Lab Meeting July 13,2010(Nicole):Mutual Localization in a Team of Autonomous Robots using Acoustic Robot Detection

Title: Mutual Localization in a Team of Autonomous Robots using Acoustic Robot Detection

Authors: David Becker and Max Risler

In RoboCup 2008: Robot Soccer World Cup XII ,Volume 5399/2009


Abstract
In order to improve self-localization accuracy we are exploring ways of mutual localization in a team of autonomous robots. Detecting team mates visually usually leads to inaccurate bearings and only rough distance estimates. Also, visually identifying teammates is not possible. Therefore we are investigating methods of gaining relative position information acoustically in a team of robots.
The technique introduced in this paper is a variant of code-multiplexed communication (CDMA, code division multiple access). In a CDMA system, several receivers and senders can communicate at the same time, using the same carrier frequency. Well-known examples of CDMA systems include wireless computer networks and the Global Positioning System, GPS. While these systems use electro-magnetic waves, we will try to adopt the CDMA principle towards using acoustic pattern recognition, enabling robots to calculate distances and bearings to each other.
First, we explain the general idea of cross-correlation functions and appropriate signal pattern generation. We will further explain the importance of synchronized clocks and discuss the problems arising from clock drifts.
Finally, we describe an implementation using the Aibo ERS-7 as platform and briefly state basic results, including measurement accuracy and a runtime estimate. We will briefly discuss acoustic localization in the specific scenario of a RoboCup soccer game.

[link]

Lab Meeting July 6th (Casey): Live Dense Reconstruction with a Single Moving Camera (CVPR 2010)

Authors: Richard A. Newcombe and Andrew J. Davison

Abstract:

We present a method which enables rapid and dense reconstruction of scenes browsed by a single live camera. We take point-based real-time structure from motion (SFM) as our starting point, generating accurate 3D camera pose estimates and a sparse point cloud. Our main novel contribution is to use an approximate but smooth base mesh generated from the SFM to predict the view at a bundle of poses around automatically selected reference frames spanning the scene, and then warp the base mesh into highly accurate depth maps based on view-predictive optical flow and a constrained scene flow update. The quality of the resulting depth maps means that a convincing global scene model can be obtained simply by placing them side by side and removing overlapping regions. We show that a cluttered indoor environment can be reconstructed from a live hand-held camera in a few seconds, with all processing performed by current desktop hardware. Real-time monocular dense reconstruction opens up many application areas, and we demonstrate both real-time novel view synthesis and advanced augmented reality where augmentations interact physically with the 3D scene and are correctly clipped by occlusions.

[Paper]

Lab Meeting July 6th 2010 (Andi): Upsampling Range Data in Dynamic Environments (CVPR 2010 )

Authors

Jennifer Dolson, Jongmin Baek, Christian Plagemann and Sebastian Thrun (Stanford University)

Abstract

We present a flexible method for fusing information from optical and range sensors based on an accelerated high-dimensional filtering approach. Our system takes as input a sequence of monocular camera images as well as a stream of sparse range measurements as obtained from a laser or other sensor system. In contrast with existing approaches, we do not assume that the depth and color data streams have the same data rates or that the observed scene is fully static. Our method produces a dense, high-resolution depth map of the scene, automatically generating confidence values for every interpolated depth point. We describe how to integrate priors on object shape, motion and appearance and how to achieve an efficient implementation using parallel processing hardware such as GPUs.

paper

Lab Meeting June 29th, 2010 (KuoHuel): People Tracking with Human Motion Predictions from Social Forces (ICRA'10)

Title: People Tracking with Human Motion Predictions from Social Forces

Authors: Matthias Luber, Johannes A. Stork, Gian Diego Tipaldi, and Kai O. Arras

Abstract:

For many tasks in populated environments, robots need to keep track of present and future motion states of people. Most approaches to people tracking make weak assumptions on human motion such as constant velocity and direction. But even over a short period, human motion behavior is more complex and influenced by factors such as an intended goal, other people, objects in the environment, or social rules. Therefore, more sophisticated motion models are highly desirable especially since people frequently undergo lengthy occlusion events.

For the study of crowd behavior or evacuation dynamics, computational models that describe individual and collective pedestrian dynamics have been developed in e.g. the social psychology community. In this paper, we make use of such a model for the purpose of people tracking. Concretely, we integrate a pedestrian dynamics model based on social forces into a multi-hypothesis target tracker. We show how the re ned motion predictions translate into more informed probability distributions over hypotheses and nally into a more robust tracking behavior and better occlusion handling. In experiments in indoor and outdoor environments with data from a laser range nder, the social force model leads to more accurate tracking with up to two times fewer data association errors.

[link]

Lab Meeting June 29th, 2010 (Jeff): Fully Autonomous Trajectory Estimation with Long-Range Passive RFID

Title: Fully Autonomous Trajectory Estimation with Long-Range Passive RFID

Authors: Philipp Vorst and Andreas Zell

Abstract:

We present a novel approach which enables a mobile robot to estimate its trajectory in an unknown environment with long-range passive radio-frequency identi cation
(RFID). The estimation is based only on odometry and RFID measurements. The technique requires no prior observation model and makes no assumptions on the RFID setup. In
particular, it is adaptive to the power level, the way the RFID antennas are mounted on the robot, and environmental characteristics, which have major impact on long-range RFID
measurements. Tag positions need not be known in advance, and only the arbitrary, given infrastructure of RFID tags in the environment is utilized. By a series of experiments with a
mobile robot, we show that trajectory estimation is achieved accurately and robustly.

Link:
IEEE International Conference on Robotics and Automation(ICRA), May 2010
http://www.ra.cs.uni-tuebingen.de/publikationen/2010/vorst2010icra.pdf

Lab Meeting June 8th, 2010 (Wang Li): Pictorial Structures for Object Recognition

Pictorial Structures for Object Recognition

Pedro F. Felzenszwalb
Daniel P. Huttenlocher
IJCV 61(1), 2005

Abstract
In this paper we present a computationally efficient framework for part-based modeling and recognition of objects, motivated by the pictorial structure models introduced by Fischler and Elschlager. We address the problem of using pictorial structure models to find instances of an object in an image as well as the problem of learning an object model from training examples, presenting efficient algorithms in both cases. We demonstrate the techniques
by learning models that represent faces and human bodies and using the resulting
models to locate the corresponding objects in novel images.

Paper Link

MSI Robot Vacuum

CMU PhD Thesis Defense: Search in the Physical World

Search in the Physical World

Geoffrey A. Hollinger
Carnegie Mellon University

June 01, 2010, 10:00 a.m., NSH 3305
Abstract
This thesis examines search in the physical world, which differs significantly from the searches in the digital world that we perform every day on our computers. When searching the internet, for instance, success is a matter of informed indexing that allows the information to be retrieved quickly. In these cases, there is no consideration of the physical nature of the world, and the search is not cognizant of space, time, or traversal distance. In contrast, search in the physical world must consider a target that could be continuously moving, possibly even trying to evade being found. The environment may be partially known, and the search proceeds with information gathered during the search itself. In many cases, such as guaranteeing capture of an adversarial target, the problem cannot be solved with a single searcher, and all group members must coordinate their actions with others on the team. Prior work has explored limited instances of such problems, but existing techniques either scale poorly or do not have performance guarantees.

Two of the main variations of search in the physical world are considered: efficient search and guaranteed search. During efficient search, robots move to optimize the average-case performance of the search given a model of the target’s motion. During guaranteed search, robots coordinate to provide worst-case guarantees on search time if the target is adversarial. This thesis unifies these search problems and shows them to be NP-hard, which suggests that a scalable and optimal algorithm is unlikely. Despite these hardness results, algorithms using implicit coordination can provide scalable and high-performing approximate solutions to many real-world search problems. Implicit coordination arises when robots share their locations, measurements, and/or actions to improve the plans of their teammates. In accord with this design strategy, a linearly scalable efficient search algorithm is presented that utilizes implicit coordination to achieve bounded performance. In addition, this thesis contributes a novel approach that augments the coordination with a pre-search spanning tree generation step, which leads to an anytime algorithm for guaranteed search.

With a focus on decentralized and online operation, the proposed search algorithms are extended to take into account team constraints, limited communication, and partially known environments. The techniques are illustrated using a scenario in the literature that incorporates both efficient and guaranteed search, and they are validated both in simulation and on human-robot search teams operating in the physical world. The developed framework enables teams of autonomous agents to search environments outside the scope of previous techniques, and the analysis provides insight into the complexity of multi-robot coordination problems.

[Thesis PDF]

Thesis Committee
Sanjiv Singh, Chair
Geoff Gordon
Reid Simmons
Athanasios Kehagias, Aristotle University of Thessaloniki

Department machine learning talks: Interactively Building Mashups by Demonstration

Title: Interactively Building Mashups by Demonstration
Speaker: Dr. Craig A. Knoblock, University of Southern California
Time: 10:30am, May 25 (Tue), 2010
Place: Room 210, CSIE Building

Abstract:

There are a number of tools and services available now for building mashups on the Web. However, many of the tools for constructing mashups reply on a widget paradigm, where users must select, customize, and connect widgets to build the desired application. While this approach does not require programming, the users must still understand programming concepts to successfully create a mashup. In this talk I describe our programming-by-demonstration approach to building mashups by example. Instead of requiring a user to select and customize a set of widgets, the user simply demonstrates the integration task by example. I will describe how this approach addresses the problems of extracting data from various sources, cleaning and modeling the extracted data, integrating the data across sources, and visualizing the integrated results in a geospatial context. We implemented these ideas in a system called Karma and evaluated Karma on a set of 20 users and showed that compared to other mashup construction tools, Karma allowed more of the users to successfully build mashups and made it possible to build these mashups significantly faster compared to using a widget-based approach.

This research is joint work with Shubham Gupta, Pedro Szekely, and Rattapoom Tuchinda.

Short Biography:

Dr. Craig Knoblock is a Research Professor in Computer Science and a Senior Project Leader in the Information Sciences Institute at the University of Southern California (USC). He received both his M.S. and Ph.D. in Computer Science from Carnegie Mellon and his B.S. from Syracuse University. His current research interests include information integration, information extraction, machine learning, users interfaces, constraint reasoning, geospatial data fusion, and bioinformatics. He has published one book and over 200 articles, book chapters, and conference papers on his research. He has served on the Senior Program Committees of the National Artificial Intelligence Conference, the International Joint Conference on AI, the International Semantic Web Conference, and the International Conference on Intelligent User Interfaces. He was program co-chair for the 2008 AAAI track on AI and the Web and he is conference chair for the 2011 International Joint Conference on AI (IJCAI). He is on the editorial board of Artificial Intelligence, AAAI Press, Computational Intelligence, and the Journal on Foundations and Trends in Web Science. He is a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI), a Distinguished Scientist of the Association of Computing Machinery (ACM), a Trustee of the International Joint Conference on Artificial Intelligence (IJCAI), and past President of the International Conference on Automated Planning and Scheduling (ICAPS). He has started two companies, Fetch Technologies and Geosemble Technologies, based on his research at USC.

Department machine learning talks: Transfer Learning with Applications

Title: Transfer Learning with Applications
Speaker: Prof. Qiang Yang, Hong Kong University of Science and Technology
Time: 11:15am, May 25 (Tue), 2010
Place: Room 210, CSIE Building

Abstract:

Transfer learning is a new machine learning and data mining framework that allows the training and test data to come from different distributions or feature spaces. We can find many novel applications of machine learning and data mining where transfer learning is necessary. In this talk, I will give an introduction to transfer learning and then highlight some important applications such as text and image classification, sensor network data mining and activity recognition, collaborative filtering and bioinformatics. I will also discuss some potential future directions of transfer learning.

Short Biography:

Qiang Yang is a professor of the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology. He is also an adjunct professor at Peking University, Beijing, and at Zhongshan University in Guangzhou, China. He received his PhD degree from the University of Maryland, College Park. His research interests include AI planning and sensor-based activity recognition, machine learning and case-based reasoning, and data mining. He is a senior member of the IEEE, the AAAI, and the ACM, and an associate editor for the IEEE Transactions on Knowledge and Data Engineering and IEEE Intelligent Systems, as well as the International Journal of Knowledge and Information Systems. More information about him can be found at http://www.cse.ust.hk/~qyang/

Lab Meeting June 8th, 2010 (fish60): Learning to Navigate Through Crowded Environments

Peter Henry, Christian Vollmer, Brian Ferris, and Dieter Fox,
Learning to Navigate Through Crowded Environments,
in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA2010), Anchorage, Alaska, May 2010

Abstract—The goal of this research is to enable mobile robots to navigate through crowded environments such as indoor shopping malls, airports, or downtown side walks. The key research question addressed in this paper is how to learn planners that generate human-like motion behavior. Our approach uses inverse reinforcement learning (IRL) to learn human-like navigation behavior based on example paths. Since robots have only limited sensing, we extend existing IRL methods to the case of partially observable environments. We demonstrate the capabilities of our approach using a realistic crowd flow simulator in which we modeled multiple scenarios in crowded environments. We show that our planner learned to guide the robot along the flow of people when the environment is crowded, and along the shortest path if no people are around.

Link

News: Innovation: Teaching robots some manners

13:07 17 May 2010 by Colin Barras

Where PCs are concerned, faster is invariably better. But things aren't so clear-cut in human society. The next generation of social robots will be better loved if they adopt more human-like behaviour – even if that means losing some of their raw efficiency.

Norihiro Hagita and colleagues at the ATR laboratories in Kyoto, Japan, asked 38 volunteers to click on a PC mouse to enlarge an image. The response was programmed to be delayed by 1 to 3 seconds. As expected, an immediate response was most favoured, and participants expressed more and more dissatisfaction as the delay lengthened.

But a version of the experiment that involved a humanoid robot threw up a surprising result. The volunteers were asked to tell the robot to take out the rubbish, and the robot verbally acknowledged the request. This time an immediate response – beginning the moment the volunteer finished talking – was considered less welcome than one that was delayed by a second.

...

See the full article here.

News: Software that Learns by Watching

KarDo learns how to perform common IT support tests by observing what the experts do.
By Duncan Graham-Rowe
WEDNESDAY, MAY 19, 2010

Overworked and much in demand, IT support staff can't be in two places at once. But software designed to watch and learn as they carry out common tasks could soon help--by automatically performing the same jobs across different computers.

The new software system, called KarDo, was developed by researchers at MIT. It can automatically configure an e-mail account, install a virus scanner, or set up access to a virtual private network, says MIT's Dina Katabi, an associate professor at MIT.

Crucially, the software just needs to watch an administrator perform this task once before being able to carry out the same job on computers running different software. Businesses spend billions of dollars each year on simple and repetitive IT tasks, according to reports from the analyst groups Forrester and Gartner. KarDo could reduce these costs by as much as 20 percent, Katabi says.

See the full article here.

Lab Meeting June 1st, 2010 (Kuen-Han): Multiframe Motion Segmentation with Missing Data Using PowerFactorization and GPCA(IJCV 2008)

Title: Multiframe Motion Segmentation with Missing Data Using
PowerFactorization and GPCA
Authors: René Vidal · Roberto Tron · Richard Hartley

Abstract: We consider the problem of segmenting multiple
rigid-body motions from point correspondences in multiple
affine views. We cast this problem as a subspace clustering
problem in which point trajectories associated with each
motion live in a linear subspace of dimension two, three or
four. Our algorithm involves projecting all point trajectories
onto a 5-dimensional subspace using the SVD, the Power-
Factorization method, or RANSAC, and fitting multiple linear
subspaces representing different rigid-body motions to
the points in R5 using GPCA. Unlike previous work, our
approach does not restrict the motion subspaces to be
fourdimensional and independent. Instead, it deals gracefully
with all the spectrum of possible affine motions: from twodimensional
and partially dependent to four-dimensional and fully independent.

Our algorithm can handle the case of missing data, meaning
that point tracks do not have to be visible in all images, by
using the PowerFactorization method to project the data. In
addition, our method can handle outlying trajectories by using
RANSAC to perform the projection.

We compare our approach to other methods on a database of
167 motion sequences with full motions, independent motions,
degenerate motions, partially dependent motions, missing data,
outliers, etc. On motion sequences with complete data our
method achieves a misclassification error of less that 5% for
two motions and 29% for three motions.

paper link

Lab Meeting June 1, 2010 (Jimmy): Object Recognition in 3D Point Clouds Using Web Data and Domain Adaptation

Title: Object Recognition in 3D Point Clouds Using Web Data and Domain Adaptation
In: IJRR2010
Authors: Kevin Lai and Dieter Fox

Abstract
In recent years, object detection has become an increasingly active field of research in robotics. An important problem in object detection is the availability of a sufficient amount of labeled training data to learn good classifiers. In this paper we show how to significantly reduce the need for manually labeled training data by leveraging data sets available on the World Wide Web. Specifically, we show how to use objects from Google’s 3D Warehouse to train an object detection system for 3D point clouds collected by robots navigating through both urban and indoor environments. In order to deal with the different characteristics of the web data and the real robot data, we additionally use a small set of labeled point clouds and perform domain adaptation. Our experiments demonstrate that additional data taken from the 3D Warehouse along with our domain adaptation greatly improves the classification accuracy on real-world environments.

[pdf]

Lab Meeting May, 18 (Gary) : "2D vs. 3D Deformable Face Models: Representational Power, Construction, and Real-Time Fitting "( IJCV 2007)

Title:
2D vs. 3D Deformable Face Models: Representational Power, Construction, and Real-Time Fitting

Authors: Iain Matthews, Jing Xiao, Simon Baker


Abstract:

Model-based face analysis is a general paradigm with applications that include face recognition, expression recognition, lip-reading, head pose estimation, and gaze estimation. A face model is first constructed from a collection of training data, either 2D images or 3D range scans. The face model is then fit to the input image(s) and the model parameters used in whatever the application is. Most existing face models can be classified as either 2D (e.g. Active Appearance Models) or 3D (e.g. Morphable Models). In this paper we compare 2D and 3D face models along three axes: (1) representational power, (2) construction, and (3) real-time fitting. For each axis in turn, we outline the differences that result from using a 2D or a 3D face model.


link

ICRA 2010 Awards - Best Cognitive Robotics Paper

• Gesture-Based Human-Robot Jazz Improvisation: Guy Hoffman and Gil Weinberg (Video)
  
• Categorizing Object-Action Relations from Semantic Scene Graphs: Eren Erdal Aksoy, Alexey Abramov, Florentin Woergoetter and Babette Dellen
• Mapping Indoor Environments Based on Human Activity: Slawomir Grzonka, Frederic Dijoux, Andreas Karwath and Wolfram Burgard
• Biomimetic Motor Behavior for Simultaneous Adaptation of Force, Impedance and Trajectory in Interaction Tasks: Gowrishankar Ganesh, Alin Albu-Schäffer, Masahiko Haruno, Mitsuo Kawato and Etienne Burdet
  

ICRA 2010 Awards - KUKA Service Robotics Best Paper

• Visual Path Following on a Manifold in Unstructured Three-Dimensional Terrain: Paul Timothy Furgale and Timothy Barfoot (Video)
  
• Efficiency Based Modulation for Wheelchair Driving Collaborative Control: Christina Urdiales, Manuel Fernandez-Carmona, Jose Manuel Peula Palacios, Roberta Annicchiarico, Francisco Sandoval and Carlo Caltagirone
• Anytime Online Novelty Detection for Vehicle Safeguarding: Boris Sofman, James Bagnell and Anthony Stentz
• Pulling Open Doors and Drawers: Coordinating an Omni-Directional Base and a Compliant Arm with Equilibrium Point Control: Advait Jain and Charlie Kemp (Video)
  

ICRA 2010 Awards - Best Conference Paper

• Integrated Silicon-PDMS Process for Microbot Mechanisms: Aaron P. Gerratt, Ivan Penskiy and Sarah Bergbreiter
• The Distributed Flight Array: Raymond Oung, Frederic Bourgault, Matthew Donovan and Rafaello D'Andrea
• MoonWalker, a Lower Limb Exoskeleton able to Sustain Bodyweight using a Passive Force Balancer: Sebastien Krut, Michel Benoit, Etienne Dombre and François Pierrot
• Fast, Robust Quadruped Locomotion Over Challenging Terrain: Mrinal Kalakriskhan, Jonas Buchli, Peter Pastor, Michael Mistry and Stefan Schaal

ICRA 2010 Awards - Best Student Paper

• Non-Ideal Swimming of Artificial Bacterial Flagella Near a Surface: Kathrin Eva Peyer, Li Zhang, Bradley Kratochvil and Bradley J. Nelson
• Feature Detection and Matching in Images with Radial Distortion: Miguel Lourenço, Joăo P. Barreto and Abed Malti
• Mapping Indoor Environments Based on Human Activity: Slawomir Grzonka, Frederic Dijoux, Andreas Karwath and Wolfram Burgard
• Toward the Set of Frictional Velocity Fields Generable by 6-Degree-Of-Freedom Oscillatory Motion of a Rigid Plate: Thomas Vose, Paul Umbanhowar and Kevin Lynch