Presentations PDF Print E-mail

IROS 2015: Presentation of our papers Dynamic obstacles detection and 3D map updating and Rigid tool affordance matching points of regard.

The 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2015) is being held these days (September 28 - October 2, 2015) in Hamburg, Germany . The members of ALCOR Lab are presenting the papers Dynamic obstacles detection and 3D map updating and Rigid tool affordance matching points of regard (Workshop "Learning Object Affordances: a fundamental step to allow prediction, planning and tool use?). The paper abstracts are presented below.

Dynamic obstacles detection and 3D map updating

Abstract: We present a real time method for updating a 3D map with dynamic obstacles detection. Moving obstacles are detected through ray-casting on spherical voxelization of point clouds. We evaluate the accuracy of this method on a point cloud dataset, suitably constructed for testing ray- surface intersection under relative motion conditions. Moreover, we show the benefits of the map updating in a real robot equipped with a rotating LIDAR system, navigating in real world scenarios, populated by moving people.

 

Rigid tool affordance matching points of regard

Abstract: In this abstract we briefly introduce the analysis of simple rigid object affordance by experimentally establishing the relation between the point of regard of subjects before grasping an object and the finger tip points of contact once the object is grasped. The analysis show that there is a strong relation between these data, in so justifying the hypothesis that people figures out how objects are afforded according to their functionality.

 

 


 

RSS 2015 Workshop: Learning for Visual and Tactile Interaction. Presentation of our paper Dynamic contact sensing for articulated tracked vehicles.

The 2015 Robotics: Science and Systems Conference (RSS 2015) will be held between July 13 and 17, 2015 in Rome, Italy. The assistant professor and member of ALCOR Lab Mario Gianni will present the paper Dynamic contact sensing for articulated tracked vehicles , co-authored with Fiora Pirri and Manuel Ruiz, at the Workshop Learning for Visual and Tactile Interaction.


GRAPP 2015: Presentation of our paper Point Cloud Structural Parts Extraction based on Segmentation Energy Minimization.

The 10th International Conference on Computer Graphics Theory and Applications (GRAPP 2015) has been held between March 11 and 14, 2015 in Berlin, Germany. The member of ALCOR Lab and Ph.D. student Valsamis Ntouskos has presented the paper Point Cloud Structural Parts Extraction based on Segmentation Energy Minimization, co-authored with Bruno Cafaro, Fiora Pirri, Manuel Ruiz and Iman Azimi. The paper abstract is presented below.

Abstract: In this work we consider 3D point sets, which in a typical setting represent unorganized point clouds. Segmentation of these point sets requires first to single out structural components of the unknown surface discretely approximated by the point cloud. Structural components, in turn, are surface patches approximating unknown parts of elementary geometric structures, such as planes, ellipsoids, spheres and so on. The approach used is based on level set methods computing the moving front of the surface and tracing the interfaces between different parts of it. Level set methods are widely recognized to be one of the most efficient methods to segment both 2D images and 3D medical images. Level set methods for 3D segmentation have recently received an increasing interest. We contribute by proposing a novel approach for raw point sets. Based on the motion and distance functions of the level set we introduce four energy minimization models, which are used for segmentation, by considering an equal number of distance functions specified by geometric features. Finally we evaluate the proposed algorithm on point sets simulating unorganized point clouds.

The presentation of the paper can be found here.


Best PhD Student Award for our paper Collaborative Activities Understanding from 3D Data presented at ICPRAM 2015

We are happy to announce that Fabrizio Natola, member of ALCOR Lab, received the ICPRAM 2015 Best PhD Student Award for the paper Collaborative Activities Understanding from 3D Data co-authored with Valsamis Ntouskos and Fiora Pirri. The 4th International Conference on Pattern Recognition Applications and Methods (ICPRAM) was held on 10-12 January in Lisbon, Portugal. Congratulations Fabrizio!



ICPRAM 2015 Doctoral Consortium: Presentation of our paper Collaborative Activities Understanding from 3D Data.

The Doctoral Consortium will be held between January 10 and 12, 2015 in Lisbon, Portugal and will take place in conjunction with the 4th International Conference on Pattern Recognition Applications and Methods (ICPRAM). The member of ALCOR Lab, Fabrizio Natola will be presenting the paper Collaborative Activities Understanding from 3D Data co-authored with Valsamis Ntouskos and Fiora Pirri.

The presentation of the paper can be found here.


Attention & running commentaries in unknown Environments talk presented at ISACS 2014

The 7th International Symposium on Attention in Cognitive Systems (ISACS 2014) has been held on 1 December, 2014, in Bielefeld, Germany. The head of ALCOR Lab Fiora Pirri, has given the talk Attention & running commentaries in unknown Environments.

The abstract of the talk can be found here and the presentation here.


IROS 2014: Presentation of our papers Real-time Autonomous 3D Navigation for Tracked Vehicles in Rescue Environments and Point Cloud Segmentation and 3D Path Planning for Tracked Vehicles in Cluttered and Dynamic Environments.

The 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2014) will be held between September 14 and 18, 2014, in Chicago, Illinois, USA. The members of ALCOR Lab Mario Gianni and Matteo Menna will be presenting the papers Real-time Autonomous 3D Navigation for Tracked Vehicles in Rescue Environments and Point Cloud Segmentation and 3D Path Planning for Tracked Vehicles in Cluttered and Dynamic Environments (3rd IROS Workshop on Robots in Clutter: Perception and Interaction in Clutter), both co-authored with Federico Ferri, Matteo Menna and Fiora Pirri. The paper abstracts are presented below.

Real-time Autonomous 3D Navigation for Tracked Vehicles in Rescue Environments

Abstract: The paper presents a novel framework for 3D autonomous navigation for tracked vehicles. The framework takes care of clustering and segmentation of point clouds,traversability analysis, autonomous 3D path planning, motion planning and flippers control. Results illustrated in an experiment section show that the framework is promising to face harsh terrains. Robot performance is proved in three main experiments taken in a training rescue area, on fire escape stairs and in a non-planar testing environment, built ad-hoc to prove 3D path planning functionalities. Performance tests are also presented.

Point Cloud Segmentation and 3D Path Planning for Tracked  Vehicles in Cluttered and Dynamic Environments

Abstract: The paper presents a framework for tracked vehicle 3D path planning in rough areas, with dynamic obstacles. The framework provides methods for real-time point cloud interpretation, segmentation and traversabilty analysis tacking also into account changes such as dynamic obstacles and provides a terrain structure interpretation. Moreover the paper presents R2A* an extended version of randomized A* coping with difficult terrains and complex paths for non-holonomic robots.


SSRR 2013: Presentation of our papers An Augmented Reality approach for trajectory planning and control of tracked vehicles in rescue environments and Terrain Traversability in Rescue Environments.

The 11th IEEE International Symposium on Safety, Security and Rescue Robotics (SSRR 2013) is being held these days (October 21-26, 2013) in Linkoping, Sweden. The member of ALCOR Lab and Ph.D student Mario Gianni is presenting the papers An Augmented Reality approach for trajectory planning and control of tracked vehicles in rescue environments, co-authored with Gianpaolo Gonnelli, Arnab Sinha, Matteo Menna and Fiora Pirri, and Terrain Traversability in Rescue Environments, co-authored with Bruno Cafaro, Fiora Pirri, Manuel Ruiz and Arnab Sinha. The paper abstracts are presented below.

An Augmented Reality approach for trajectory planning and control of tracked vehicles in rescue environments (Best Paper Award Finalist)

Abstract: In this paper we propose a framework for trajectory planning and control of tracked vehicles for rescue environments, based on Augmented Reality (AR). The framework provides  the human operator with an AR-based interface that facilitates both 3D path planning and obstacle negotiation. The interface converts the 3D movements of a marker pen, handheld by the operator, into trajectories feasible for the tracked vehicle. The framework implements a trajectory tracking controller to allow the tracked vehicle to autonomously follow the trajectories, decided by the operator. This controller relies on a localization system which provides, at real-time, position feedback. The localization system exploits the performance of a Dead Reckoning System together with the accuracy of an ICP-based SLAM in pose estimation, to determine the pose of the tracked vehicle within the 3D map. We demonstrate the application of the planning framework in autonomous robot navigation for evaluating the robot capabilities  in rescue environments. Our experiments show the effectiveness of the trajectory tracking control method.

Terrain Traversability in Rescue Environments

Abstract: 3D Terrain understanding and structure estimation is a crucial issue  for robots navigating rescue scenarios. Large scale 3D point clouds, even if crisp and yielding a detailed representation of the scene,  provide no information about what is ground, and what is top, what can be surmounted and what can be not, what can be crossed, and what is too deep to be traversed. In this work, we propose a new preliminary method for point cloud structuring, leading to the definition of a traversability map labeled with a cost that specifies how far is the considered region from a traversable one. The representation comes with a real-time algorithm that can be used for the safe navigation of a specific robot, according to its own limitations or constraints. Here, by robot constraints, we mean the length, height, weight of the robot, together with its kinematics constraints (in terms of ground mobility). We present results of the method with experiments taken on different scenarios, furthermore we illustrate the pros and contras of relying only on points cloud data set, without resorting to a surface reconstruction.



TAROS 2013: Presentation of our paper ARE: Augmented Reality Environment for Mobile Robots

The 14th Conference on Towards Autonomous Robotic Systems (TAROS 2013) has been held between August 28 and 30 in Oxford, UK. The member of ALCOR Lab and Ph.D student Mario Gianni has presented the poster of the paper ARE: Augmented Reality Environment for Mobile Robots, co-authored with Federico Ferri and Fiora Pirri. The paper abstract is presented below.

Abstract: In this paper we present ARE, an Augmented Reality Environment, with the main purpose of providing cognitive robotics modelers with a development tool for constructing, at real-time, complex planning scenarios for robots, eliminating the need to model the dynamics of both the robot and the real environment as it would be required by whole simulation environments. The framework also builds a world model representation that serves as ground truth for training and validating algorithms for vision, motion planning and control. We demonstrate the application of the AR-based framework for evaluating the capability of the robot to plan safe paths to goal locations in real outdoor scenarios, while the planning scene dynamically changes, being augmented by virtual objects.



ICPRAM 2013: Presentation of our paper Discriminative Sequence Back-constrained GP-LVM for MOCAP based Action Recognition

The 2nd International Conference on Pattern Recognition Applications and Methods (ICPRAM 2013) will be held between February 15 and 18 in Barcelona, Spain. We are going to participate at the conference while the member of ALCOR Lab and Ph.D student Valsamis Ntouskos wiil present the paper Discriminative Sequence Back-constrained GP-LVM for MOCAP based Action Recognition, co-authored with Panagiotis Papadakis and Fiora Pirri. The paper abstract is presented below.

Abstract: In this paper we address the problem of human action recognition within Motion Capture sequences. We introduce a method based on Gaussian Process Latent Variable Models and Alignment Kernels. We build a new discriminative latent variable model with back-constraints induced by the similarity of the original sequences. We compare the proposed method with a standard sequence classification method based on Dynamic Time Warping and with the recently introduced V-GPDS model which is able to model highly dimensional dynamical systems. The proposed methodology exhibits high performance even for datasets that have not been manually preprocessed while it further allows fast inference by exploiting the back constraints.

 
© 2017 Alcor
Joomla! is Free Software released under the GNU General Public License.