localization of Planetary Exploration Rovers with Orbital Imaging: a survey of approaches 13:40
    Authors: E. Boukas, A. Gasteratos and G. Visenti 15min + 3min questions
    Paper, Presentation

    Abstract: Owing to the rovers exploring the surface of Mars being assigned with ever more complex tasks, it is the autonomy of such operations that enables their effective planetary activities. An indicative case of the escalation in requirements is the upcoming Mars Sample Return mission (MSR), which is a joint effort of the National Aeronautics and Space Administration (NASA) and the European Space Agency (ESA). The mission involves a Sample Fetching Rover (SFR) to gather a previously deposited cache of soil that, eventually, will be directed towards Earth. With the aim to retrieve the cache and rendezvous with the Mars Ascent Vehicle (MAV), the rover should be apt to globally localize itself on the Martian surface. Due to the absence of Global Navigation Satellite System (GNSS) on Mars, the most suited approach is the blending of information stemming from ground rovers and orbital imagery. The scope of the paper in hand is to summarize the work delivered so far on the localization of space exploratory rovers based on such information.

  • Regular Talk: A probabilistic distribution approach for the classification of urban roads in complex environments 13:58
    Authors: G. B. Vitor, A. C. Victorino and J. V. Ferreira 15min + 3min questions
    Paper, Presentation Video1, Video2

    Abstract: Navigation in urban environments has been receiving considerable attention over the past few years, especially for self-driving cars. Road detection for Autonomous Systems, and also for ADAS (Advanced Driving Assistance Systems) remains a major challenging in inner-city scenarios motivated by the high complexity in scene layout with unmarked or weakly marked roads and poor lightning conditions. This paper introduces a novel method that creates a classifier based on a set of probability distribution. The classifier, created using a Joint Boosting algorithm, aims at detecting semantic information in roads. This approach is composed of a set of parallel processes to calculate the superpixel using the Watershed Transform method and the construction of feature maps based on Textons and Disptons. As a result, a set of probability distribution is generated. It will be used as an input to model the week classifier by our Joint Boosting algorithm. The experimental results using the Urban-Kitty benchmark are comparable to the state-of-the-art approaches and can largely improve the effectiveness of the detection in several conditions.

Session III: Navigation, Control, Planning 14:16
Chairman: Kasuya Yoshida (Tohoku University, Japan)
  • Invited Talk Canceled: Dimi Apostolopoulos (Carnegie Mellon University, Robotics Institute, USA)
    Invited Talk: Important Considerations in the Design of All-terrain Wheeled Robots 14:16
    Keynote speaker: Dimi Apostolopoulos (Carnegie Mellon University, Robotics Institute, USA) 0 min

    Abstract: Two considerations stand out when designing the locomotion subsystem of all-terrain robots. The first is the ability to handle a variety of ground conditions. The second is the capacity to react to forces generated from the robotís interaction with its environment. A great deal of research and development has been devoted to designing innovative drive, steering, and suspension assemblies that maximize a robot's inherent mobility and terrainability. In this talk, I will discuss key metrics in the design of wheeled robotic locomotion and share lessons and observations from the field validation of advanced robot prototypes that feature all-wheel-drive and simple planar suspension geometries.

  • Regular Talk: A Planner for All Terrain Vehicles on Unknown Rough Terrains based on the MPC Paradigm and D*- like Algorithm 14:56
    Authors: A. Tahirovic, M. Brkic, G. Magnani and L. Bascetta 15min + 3min questions
    Paper, Presentation Video1

    Abstract: A novel conceptual design of a planner for a mobile vehicle, operating on poorly traversable unknown rough terrains, is discussed. Finding a way to include a vehicle model into the planning stage, while coping with unknown or partially known terrains, is a challenging and rarely addressed optimization setup. The main advantages of a possible solution of such a problem would be twofold. First, the planner would give trajectories which are feasible to follow by the vehicle, which is not the case in many other state of the art planning algorithms especially for large vehicle speeds. Second, those trajectories would be the optimal ones in accordance to the current vehicle states and knowledge on its environment. We propose a solution based on an MPC planning paradigm, wherein the planner solves a constrained optimal control problem at each time instant using the current knowledge on the terrain, which is caught appropriately by an objective function. Solving an optimal control problem allows for the vehicle model being included into the planning stage, while the repeated optimization allows for taking continuously into account new terrain information. To deal with the information given beyond the sensor range and to guarantee reaching a given goal position, we have adopted a D*-like algorithm for rough terrains being used as a cost-to-go term within the optimization setup.

  • Regular Talk: An image based dynamic window approach for local navigation of an autonomous vehicle in urban environments 15:14
    Authors: D. Alves de Lima and A. Correa Victorino 15min + 3min questions
    Paper, Presentation Video1, Video2, Video3, Video4, Video5, Video6

    Abstract: This paper presents a local navigation strategy for autonomous vehicles in urban environments with an Image Based Dynamic Window Approach (IDWA). Differently from the global navigation techniques, which requires the vehicle localization to perform its movement, the focus here was to solve the navigation problem in local navigation steps. For that, the environment features will be used, performing the road lane following e.g. The DWA performs a reactive obstacle avoidance while trying to reach a goal destination. In this case, reach the goal destination is based on the Image Based Visual Servoing equations for road lane following, which were incorporated into the DWA. The final solution takes into account the car kinematics/dynamics constraints to allow the vehicle to follow the road lane while avoiding obstacles. The results show the viability of the proposed methodology.

    Coffee Break 15:32-15:52

  • Regular Talk: Towards Lifelong Learning of Optimal Control for Kinematically Complex Robots 15:52
    Authors: A. Dettmann, M. Langosz, Kai von Szadkowski, and S. Bartsch 15min + 3min questions
    Paper, Presentation

    Abstract: Robots intended to perform mobile manipulation in complex environments are commonly equipped with an extensive set of sensors and motors, creating a wide range of perception and interaction capabilities. However, to exploit all theoretically possible abilities of such systems, a control strategy is required that allows to determine and apply the best solution for a given task within an appropriate time frame. In this paper, a lifelong self-improving control scheme for kinematically complex robots is presented, which uses simulation-based behavior generation and optimization procedures to create a library of well-performing solutions for varying tasks and conditions, and combines it with case-based selection, evaluation, and online adaptation methods.

Session IV: Cooperative Robots, Software architecture 16:10
Chairman: Philippe Martinet (IRCCyN, France)
  • Invited Talk: Roland Lenain (IRSTEA, France)
    Invited Talk: Formation control of off-road fleet of UGVs: issues, advances and applications 16:10
    Keynote speaker: Roland Lenain (IRSTEA, France) 35min + 5min questions
    Presentation Video1, Video2, Video3, Video4, Video5, Video6, Video7, Video8, Video9, Video10, Video11
    Co-authors: Audrey Guillet, Benoit Thuilot, Christophe Cariou

    Abstract: The control of several mobile robots in a coordinated global motion has several potential applications, especially in an off-road context: defense, environment monitoring or agriculture... Nevertheless, despite the important progress in robotics and autonomous driving, some key issues are still challenging and subjected to development. In particular, the varying conditions encountered in natural environment, influences perception, communications and robot dynamics, and have then to be addressed. The needed accuracy, reliability and safety indeed require developing and using robust and adaptable control architecture. This talk first introduces to problems arising in off-road context when achieving the control of several robots in cooperation. Some control strategies and ongoing development are then presented in order to preserve the accuracy and reliability. Experimental illustrations permit to consider short and long term applications. Finally, open issues and perspectives close the talk.

  • Regular Talk: Integrating ABSYNTHE autonomous navigation system into ROS 16:50
    Authors: A. Llamazares, E. Molinos, M. Ocana and F. Herranz 15min + 3min questions
    Paper, Presentation Video1, Video2, Video3

    Abstract: ABSYNTHE, which stands for Abstraction, Synthesis, and Integration of Information for Human-Robot Teams, is an interdisciplinary project which aims to develop basic concepts and structures for the abstraction of partial views of the environment and the actions and intentions of teams, as well as the integration of this information into situation assessments. One of our key objectives with this project is to develop the autonomous navigation system to be used in different platforms (big all terrain outdoor and small indoor robots) that can contain a variety of heterogeneous sensors. It represents a challenging topic because we have to develop a robust and safety navigation system that can be used by these different robots. The goal of this paper is to show the integration of the navigation system into Robot Operating System (ROS)

  • Regular Talk: The Artemis Rover as an Example for Model Based Engineering in Space Robotics 17:08
    Authors: J. Schwendner,T. M. Roehr, S. Haase, M. Wirkus, M. Manz, S. Arnold and J. Machowinski 15min + 3min questions
    Paper, Presentation

    Abstract: Future application of robotic missions in the space context will require the systems to have both mobility and manipulation capabilities. The limited direct communication with the systems due to visibility, and severe time delays also make it a requirement for the system to perform its actions mainly autonomously. The increasing complexity of the task, as well as the strict requirements for reliability and fault tolerance pose a significant challenge to both engineering and research activities. The SpaceBot Cup was held in November 2013 to probe those capabilities in the context of a competition. In this paper we present the Artemis rover and its software architecture as well as the competition results and lessons learned. Special attention is given to the modular design based on the Robot Construction Kit (Rock) framework Ė a component based software framework, which uses a component model based on the Orocos Real-Time-Toolkit (RTT).

Closing 17:26
Author Information

    Format of the paper: Papers should be prepared according to the ICRA14 final camera ready format and should be 4 to 6 pages long. The detailed information on the paper format is available from the ICRA14 page. http://www6.cityu.edu.hk/icra2014/paper_submission.htm. Papers must be sent to Philippe Martinet by email at Philippe.Martinet@irccyn.ec-nantes.fr

    Important dates

    • Deadline for Paper submission: February 28th, 2014
    • Acceptance with review comments: March 15th, 2014
    • Deadline for final paper submission: March 31th, 12am at last, 2014

    Talk information

    • Invited Talk: 40 min (35 min Talk, 5 min question)
    • Regular Talk: 18 min (15 min Talk, 3 min question)


Professor Philippe Martinet, IRCCyN-CNRS Laboratory, Ecole Centrale de Nantes, 1 rue de la NoŽ, 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 Kasuya Yoshida, Space Robotics Lab, Department of Aeronautics and Space Engineering, Tohoku University, Aoba 01, Sendai 980-8579, Japan Phone: +81 (22) 217-6992, Fax : + 81 (22) 795-6993, Email: yoshida@astro.mech.tohoku.ac.jp,
Home page: http://db.tohoku.ac.jp/whois/e_detail/da1574fdf8452accf00e06c018e31523.html

Professor Marcel Bergerman, Robotics Institute, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh PA 15213-3890 Phone: +1 (412) 513-6110 Fax : +1 412-206-0828, Email: marcel@cmu.edu,
Home page: http://www.cs.cmu.edu/~mbergerm/

General Scope

In robotics research, autonomy has presented a long standing challenge on many fronts, particularly for motion control. Mobile robot autonomy is dependent on a variety of technological solutions and their integration. Some key areas include enhanced traction methods, outdoor perception, localization, map building, obstacle avoidance, safety, maintenance etc. Great effort and resources have already been invested worldwide to develop such technologies to enable the autonomy of mobile robots. This workshop will focus on state-of-the-art developments in modeling, perception, estimation and control of all-terrain mobile robots. Mobility in outdoor unstructured environments remains a critical technology where many interesting research topics must be addressed. Precise modeling and estimation of the contact between tire and ground, localization and mapping in unstructured environment, robustness to the uncertainties of parameters and precise trajectory tracking in dynamic environment represent challenging issues for our scientific community. The proposed workshop will summarize existing results, exchange ongoing research and address future directions in these diverse areas.

Main Topics

  • Detection, tracking and classification
  • Feature extraction and feature selection
  • Cooperative techniques
  • Collision prediction and avoidance
  • Environment perception
  • Robot localization
  • Autonomous navigation
  • Real-time perception and sensor fusion
  • SLAM in dynamic environments
  • Mapping and maps for navigation
  • Real-time motion planning in dynamic Environments
  • 3D Mapping, traversability
  • Robust sensor-based 3D reconstruction
  • Modeling and Control of mobile robot
  • Trajectory/object tracking in hard conditions
  • Machine Vision for Outdoor Environment
  • 3D Sensing and Reconstruction of Outdoor Environment
  • Robotics for Fruit/Vegetable production
  • Guidance in Orchard Environment
  • Sensing in partially cluttered partially structured environments
  • Kinematic slip modeling and slip estimation
  • Path tracking and control methods
  • Off-road mobile robot control
  • Mobile robot safety (integrity, traversability, stability)
  • Low cost localization system
  • Multi autonomous vehicles studies, models, techniques and simulations
  • International Program Committee

  • Sunil Agrawal (Columbia University, USA)
  • Faiz Ben Amar (ISIR, France)
  • Marcel Bergerman(CMU, USA)
  • John Billingsley (USQ, Autralia)
  • Wang Han (NTU, Singapore)
  • Karl Iagnemma (MIT, USA)
  • Roland Lenain (IRSTEA, France)
  • Philippe Martinet (IRCCyN, Ecole Centrale de Nantes, France)
  • Cedric Pradalier, (Georgiatech, France)
  • Paul Furgale (ETH Zurich, Switzerland)
  • Kasuya Yoshida (Tohoku Univ., Japan)
  • Danwei Wang (NTU, Singapore)
  • Previous workshops

      Previously, several workshops were organized in the near same field but dedicated

      • to Space : Planetary Rovers workshop was organized in Anchorage during ICRA10, Space Robotics workshop was organized in Shanghai during ICRA11, Planetary Rovers workshop was organized in Karlsruhe during ICRA13,
      • to agriculture : Autonomous Agriculture was organized in Kobe during ICRA'09, Agricultural Robotics: Enabling Safe, Efficient, Affordable Robots for Food Production was organized in Vilamoura during IROSí12,
      • to AGV & ITS: MEPPC08 was organized in Nice during IROSí08 (more than 60 registered people), SNODE'09 in Kobe during ICRA'09 (around 70 attendees), and RITS'10 in Anchrorage during ICRA'10 (around 35 attendees),

      A special issue in International Journal of Fields Robotics, mainly focused on Vehicle-terrain interactions for mobile robots, has been published in march 2010. The best papers of the present workshop proposal will be pushed to be extended and published in a special issue that we will initialized in 2014.

      Proceedings: The workshop proceedings will be published within the ICRA14 Workshop/Tutorial CDROM and electronically as a pdf file.

      Special issue: Selected papers will be considered for a special issue in the International Journal of Fields Robotics in connection with this workshop. We will issue an open call, submissions will go through a separate peer review process.