Lab Meeting July 3rd, 2013 (Jeff): Switchable Constraints vs. Max-Mixture Models vs. RRR - A Comparison of Three Approaches to Robust Pose Graph SLAM

Title: Switchable Constraints vs. Max-Mixture Models vs. RRR - A Comparison of Three Approaches to Robust Pose Graph SLAM

Authors: Niko Sünderhauf and Peter Protzel

Abstract:

SLAM algorithms that can infer a correct map despite the presence of outliers have recently attracted increasing attention. In the context of SLAM, outlier constraints are typically caused by a failed place recognition due to perceptional aliasing. If not handled correctly, they can have catastrophic effects on the inferred map. Since robust robotic mapping and SLAM are among the key requirements for autonomous long-term operation, inference methods that can cope with such data association failures are a hot topic in current research. Our paper compares three very recently published approaches to robust pose graph SLAM, namely switchable constraints, max-mixture models and the RRR algorithm. All three methods were developed as extensions to existing factor graph-based SLAM back-ends and aim at improving the overall system’s robustness to false positive loop closure constraints. Due to the novelty of the three proposed algorithms, no direct comparison has been conducted so far.


IEEE International Conference on Robotics and Automation (ICRA), 2013

Link:
LocalLink
http://www.tu-chemnitz.de/etit/proaut/rsrc/ICRA12-comparisonRobustSLAM.pdf

Reference Link:
Switchable Constraints
http://www.tu-chemnitz.de/etit/proaut/mitarbeiter/rsrc/IROS12-switchableConstraints.pdf
Max-Mixture
http://www.roboticsproceedings.org/rss08/p40.pdf
RRR
http://www.roboticsproceedings.org/rss08/p30.pdf

Lab Meeting Jun. 19, 2013 (Alan) : Dense Variational Reconstruction of Non-Rigid Surfaces from Monocular Video

Title: Dense Variational Reconstruction of Non-Rigid Surfaces from Monocular Video (CVPR 2013 Oral)
Authors: Ravi Garg, Anastasios Roussos, Lourdes Agapito

Abstract
This paper offers the first variational approach to the problem of dense 3D reconstruction of non-rigid surfaces from a monocular video sequence. We formulate nonrigid structure from motion (NRSfM) as a global variational energy minimization problem to estimate dense low-rank smooth 3D shapes for every frame along with the camera motion matrices, given dense 2D correspondences.
Unlike traditional factorization based approaches to NRSfM, which model the low-rank non-rigid shape using a fixed number of basis shapes and corresponding coefficients, we minimize the rank of the matrix of time-varying shapes directly via trace norm minimization. In conjunction with this low-rank constraint, we use an edge preserving total-variation regularization term to obtain spatially smooth shapes for every frame. Thanks to proximal splitting techniques the optimization problem can be decomposed into many point-wise sub-problems and simple linear systems which can be easily solved on GPU hardware. We show results on real sequences of different objects (face, torso, beating heart) where, despite challenges in tracking, illumination changes and occlusions, our method reconstructs highly deforming smooth surfaces densely and accurately directly from video, without the need for any prior models or shape templates.

Link

Lab meeting May 29th 2013 (Jim): Reciprocal collision avoidance

I'm going to present the idea of "reciprocal collision avoidance": each moving agent
should take responsibilities for collision avoidance with each other during the navigation. Based on the model of velocity obstacles, the "reciprocal velocity obstacles" and its variations are developed for multi-agent navigation. The main references / materials are the following papers:

Reciprocal Velocity Obstacles for Real-time Multi-agent Navigation
Jur van den Berg, Ming C. Lin, Dinesh Manocha
IEEE International Conference on Robotics and Automation (ICRA), 2008
website

TheHybrid Reciprocal Velocity Obstacle
Jamie Snape, Jur van den Berg, Stephen J. Guy, Dinesh Manocha
IEEE Transactions on Robotics (T-RO), vol. 27, pp. 696-706, 2011

website

Reciprocaln-body Collision Avoidance
Jur van den Berg, Stephen J. Guy, Ming C. Lin, Dinesh Manocha
Robotics Research: The 14th International Symposium (ISRR), Springer Tracts in Advanced Robotics (STAR), vol. 70, pp. 3-19, 2011

website

Lab meeting May 22th 2013 (Tom Hsu): Incorporating User Interaction and Topological Constraints within Contour Completion via Discrete Calculus

Presented by: Tom Hsu

From: Proc. of the Computer Vision and Pattern Recognition (CVPR'13),  Portland, Oregon 2013.

Authors: Jia Xu Maxwell D. Collins Vikas Singh (University of Wisconsin-Madison)

Link: Paper

Abstract: 

We study the problem of interactive segmentation and contour completion for multiple objects. The form of constraints our model incorporates are those coming from user scribbles (interior or exterior constraints) as well as information regarding the topology of the 2-D space after partitioning (number of closed contours desired). We discuss how concepts from discrete calculus and a simple identity using the Euler characteristic of a planar graph can be utilized to derive a practical algorithm for this problem. We also present specialized branch and bound methods for the case of single contour completion under such constraints. On an extensive dataset of ~1000 images, our experiments suggest that a small amount of side knowledge can give strong improvements over fully unsupervised contour completion methods. We show that by interpreting user indications topologically, user effort is substantially reduced.

Lab meeting Mar 8th 2013 (Gene): Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization

Presented by: Gene

From: CVPR2013

Authors: Marcus A. Brubaker, Andreas Geiger, Raquel Urtasun

Abstract:

In this paper we propose an affordable solution to selflocalization, which utilizes visual odometry and road maps as the only inputs. To this end, we present a probabilistic model as well as an efficient approximate inference algorithm, which is able to utilize distributed computation to meet the real-time requirements of autonomous systems. Because of the probabilistic nature of the model we are able to cope with uncertainty due to noisy visual odometry and inherent ambiguities in the map (e.g., in a Manhattan world). By exploiting freely available, community developed maps and visual odometry measurements, we are able to localize a vehicle up to 3m after only a few seconds of driving on maps which contain more than 2,150km of drivable roads.


Link

Lab meeting Apr 24th 2013 (Hank Lin): Scene Parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers

Presented by: Hank Lin

From: Proc. of the International Conference on Machine Learning (ICML'12), Edinburgh, Scotland, 2012.

Authors: C. Farabet, C. Couprie, L. Najman, Y. LeCun

Link: Paper Video

Abstract: 

     Scene parsing, or semantic segmentation, consists in la-

beling each pixel in an image with the category of the object

it belongs to. It is a challenging task that involves the simul-

taneous detection, segmentation and recognition of all the

objects in the image.

     The scene parsing method proposed here starts by com-

puting a tree of segments from a graph of pixel dissimilari-

ties. Simultaneously, a set of dense feature vectors is com-

puted which encodes regions of multiple sizes centered on

each pixel. The feature extractor is a multiscale convolu-

tional network trained from raw pixels. The feature vec-

tors associated with the segments covered by each node in

the tree are aggregated and fed to a classifier which pro-

duces an estimate of the distribution of object categories

contained in the segment. A subset of tree nodes that cover

the image are then selected so as to maximize the aver-

age “purity” of the class distributions, hence maximizing

the overall likelihood that each segment will contain a sin-

gle object. The convolutional network feature extractor is

trained end-to-end from raw pixels, alleviating the need for

engineered features. After training, the system is parameter

free.

      The system yields record accuracies on the Stanford

Background Dataset (8 classes), the Sift Flow Dataset (33

classes) and the Barcelona Dataset (170 classes) while

being an order of magnitude faster than competing ap-

proaches, producing a 320 × 240 image labeling in less

than 1 second.

Lab meeting Apr 17th 2013 (Bang-Cheng Wang): Biped Walking Pattern Generation by using Preview Control of Zero-Moment Point

Presented by Bang-Cheng Wang

From Proceedings of the 2003 IEEE
International Conference on Robotics & Automation
Taipei, Taiwan, September 14-19, 2003.

Authors:
Shuuji KAJITA, Fumio KANEHIRO, Kenji KANEKO, Kiyoshi FUJIWARA,
Kensuke HARADA, Kazuhito YOKOI and Hirohisa HIRUKAWA

Abstract:
We introduce a new method of a biped walking pattern
generation by using a preview control of the zero moment
point (ZMP). First, the dynamics of a biped
robot is modeled as a running cart on a table which
gives a convenient representation to treat ZMP. After
reviewing conventional methods of ZMP based pattern
generation, we formalize the problem as the design of a
ZMP tracking servo controller. It is shown that we can
realize such controller by adopting the preview control
theory that uses the future reference. It is also shown
that a preview controller can be used to compensate
the ZMP error caused by the difference between a simple
model and the precise multibody model. The effectiveness
of the proposed method is demonstrated by a
simulation of walking on spiral stairs.

Link

Lab Meeting April 10, 2013 (Jimmy): Geodesic Flow Kernel for Unsupervised Domain Adaptation

Title: Geodesic Flow Kernel for Unsupervised Domain Adaptation
Authors: Boqing Gong, Yuan Shi, Fei Sha, Kristen Grauman
In: CVPR2012

Abstract
In real-world applications of visual recognition, many factors—such as pose, illumination, or image quality—can cause a significant mismatch between the source domain on which classifiers are trained and the target domain to which those classifiers are applied. As such, the classifiers often perform poorly on the target domain. Domain adaptation techniques aim to correct the mismatch. Existing approaches have concentrated on learning feature representations that are invariant across domains, and they often do not directly exploit low-dimensional structures that are intrinsic to many vision datasets. In this paper, we propose a new kernel-based method that takes advantage of such structures. Our geodesic flow kernel models domain shift by integrating an infinite number of subspaces that characterize changes in geometric and statistical properties from the source to the target domain. Our approach is computationally advantageous, automatically inferring important algorithmic parameters without requiring extensive crossvalidation or labeled data from either domain. We also introduce a metric that reliably measures the adaptability between a pair of source and target domains. For a given target domain and several source domains, the metric can be used to automatically select the optimal source domain to adapt and avoid less desirable ones. Empirical studies on standard datasets demonstrate the advantages of our approach over competing methods.

[link]

Lab Meeting, March 28, 2013 (Chiang Yi): Efficient Model-based 3D Tracking of Hand Articulations using Kinect (BMVC 2011)

Authors: Iason Oikonomidis, Nikolaos Kyriazis
 ,Antonis A. Argyros

Abstract:
We present a novel solution to the problem of recovering and tracking the 3D po-
sition, orientation and full articulation of a human hand from markerless visual obser-
vations obtained by a Kinect sensor. We treat this as an optimization problem, seeking
for the hand model parameters that minimize the discrepancy between the appearance
and 3D structure of hypothesized instances of a hand model and actual hand observa-
tions. This optimization problem is effectively solved using a variant of Particle Swarm
Optimization (PSO). The proposed method does not require special markers and/or a
complex image acquisition setup. Being model based, it provides continuous solutions
to the problem of tracking hand articulations. Extensive experiments with a prototype
GPU-based implementation of the proposed method demonstrate that accurate and ro-
bust 3D tracking of hand articulations can be achieved in near real-time (15Hz).


LINK

extended work: Tracking the articulated motion of two strongly interacting hands

Lab Meeting, March 21, 2013 (Yen-Ting): Extracting 3D Scene-Consistent Object Proposals and Depth from Stereo Images (ECCV 2012)

Authors: Michael Bleyer, Christoph Rhemann, and Carsten Rother

Abstract: This work combines two active areas of research in computer vision: unsupervised object extraction from a single image, and depth estimation from a stereo image pair. A recent, successful trend in unsupervised object extraction is to exploit so-called “3D scene-consistency”, that is enforcing that objects obey underlying physical constraints of the 3D scene, such as occupancy of 3D space and gravity of objects. Our main contribution is to introduce the concept of 3D scene-consistency into stereo matching. We show that this concept is beneficial for both tasks, object extraction and depth estimation. In particular, we demonstrate that our approach is able to create a large set of 3D scene-consistent object proposals, by varying e.g. the prior on the number of objects...

Link

Lab Meeting, March 14, 2013 (Channing): The Design of LEO: a 2D Bipedal Walking Robot for Online Autonomous Reinforcement Learning (IROS 2010)

Authors: Erik Schuitema, Martijn Wisse, Thijs Ramakers and Pieter Jonker

Abstract: Real robots demonstrating online Reinforcement Learning (RL) to learn new tasks are hard to find. The specific properties and limitations of real robots have a large impact on their suitability for RL experiments. In this work, we derive the main hardware and software requirements that a RL robot should fulfill, and present our biped robot LEO that was specifically designed to meet these requirements. We verify its aptitude in autonomous walking experiments using a pre-programmed controller. Although there is room
for improvement in the design, the robot was able to walk, fall and stand up without human intervention for 8 hours, during which it made over 43,000 footsteps.

Link

Lab Meeting, March 7, 2013 (Benny):A Segmentation and Data Association Annotation System for Laser-based Multi-Target Tracking Evaluation

Author: Chien-Chen Weng, Chieh-Chih Wang and Jennifer Healey

Abstract—2D laser scanners are now widely used to accomplish robot perception tasks such as SLAM and multi-target tracking (MTT). While a number of SLAM benchmarking datasets are available, only a few works have discussed the issues of collecting multi-target tracking benchmarking datasets.

In this work, a segmentation and data association annotation system is proposed for evaluating multi-target tracking using 2D laser scanners. The proposed annotation system uses the existing MTT algorithm to generate initial annotation results and uses camera images as the strong hints to assist annotators to recognize moving objects in laser scans. The annotators can draw the object’s shape and future trajectory to automate segmentation and data association and reduce the annotation task loading. The user study results show that the performance of the proposed annotation system is superior in the V-measure vs. annotation speed tests and the false positive and false negative rates.

Link

Lab meeting Feb. 21, 2013 (ChihChung) A Tensor-Based Algorithm for High-Order Graph Matching (PAMI 2010)

Authors: Olivier Duchenne, Francis Bach, In-So Kweon, and Jean Ponce

Abstract: This paper addresses the problem of establishing correspondences between two sets of visual features using higher-order constraints instead of the unary or pairwise ones used in classical methods. Concretely, the corresponding hypergraph matching problem is formulated as the maximization of a multi-linear objective function over all permutations of the features. This function is defined by a tensor representing the affinity between feature tuples. It is maximized using a generalization of spectral techniques where a relaxed problem is first solved by a multi-dimensional power method, and the solution is then projected onto the closest assignment matrix. The proposed approach has been implemented, and it is compared to state-of-the-art algorithms on both synthetic and real data.

Link

Lab meeting Jan. 23, 2013 (Gene): Fully Distributed Scalable Smoothing and Mapping with Robust Multi-robot Data Association (IEEE 2012)

Title: Fully Distributed Scalable Smoothing and Mapping with Robust Multi-robot Data Association (IEEE 2012)
Authors: Alexander Chunningham, Kai M. Wurm, Wolfarm Burgard, and Frank Dellaert

Abstract:


In this paper we focus on the multi-robot perception problem, and present an experimentally validated end-to-end multi-robot mapping framework, enabling individual robots in a team to see beyond their individual sensor horizons. The inference part of our system is the DDF-SAM algorithm [1], which provides a decentralized communication and inference scheme, but did not address the crucial issue of data association.

One key contribution is a novel, RANSAC-based, approach for performing the between-robot data associations and initialization of relative frames of reference. We demonstrate this system with both data collected from real robot experiments, as well as in a large scale simulated experiment demonstrating the scalability of the proposed approach.

Link

Lab meeting Jan 9th 2013 (Bang-Cheng Wang): Kicking a Ball – Modeling Complex Dynamic Motions for Humanoid Robots

Presented by Bang-Cheng Wang

From RoboCup 2010: Robot Soccer World Cup XIV, ser. Lecture Notes 

in Artificial Intelligence, E. Chown, A. Matsumoto, P. Pl¨oger, 

and J. R. del Solar, Eds. Springer, to appear in 2011.

Authors:
Judith Müller, Tim Laue, and Thomas Röfer

Abstract:
Complex motions like kicking a ball into the goal are becoming
more important in RoboCup leagues such as the Standard Platform
League. Thus, there is a need for motion sequences that can be parameterized
and changed dynamically. This paper presents a motion engine
that translates motions into joint angles by using trajectories. These
motions are defined as a set of Bezier curves that can be changed online
to allow adjusting, for example, a kicking motion precisely to the actual
position of the ball. During the execution, motions are stabilized by
the combination of center of mass balancing and a gyro feedback-based
closed-loop PID controller.

Lab Meeting December 19th, 2012 (Jeff): Inference on networks of mixtures for robust robot mapping

Title: Inference on networks of mixtures for robust robot mapping

Authors: Edwin Olson and Pratik Agarwal

Abstract:

The central challenge in robotic mapping is obtaining reliable data associations (or “loop closures”): state-of-the-art inference algorithms can fail catastrophically if even
one erroneous loop closure is incorporated into the map. Consequently, much work has been done to push error rates closer to zero. However, a long-lived or multi-robot system will
still encounter errors, leading to system failure.

We propose a fundamentally different approach: allow richer error models that allow the probability of a failure to be explicitly modeled. In other words, we optimize the map while
simultaneously determining which loop closures are correct from within a single integrated Bayesian framework. Unlike earlier multiple-hypothesis approaches, our approach avoids
exponential memory complexity and is fast enough for realtime performance.

We show that the proposed method not only allows loop closing errors to be automatically identified, but also that in extreme cases, the “front-end” loop-validation systems can be unnecessary. We demonstrate our system both on standard benchmarks and on the real-world datasets that motivated this work.

Link:
Robotics: Science and Systems(RSS), 2012
LocalLink
http://april.eecs.umich.edu/papers/details.php?name=olson2012rss
http://www.roboticsproceedings.org/rss08/p40.pdf

Lab meeting Dec. 12, 2012 (Alan): A Simple Prior-free Method for Non-Rigid Structure-from-Motion Factorization (CVPR 2012 Best Paper Award)

Title: A Simple Prior-free Method for Non-Rigid Structure-from-Motion Factorization (CVPR 2012 Best Paper Award)
Authors: Yuchao Dai, Hongdong Li, Mingyi He

Abstract:
This paper proposes a simple “prior-free” method for solving non-rigid structure-from-motion factorization problems. Other than using the basic low-rank condition, our method does not assume any extra prior knowledge about the nonrigid scene or about the camera motions. Yet, it runs reliably, produces optimal result, and does not suffer from the inherent basis-ambiguity issue which plagued many conventional nonrigid factorization techniques.

Our method is easy to implement, which involves solving no more than an SDP (semi-definite programming) of small and fixed size, a linear Least-Squares or trace-norm minimization. Extensive experiments have demonstrated that it outperforms most of the existing linear methods of nonrigid factorization. This paper offers not only new theoretical insight, but also a practical, everyday solution, to non-rigid structure-from-motion.

Link

Lab meeting Dec 5th 2012 (Jim): Imitation Learning by Coaching

Title: Imitation Learning by Coaching
Authors: He He, Hal Daumé III and Jason Eisner
Neural Information Processing Systems (NIPS), 2012

Abstract:
... we propose to use a coach that demonstrates easy-to-learn actions for the learner and gradually approaches the oracle. ... We apply our algorithm to cost-sensitive dynamic feature selection, a hard decision problem that considers a user-specified accuracy-cost trade-off. ...

Link

NTU CSIE Talk: [2012-11-09] Dr. Koji Yatani, "A Ph.D. – What does it take?"

Title: A Ph.D. – What does it take?

Date: 2012-11-09 2:20pm

Location: R103

Speaker: Dr. Koji Yatani, Microsoft Research Asia

 

Abstract:

 

Getting a Ph.D. surely needs long effort, but why? Of course, research takes time, but a Ph.D. is not just about research. A Ph.D. student needs to be more than just a research person to be a successful Ph.D. This talk is not about a collection of my research projects (although I will introduce some of them a bit); rather, a collection of my experience in research at University of Toronto, Microsoft Research Asia, and industry labs where I did my internship. Through this talk, I will attempt to share my thoughts on what I believe a Ph.D. student should do and learn before getting her Ph.D. Your honest discussions, opinions and feedback would be greatly appreciated.

 

Biography: 

 

Dr. Koji Yatani (http://yatani.jp) is an associate researcher in Human-Computer Interaction Group at Microsoft Research Asia. His main research interests lie in Human-Computer Interaction (HCI) and its intersections with Ubiquitous Computing and Computational Linguistics. More specifically, he is interested in designing new forms of interacting with mobile devices, and developing new hardware and sensing technologies to support user interactions in mobile/ubiquitous computing environments. He is also interested in developing interactive systems and exploring new applications using computational linguistics methods.

 

He received B.Eng. and M.Sci. from University of Tokyo in 2003 and 2005, respectively, and his Ph.D. in Computer Science from University of Toronto in 2011. On November 2011, he joined HCI group at Microsoft Research Asia in Beijing. He was a recipient of NTT Docomo Scholarship (October 2003 -- March 2005), and Japan Society for the Promotion of Science Research Fellowship for Young Scientists (April 2005 -- March 2006). He received the Best Paper Award at CHI 2011. He served as a program committee on CHI 2013, Ubicomp 2012, and WHC 2013. He also served as a Mentoring co-chair on ITS 2012.

Lab meeting Oct 17th 2012 (Hank): Motion Segmentation of Multiple Objects from a Freely Moving Monocular Camera

Lab meeting Oct 17th 2012 (Hank): Motion Segmentation of Multiple Objects from a Freely Moving Monocular Camera

Link

Presented by Hank Lin

From ICRA2012

Authors: Rahul Kumar Namdev, Abhijit Kundu, K Madhava Krishna and C. V. Jawahar


Abstract:
Motion segmentation or segmentation of moving
objects is an inevitable component for mobile robotic systems
such as the case with robots performing SLAM and collision
avoidance in dynamic worlds. This paper proposes an incre-mental motion segmentation system that efficiently segments
multiple moving objects and simultaneously build the map of
the environment using visual SLAM modules. Multiple cues
based on optical flow and two view geometry are integrated
to achieve this segmentation. A dense optical flow algorithm
provides for dense tracking of features. Motion potentials based
on geometry are computed for each of these dense tracks. These
geometric potentials along with optical flow potentials are used
to form a graph like structure. A graph based segmentation
algorithm then clusters together nodes of similar potentials
to form the eventual motion segments. Experimental results
of high quality segmentation on different publicly available
datasets demonstrate the effectiveness of our method.