2D Localization of Outdoor Mobile Robots Using 3D Laser Range Data

Takeshi Takahashi
Master's thesis
Robotics Institute, Carnegie Mellon University,
May, 2007

Abstract
Robot localization in outdoor environments is a challenging problem because of unstructured terrains. Ladars that are not horizontally attached have benefits for detecting obstacles but are not suitable for some localization algorithms used for indoor robots, which have horizontally fixed ladars. The data obtained from tilted ladars are 3D while these from non-tilted ladars are 2D. We present a 2D localization approach for these non-horizontally attached ladars. This algorithm combines 2D particle filter localization with a 3D perception system. We localize the vehicle by comparing a local map with a previously known map. These maps are created by converting 3D data into 2D data. Experimental results show that our approach is able to utilize the benefits of 3D data and 2D maps to efficiently overcome the problems of outdoor environments.

See the complete thesis.

Georgia Tech PhD thesis: Acoustical Awareness for Intelligent Robotic Action

Eric Martinson,
Acoustical Awareness for Intelligent Robotic Action,
PhD Thesis, College of Computing,
Georgia Institute of Technology,
Nov. 2007

With the growth of successes in pattern recognition and signal processing, mobile robot applications today are increasingly equipping their hardware with microphones to improve the set of available sensory information. However, if the robot, and therefore the microphone, ends up in a poor location acoustically, then the data will remain noisy and potentially useless for accomplishing the required task. This is compounded by the fact that there are many bad acoustic locations through which a robot is likely to pass, and so the results from auditory sensors often remain poor for much of the task.

The movement of the robot, though, can also be an important tool for overcoming these problems, a tool that has not been exploited in the traditional signal processing community. Robots are not limited to a single location as are traditionally placed microphones, nor are they powerless over to where they will be moved as with wearable computers. If there is a better location available for performing its task, a robot can navigate to that location under its own power. Furthermore, when deciding where to move, robots can develop complex models of the environment. Using an array of sensors, a mobile robot can build models of sound flow through an area, picking from those models the paths most likely to improve performance of an acoustic application.

In this dissertation, we address the question of how to exploit robotic movement. Using common sensors, we present a collection of tools for gathering information about the auditory scene and incorporating that information into a general framework for acoustical awareness. Thus equipped, robots can make intelligent decisions regarding control strategies to enhance their performance on the underlying acoustic application.

The full thesis.

Door safety system

As the reinstallation of the computer which contains the database of our card data, I have to rebuild the database(I will make more backup this time). So, please contact me if your card record is not in the new database system. (If you are not sure your record is in database or not, just try it out with the door safy system.)

Sorry for the inconvenience.

Team MIT Urban Challenge

This technical report describes Team MIT’s approach to the DARPA Urban Challenge. We have developed a novel strategy for using many inexpensive sensors, mounted on the vehicle periphery, and calibrated with a new crossmodal calibration technique. Lidar, camera, and radar data streams are processed using an innovative, locally smooth state representation that provides robust perception for realtime autonomous control. A resilient planning and control architecture has been developed for driving in traffic, comprised of an innovative combination of wellproven algorithms for mission planning, situational planning, situational interpretation, and trajectory control.

These innovations are being incorporated in two new robotic vehicles equipped for autonomous driving in urban environments, with extensive testing on a DARPA site visit course. Experimental results demonstrate all basic navigation and some basic traffic behaviors, including unoccupied autonomous driving, lane following using purepursuit control and our local frame perception strategy, obstacle avoidance using kinodynamic RRT path planning, Uturns, and precedence evaluation amongst other cars at intersections using our situational interpreter. We are working to extend these approaches to advanced navigation and traffic scenarios.

LINK

Lab Meeting December 18th, 2007 (Leo): Augmented State Tracking

I will try to show some simulation result of augmented state tracking.

Lab meeting December 18th:The Autonomous City Explorer Project: Aims and System Overview

Abstract—As robots are gradually leaving highly structuredfactory environments and moving into human populated environments,they need to possess more complex cognitive abilities.Not only do they have to operate efficiently and safely innatural populated environments, but also be able to achievehigher levels of cooperation and interaction with humans. TheAutonomous City Explorer (ACE) project envisions to createa robot that will autonomously navigate in an unstructuredurban environment and find its way through interaction withhumans. To achieve this, research results from the fields ofautonomous navigation, path planning, environment modeling,and human-robot interaction are combined. In this paper anovel hardware platform is introduced, a system overview isgiven, the research foci of ACE are highlighted, approaches tothe occurring challenges are proposed and analyzed, and finallysome first results are presented.

[link]http://www.csie.ntu.edu.tw/~b91501097/04399411.pdf

Lab Meeting December 18th, 2007(ZhenYu):Spherical Catadioptric Arrays: Construction, Multi-View Geometry, and Calibration

Title: Spherical Catadioptric Arrays: Construction, Multi-View Geometry, and Calibration
Author: Lanman, Douglas Crispell, Daniel Wachs, Megan Taubin, Gabriel

Proceedings of the Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06)

Abstract:
This paper introduces a novel imaging system composed of an array of spherical mirrors and a single high-resolution digital camera. We describe the mechanical design and construction of a prototype, analyze the geometry of image formation, present a tailored calibration algorithm, and discuss the effect that design decisions had on the calibration routine. This system is presented as a unique platform for the development of efficient multi-view imaging algorithms which exploit the combined properties of camera arrays and non-central projection catadioptric systems. Initial target applications include data acquisition for image-based rendering and 3D scene reconstruction. The main advantages of the proposed system include: a relatively simple calibration procedure, a wide field of view, and a single imaging sensor which eliminates the need for color calibration and guarantees time synchronization.

[Link]

Lab Meeting December 18th, 2007 (Atwood): Maximum Entropy Model and Conditional Random Field

I will talk about the relation between Maximum Entropy Model and Conditional Random Field, and my recent experiments.

Abstract:
In this chapter, we will describe a statistical model that conforms to the
maximum entropy principle (we will call it the maximum entropy model, or
ME model in short) [68, 69]. Through mathematical derivations, we will show
that the maximum entropy model is a kind of exponential model, and is a close
sibling of the Gibbs distribution described in Chap. 6. An essential difference
between the two models is that the former is a discriminative model, while
the latter is a generative model. Through a model complexity analysis, we will
show why discriminative models are generally superior to generative models in
terms of data modeling power. We will also describe the Conditional Random
Field (CRF), one of the latest discriminative models in the literature, and
prove that CRF is equivalent to the maximum entropy model.

Fulltext

Lab Meeting December 18th, 2007 (Jeff):Progress report

I will try to show some test of my recent work.

And I will try to point out some problems of EKF-SLAM and some limitations about it.

Lab Meeting 11 December (Der-Yeuan): Registration of Colored 3D Point Clouds with a Kernel-based Extension to the Normal Distributions Transform

Abstract
We present a new algorithm for scan registration
of colored 3D point data which is an extension to the Normal
Distributions Transform (NDT). The probabilistic approach of
NDT is extended to a color-aware registration algorithm by
modeling the point distributions as Gaussian mixture-models
in color space. We discuss different point cloud registration
techniques, as well as alternative variants of the proposed algorithm.
Results showing improved robustness of the proposed
method using real-world data acquired with a mobile robot and
a time-of-flight camera are presented.

Authors: Benjamin Huhle, Martin Magnusson, Achim, Lilienthal, Wolfgang, Straßer

Reference on NDT: http://citeseer.ist.psu.edu/biber03normal.html

FRC Seminar - December 12 - Autonomous Peat Moss Harvesting

FRC Seminar - Autonomous Peat Moss Harvesting

Speaker:

Carl Wellington

NREC Commercialization Specialist

National Robotics Engineering Center

Carnegie Mellon University

Date/Time/Location:

Wednesday, December 12th
Noon
NSH 1109
Pizza will be served

Abstract

This presentation will describe recent work with John Deere to deploy a team of three autonomous tractors for coordinated peat moss harvesting at a Canadian farm. We provided the perception system that estimates the location of the dumping pile and detects ditches and other obstacles. These systems were deployed for three months of testing and successfully harvested and deposited several fields of peat moss autonomously.

After discussing this application and our long term partnership with John Deere, I will describe our sensor pod and perception system, including a Markov random field ground estimation algorithm used for pile estimation. I'll end with some lessons learned and a discussion of the challenges in making a perception system that was deployed for months of outdoor testing without us present.

Speaker Bio

Carl Wellington is a researcher at the National Robotics Engineering Center of Carnegie Mellon University's Robotics Institute. His current focus is on perception for autonomous ground vehicles and includes project work with John Deere and Darpa's UPI Crusher program. He received his PhD from Carnegie Mellon's Robotics Institute in 2005 and his BS in Engineering from Swarthmore College in 1999.

Door safety system

We could start to operate the system now! (As almost every member is rigistered now.)

Things to be concerned:
1. Press the red bottom at the top of the door to enable/disable the door safety lock.
2. Keep the door closed and lock on usually. (At this time, no need the original physical door lock, remember to disable the physical door lock)
3. The last person who leaves the lab need enable the physical door lock as before.

(4. The first person who enters the lab need remember to use both their key and card. If it is very annoying, maybe we could try to disable the safety lock when condition 3. occurs)

WIRED MAGAZINE -- Getting a Grip

Building the Ultimate Robotic Hand


A 6-foot-tall, one-armed robot named Stair 1.0 balances on a modified Segway platform in the doorway of a Stanford University conference room. It has an arm, cameras and laser scanners for eyes, and a tangle of electrical intestines stuffed into its base.
...
To do real work in our offices and homes, to fetch our staplers or clean up our rooms, robots are going to have to master their hands. They'll need the kind of "hand-eye" coordination that enables them to identify targets, guide their mechanical mitts toward them, and then manipulate the objects deftly.
...
But the next generation, Stair 2.0, will actually analyze its own actions. The next Stair will look for the object in its hand and measure the force its fingers are applying to determine whether it's holding anything. It will plan an action, execute it, and observe the result, completing a feedback loop. And it will keep going through the loop until it succeeds at its task.
...

For detail: Link

IROS 2007: Spatial Reasoning for Human Robot Interaction

Emrah Akin Sisbot, Luis F. Marin and Rachid Alami

Abstract
Robots’ interaction with humans raises new issuesfor geometrical reasoning where the humans must be taken explicitly into account. We claim that a human-aware motion system must not only elaborate safe robot motions, but also synthesize good, socially acceptable and legible movement.
This paper focuses on a manipulation planner and a placement mechanism that take explicitly into account its human partners by reasoning about their accessibility, their vision field and their preferences. This planner is part of a human-aware motion and manipulation planning and control system that we aim to develop in order to achieve motion and manipulation tasks in presence or in synergy with humans.

[Intelligence Seminar]Activity Recognition from Wearable Sensors

Intelligence Seminar
Title: Activity Recognition from Wearable Sensors
Date: Nov 29

Speaker:

Dieter Fox is Associate Professor and Director of the Robotics and State Estimation Lab in the Computer Science & Engineering Department at the University of Washington, Seattle. He obtained his Ph.D. from the University of Bonn, Germany. Before joining UW, he spent two years as a postdoctoral researcher at the CMU Robot Learning Lab.

Dieter's research focuses on probabilistic state estimation with applications in robotics and activity recognition.

Abstract:

Recent advances in wearable sensing and computing devices and in fast, probabilistic inference techniques make possible the fine-grained estimation of a person's activities over extended periods of time. In this talk I will show how dynamic Bayesian networks and conditional random fields can be used to estimate the location and activity of a person based on information such as GPS readings or WiFi signal strength. Our models use multiple levels of abstraction to bridge the gap between raw sensor measurements and high level information such as a user's mode of transportation, her current goal, and her significant places (e.g. home or work place). I will also present work on using RFID tags or a wearable multi-sensor system to estimate a person's fine-grained activities.

This is joint work with Brian Ferris, Lin Liao, Don Patterson, Amarnag Subramanya, Jeff Bilmes, Gaetano Borriello, and Henry Kautz.

[IROS'07]Feature Selection in Conditional Random Fields for Activity Recognition

Title: Feature Selection in Conditional Random Fields for Activity Recognition

Author:
Vail, Douglas Carnegie Mellon Univ.
Lafferty, John Carnegie Mellon Univ.
Veloso, Manuela Carnegie Mellon Univ.

Abstract:

Temporal classification, such as activity recognition,
is a key component for creating intelligent robot systems.
In the case of robots, classification algorithms must robustly
incorporate complex, non-independent features extracted from
streams of sensor data. Conditional random fields are discriminatively
trained temporal models that can easily incorporate
such features. However, robots have few computational
resources to spare for computing a large number of features
from high bandwidth sensor data, which creates opportunities
for feature selection. Creating models that contain only the most
relevant features reduces the computational burden of temporal
classification. In this paper, we show that l1 regularization is an
effective technique for feature selection in conditional random
fields. We present results from a multi-robot tag domain with
data from both real and simulated robots that compare the
classification accuracy of models trained with l1 regularization,
which simultaneously smoothes the model and selects features;
l2 regularization, which smoothes to avoid over-fitting, but
performs no feature selection; and models trained with no
smoothing.

VASC Seminar : Object Recognition by Scene Alignment

Bryan Russell
MIT
Monday, Nov 26, 3:30pm, NSH 1507

Current object recognition systems can only recognize a limited number of object categories; scaling up to many categories is the next challenge inobject recognition. We seek to build a system to recognize and localize many different object categories in complex scenes. We achieve thisthrough a deceptively simple approach: by matching the input image, in anappropriate representation, to images in a large training set of labeled images. This gives us a set of retrieval images, which provide hypothesesfor object identities and locations. We combine this knowledge from theretrieval images with an object detector to detect objects in the image. The simplicity of the approach allows learning for a large number ofobject classes embedded in many different scenes. We demonstrate improvedclassification and localization performance over a standard objectdetector using a held-out test set from the Label Me database.Furthermore, our system restricts the object search space and therefore greatly increases computational efficiency.

Bio:
After leaving sunny Phoenix, AZ, Bryan received his A.B. from DartmouthCollege. He recently defended his dissertation "Labeling, Discovering,and Detecting Objects in Images" at MIT under the supervision of WilliamFreeman and Antonio Torralba. His next journey will be as a post-doctoral fellow at Ecole Normale Supérieure under Jean Ponce and Andrew Zisserman.There, he will continue to pursue research in visual object recognitionand scene understanding.

IROS 2007 : A Spatio-Temporal Probabilistic Model for Multi-Sensor Object

Bertrand Douillard, Dieter Fox, Fabio Ramos

Abstract:

This paper presents a general framework for multi-sensor object recognition through a discriminative probabilistic approach modelling spatial and temporal correlations.The algorithm is developed in the context of Conditional Random Fields (CRFs) trained with virtual evidence boosting.The resulting system is able to integrate arbitrary sensorinformation and incorporate features extracted from the data.The spatial relationships captured by are further integratedinto a smoothing algorithm to improve recognition over time.We demonstrate the benefits of modelling spatial and temporal relationships for the problem of detecting cars using laser and vision data in outdoor environments.

link

IROS 2007: Detection and Tracking of Multiple Pedestrians

Xiaowei Shao, Huijing Zhao, Katsuyuki Nakamura, Kyoichiro Katabira, Ryosuke Shibasaki and Yuri Nakagawa

Abstract:
We propose a novel system for tracking multiple
pedestrians in a crowded scene by exploiting single-row laser
range scanners that measure distances of surrounding objects.
A walking model is built to describe the periodicity of the
movement of the feet in the spatial-temporal domain, and a
mean-shift clustering technique in combination with spatialtemporal
correlation analysis is applied to detect pedestrians.
Based on the walking model, particle filter is employed to track
multiple pedestrians. Compared with camera-based methods,
our system provides a novel technique to track multiple pedestrians
in a relatively large area. The experiments, in which over
300 pedestrians were tracked in 5 minutes, show the validity
of the proposed system.

IROS 2007: An Augmented State Vector Approach to GPS-Based Localization

Francesco Capezio, Antonio Sgorbissa, Renato Zaccaria
DIST – University of Genova, Italy

Abstract:
The paper focuses on the localization subsystem
of ANSER, a mobile robot for autonomous surveillance in
civilian airports and similar wide outdoor areas. ANSER
localization subsystem is composed of a non-differential GPS
unit and a laser rangefinder for landmark-based localization
(inertial sensors are absent). An augmented state vector
approach and an Extended Kalman filter are successfully
employed to estimate the colored components in GPS noise,
thus getting closer to the conditions for the EKF to be
applicable.