Organizational Unit:
Institute for Robotics and Intelligent Machines (IRIM)

Permanent Link
https://hdl.handle.net/1853/70657
Research Organization Registry ID
Description
Previous Names
Parent Organization
Parent Organization
Includes Organization(s)
Organizational Unit
Organizational Unit
ArchiveSpace Name Record

Filters

2001 - 2005 8
1
8
8
8
Reset filters

Settings
Author: Balch, Tucker × End date: 2009 × Start date: 2000 × search.filters.applied.f.isOrgUnitOfPublicationTitle: College of Computing ×

Publication Search Results

Now showing 1 - 8 of 8
Thumbnail Image
Item

Data-Driven MCMC for Learning and Inference in Switching Linear Dynamic Systems

2005-07 , Oh, Sang Min , Rehg, James M. , Balch, Tucker , Dellaert, Frank

Switching Linear Dynamic System (SLDS) models are a popular technique for modeling complex nonlinear dynamic systems. An SLDS has significantly more descriptive power than an HMM, but inference in SLDS models is computationally intractable. This paper describes a novel inference algorithm for SLDS models based on the Data- Driven MCMC paradigm. We describe a new proposal distribution which substantially increases the convergence speed. Comparisons to standard deterministic approximation methods demonstrate the improved accuracy of our new approach. We apply our approach to the problem of learning an SLDS model of the bee dance. Honeybees communicate the location and distance to food sources through a dance that takes place within the hive. We learn SLDS model parameters from tracking data which is automatically extracted from video. We then demonstrate the ability to successfully segment novel bee dances into their constituent parts, effectively decoding the dance of the bees.

View
Thumbnail Image
Item

Efficient Particle Filter-Based Tracking of Multiple Interacting Targets Using an MRF-based Motion Model

2003 , Balch, Tucker , Dellaert, Frank , Khan, Zia

We describe a multiple hypothesis particle filter for tracking targets that will be influenced by the proximity and/or behavior of other targets. Our contribution is to show how a Markov random field motion prior, built on the fly at each time step, can model these interactions to enable more accurate tracking. We present results for a social insect tracking application, where we model the domain knowledge that two targets cannot occupy the same space, and targets will actively avoid collisions. We show that using this model improves track quality and efficiency. Unfortunately, the joint particle tracker we propose suffers from exponential complexity in the number of tracked targets. An approximation to the joint filter, however, consisting of multiple nearly independent particle filters can provide similar track quality at substantially lower computational cost.

View
Thumbnail Image
Item

The Georgia Tech Yellow Jackets: A Marsupial Team for Urban Search and Rescue

2002 , Alegre, Fernando , Balch, Tucker , Berhault, Marc , Dellaert, Frank , Kaess, Michael , McGuire, Robert , Merrill, Ernest , Moshkina, Lilia , Ravichandran, Ram , Walker, Daniel

We describe our entry in the AAAI 2002 Urban Search and Rescue (USAR) competition, a marsupial team consisting of a larger wheeled robot and several small legged robots, carried around by the larger robot. This setup exploits complimentary strengths of each robot type in a challenging domain. We describe both the hardware and software architecture, and the on-board real-time mapping which forms the basis of accurate victim-localization crucial to the USAR domain. We also evaluate what challenges remain to be resolved in order to deploy search and rescue robots in realistic scenarios.

View
Thumbnail Image
Item

What Are the Ants Doing? Vision-Based Tracking and Reconstruction of Control Programs

2005-04 , Balch, Tucker , Dellaert, Frank , Delmotte, Florent , Khan, Zia , Egerstedt, Magnus B.

In this paper, we study the problem of going from a real-world, multi-agent system to the generation of control programs in an automatic fashion. In particular, a computer vision system is presented, capable of simultaneously tracking multiple agents, such as social insects. Moreover, the data obtained from this system is fed into a mode-reconstruction module that generates low-complexity control programs, i.e. strings of symbolic descriptions of control-interrupt pairs, consistent with the empirical data. The result is a mechanism for going from the real system to an executable implementation that can be used for controlling multiple mobile robots.

View
Thumbnail Image
Item

Value-Based Communication Preservation for Mobile Robots

2003 , Balch, Tucker , Powers, Matthew

Value-Based Communication Preservation (VBCP) is a behavior-based, computationally efficient approach to maintaining line-of-sight RF communication between members of robot teams in the context of other tasks. The goal of VBCP is, at each time step, to reactively choose a direction in which to move that provides the best communication quality of service with the rest of the team. VBCP uses information about other robots, real-time quality of service measurements and an a priori map of the environment to approximate an optimal direction in an efficient manner. Here, VBCP maintains communication between members of a robotic team while traversing an urban environment in formation. Quantitative and qualitative results are demonstrated in simulation and physical robot teams.

View
Thumbnail Image
Item

Distributed Sensor Fusion for Object Position Estimation by Multi-Robot Systems

2001 , Balch, Tucker , Martin, Martin C. , Stroupe, Ashley W.

We present a method for representing, communicating and fusing distributed, noisy and uncertain observations of an object by multiple robots. The approach relies on re-parameterization of the canonical two-dimensional Gaussian distribution that corresponds more naturally to the observation space of a robot. The approach enables two or more observers to achieve greater effective sensor coverage of the environment and improved accuracy in object position estimation. We demonstrate empirically that, when using our approach, more observers achieve more accurate estimations of an object’s position. The method is tested in three application areas, including object location, object tracking, and ball position estimation for robotic soccer. Quantitative evaluations of the technique in use on mobile robots are provided.

View
Thumbnail Image
Item

An MCMC-based Particle Filter for Tracking Multiple Interacting Targets

2003 , Khan, Zia , Balch, Tucker , Dellaert, Frank

We describe a Markov chain Monte Carlo based particle filter that effectively deals with interacting targets, i.e., targets that are influenced by the proximity and/or behavior of other targets. Such interactions cause problems for traditional approaches to the data association problem. In response, we developed a joint tracker that includes a more sophisticated motion model to maintain the identity of targets throughout an interaction, drastically reducing tracker failures. The paper presents two main contributions: (1) we show how a Markov random field (MRF) motion prior, built on the fly at each time step, can substantially improve tracking when targets interact, and (2) we show how this can be done efficiently using Markov chain Monte Carlo (MCMC) sampling. We prove that incorporating an MRF to model interactions is equivalent to adding an additional interaction factor to the importance weights in a joint particle filter. Since a joint particle filter suffers from exponential complexity in the number of tracked targets, we replace the traditional importance sampling step in the particle filter with an MCMC sampling step. The resulting filter deals efficiently and effectively with complicated interactions when targets approach each other. We present both qualitative and quantitative results to substantiate the claims made in the paper, including a large scale experiment on a video-sequence of over 10,000 frames in length.

View
Thumbnail Image
Item

Niche Selection for Foraging Tasks in Multi-Robot Teams Using Reinforcement Learning

2003 , Balch, Tucker , Ulam, Patrick D.

We present a means in which individual members of a multi-robot team may allocate themselves into specialist and generalist niches in a multi-foraging task where there may exist a cost for generalist strategies. Through the use of reinforcement learning, we show that the members can allocate themselves into effective distributions consistent with those distributions predicted by optimal foraging theory. These distributions are established without prior knowledge of the environment, without direct communication between team members, and with minimal state.

View