Publications – Piyush Khandelwal

2017

Piyush Khandelwal, Shiqi Zhang, J. Sinapov, Matteo Leonetti, J. Thomason, Fankgai Yang, I. Gori, M. Svetlik, P. Khante, Vladimir Lifschitz, J. K. Aggarwal, R. Mooney, and Peter Stone, “BWIBots: A platform for bridging the gap between AI and human–robot interaction research,” The International Journal of Robotics Research, 2017.
[Bibtex]

@article{IJRR17-khandelwal,
author = {Piyush Khandelwal and Shiqi Zhang and Jivko Sinapov and Matteo Leonetti and Jesse Thomason and Fangkai Yang and Ilaria Gori and Maxwell Svetlik and Priyanka Khante and Vladimir Lifschitz and J. K. Aggarwal and Raymond Mooney and Peter Stone},
title = {{BWI}Bots: A platform for bridging the gap between AI and human--robot interaction research},
journal = {The International Journal of Robotics Research},
year = {2017},
doi = {10.1177/0278364916688949},
abstract = {
Recent progress in both AI and robotics have enabled the
development of general purpose robot platforms that are capable of executing
a wide variety of complex, temporally extended service tasks in open
environments. This article introduces a novel, custom-designed multi-robot
platform for research on AI, robotics, and especially humanâ€“robot
interaction for service robots. Called BWIBots, the robots were designed as
a part of the Building-Wide Intelligence (BWI) project at the University of
Texas at Austin. The article begins with a description of, and
justification for, the hardware and software design decisions underlying
the BWIBots, with the aim of informing the design of such platforms in the
future. It then proceeds to present an overview of various research
contributions that have enabled the BWIBots to better (a) execute action
sequences to complete user requests, (b) efficiently ask questions to
resolve user requests, (c) understand human commands given in natural
language, and (d) understand human intention from afar. The article
concludes with a look forward towards future research opportunities and
applications enabled by the BWIBot platform.},
}

Piyush Khandelwal and Peter Stone, “Multi-Robot Human Guidance: Human Experiments and Multiple Concurrent Requests,” in International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2017.
[Bibtex]

@InProceedings{AAMAS17-khandelwal,
author = {Piyush Khandelwal and Peter Stone},
title = {Multi-Robot Human Guidance: Human Experiments and Multiple Concurrent Requests},
booktitle = {International Conference on Autonomous Agents and Multiagent Systems (AAMAS)},
location = {SÃ£o Paulo, Brazil},
month = {May},
year = {2017},
abstract = {
In the multi-robot human guidance problem, a centralized
controller makes use of multiple robots to provide navigational
assistance to a human in order to reach a goal location.
Previous work used Markov Decision Processes (MDPs) to
construct a formalization for this problem, and evaluated
this framework in an abstract setting only, i.e. without
experiments using high-fidelity simulators or real humans.
Additionally, it was unable to handle multiple concurrent
requests and did not consider buildings with multiple floors.
The main contribution of this paper is the introduction of
an extended MDP framework for the multi-robot human
guidance problem, and its application using a realistic 3D
simulation environment and a real multi-robot system. The
MDP formulation presented in this paper includes support
for planning for multiple guidance requests concurrently as
well as requests that require a human to traverse multiple
floors. We evaluate this system using real humans controlling
simulated avatars, and provide a video demonstration
of the system implemented on real robots.
},
}

Elad Liebman, Piyush Khandelwal, M. Saar-Tsechansky, and Peter Stone, “Designing Better Playlists with Monte Carlo Tree Search,” in Proceedings of the Twenty-Ninth Conference On Innovative Applications Of Artificial Intelligence (IAAI-17), 2017.
[Bibtex]

@InProceedings{IAAI2017-eladlieb,
author = {Elad Liebman and Piyush Khandelwal and Maytal Saar-Tsechansky and Peter Stone},
title = {Designing Better Playlists with Monte Carlo Tree Search},
booktitle = {Proceedings of the Twenty-Ninth Conference On Innovative Applications Of Artificial Intelligence (IAAI-17)},
location = {San Francisco, USA},
month = {February},
year = {2017},
abstract = {
In recent years, there has been growing interest in the study of automated
playlist generation - music rec- ommender systems that focus on modeling
preferences over song sequences rather than on individual songs in isolation.
This paper addresses this problem by learn- ing personalized models on the
fly of both song and transition preferences, uniquely tailored to each userâ€™s
musical tastes. Playlist recommender systems typically include two main
components: i) a preference-learning component, and ii) a planning component
for select- ing the next song in the playlist sequence. While there has been
much work on the former, very little work has been devoted to the latter.
This paper bridges this gap by focusing on the planning aspect of
playlist gen- eration within the context of DJ-MC, our playlist rec-
ommendation application. This paper also introduces a new variant of
playlist recommendation, which in- corporates the notion of diversity and
novelty directly into the reward model. We empirically demonstrate that
the proposed planning approach significantly im- proves performance
compared to the DJ-MC baseline in two playlist recommendation settings,
increasing the usability of the framework in real world settings.
},
}

Shiqi Zhang, Piyush Khandelwal, and Peter Stone, “Dynamically Constructed (PO)MDPs for Adaptive Robot Planning,” in Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI), 2017.
[Bibtex]

@InProceedings{AAAI17-Zhang,
author = {Shiqi Zhang and Piyush Khandelwal and Peter Stone},
title = {Dynamically Constructed (PO)MDPs for Adaptive Robot Planning},
booktitle = {Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI)},
location = {San Francisco, CA},
month = {February},
year = {2017},
abstract = {
To operate in human-robot coexisting environments, intelligent robots need
to imultaneously reason with commonsense knowledge and plan under
uncertainty. Markov decision processes (MDPs) and partially observable
MDPs (POMDPs), are good at planning under uncertainty toward maximizing
long-term rewards; P-LOG, a declarative programming language under Answer
Set semantics, is strong in commonsense reasoning. In this paper, we
present a novel algorithm called iCORPP to dynamically reason about, and
construct (PO)MDPs using P-LOG. iCORPP successfully shields exogenous
domain attributes from (PO)MDPs, which limits computational complexity
and enables (PO)MDPs to adapt to the value changes these attributes
produce.We conduct a number of experimental trials using two example
problems in simulation and demonstrate iCORPP on a real robot. Results
show significant improvements compared to competitive baselines.
},
}

2016

Piyush Khandelwal, Elad Liebman, Scott Niekum, and Peter Stone, “On the Analysis of Complex Backup Strategies in Monte Carlo Tree Search,” in Proceedings of The 33rd International Conference on Machine Learning, 2016, pp. 1319-1328.
[Bibtex]

@inproceedings{ICML16-khandelwal,
title={On the Analysis of Complex Backup Strategies in Monte Carlo Tree Search},
author={Piyush Khandelwal and Elad Liebman and Scott Niekum and Peter Stone},
booktitle={Proceedings of The 33rd International Conference on Machine Learning},
pages={1319--1328},
location={New York City, NY, USA},
month={June},
year={2016},
abstract = {Over the past decade, Monte Carlo Tree Search (MCTS) and
specifically Upper Confidence Bound in Trees (UCT) have proven to be quite
effective in large probabilistic planning domains. In this paper, we focus on
how values are backpropagated in the MCTS tree, and apply complex return
strategies from the Reinforcement Learning (RL) literature to MCTS, producing 4
new MCTS variants. We demonstrate that in some probabilistic planning
benchmarks from the International Planning Competition (IPC), selecting a
MCTS variant with a backup strategy different from Monte Carlo averaging can
lead to substantially better results. We also propose a hypothesis for why
different backup strategies lead to different performance in particular
environments, and manipulate a carefully structured grid-world domain to
provide empirical evidence supporting our hypothesis.},
}

Shiqi Zhang, Piyush Khandelwal, and Peter Stone, “Dynamically Constructed (PO)MDPs for Adaptive Robot Planning,” in IJCAI’16 Workshop on Autonomous Mobile Service Robots, 2016.
[Bibtex]

@InProceedings{WSR16-szhang1,
author = {Shiqi Zhang and Piyush Khandelwal and Peter Stone},
title = {Dynamically Constructed (PO)MDPs for Adaptive Robot Planning},
booktitle = {IJCAI'16 Workshop on Autonomous Mobile Service Robots},
location = {New York City, USA},
month = {July},
year = {2016},
abstract = {
To operate in human-robot coexisting environments, intelligent robots need
to simultaneously reason with commonsense knowledge and plan under
uncertainty. Markov decision processes (MDPS) and partially observable
MDPs (POMDPs), are good at planning under uncertainty toward
maximizing long-term rewards; P-LOG, a declarative programming language
under Answer Set semantics, is strong in commonsense reasoning. In
this paper, we present a novel algorithm called DCPARP to dynamically
represent, reason about, and construct (PO)MDPs using P-LOG.
DCPARP successfully shields exogenous domain attributes from (PO)MDPs
so as to limit computational complexity, but still enables (PO)MDPs to
adapt to the value changes these attributes produce. We conduct a large
number of experimental trials using two example problems in simulation and
demonstrate DCPARP on a real robot. Results show significant improvements
compared to competitive baselines.
},
}

2015

Piyush Khandelwal, Samuel Barrett, and Peter Stone, “Leading the Way: An Efficient Multi-robot Guidance System,” in International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2015.
[Bibtex]

@InProceedings{AAMAS15-khandelwal,
author = {Piyush Khandelwal and Samuel Barrett and Peter Stone},
title = {Leading the Way: An Efficient Multi-robot Guidance System},
booktitle = {International Conference on Autonomous Agents and Multiagent Systems (AAMAS)},
location = {Istanbul, Turkey},
month = {May},
year = {2015},
abstract = {
Recent advances in service robotics have made it possible to deploy a large
number of mobile robots in indoor environments to perform tasks such as
delivery, maintenance and eldercare. If a centrally connected multi-robot
system is available, can it be effectively used to aid humans in other
on-demand tasks? In this paper, we demonstrate how individual service
robots in a multi-robot system can be temporarily reassigned from their
original task to help guide a human from one location to another in the
environment. We formulate this multi-robot treatment of the human guidance
problem as a Markov Decision Process (MDP). Solving the MDP produces a
policy to efficiently guide the human, but the state space size makes it
infeasible to optimally solve it. Instead, we use the Upper Confidence
bound for Trees (UCT) planner to obtain an approximate solution. We show
that this solution outperforms an approach that uses a single robot to
guide the human from start to finish.
},
url="http://www.cs.utexas.edu/~pstone/Papers/bib2html-links/AAMAS15-khandelwal.pdf"
}

Shiqi Zhang, Fankgai Yang, Piyush Khandelwal, and Peter Stone, “Mobile Robot Planning using Action Language BC with an Abstraction Hierarchy,” in Proceedings of the 13th International Conference on Logic Programming and Non-monotonic Reasoning (LPNMR), 2015.
[Bibtex]

@InProceedings{LPNMR15-zhang,
author = {Shiqi Zhang and Fangkai Yang and Piyush Khandelwal and Peter Stone},
title = {Mobile Robot Planning using Action Language BC with an Abstraction Hierarchy},
booktitle = {Proceedings of the 13th International Conference on Logic
Programming and Non-monotonic Reasoning (LPNMR)},
location = {Lexington, KY, USA},
month = {September},
year = {2015},
abstract = {
Planning in real-world environments can be challenging for intelligent
robots due to incomplete domain knowledge that results from unpredictable
domain dynamism, and due to lack of global observability. Action language BC
can be used for planning by formalizing the preconditions and (direct and
indirect) effects of actions, and is especially suited for planning in
robotic domains by incorporating defaults with the incomplete domain
knowledge. However, planning with BC is very computationally expensive,
especially when action costs are considered. We introduce algorithm PlanHG
for formalizing BC domains at different abstraction levels in order to trade
optimality for significant efficiency improvement when aiming to minimize
overall plan cost. We observe orders of magnitude improvement in efficiency
compared to a standard â€œflatâ€ planning approach.
},
url="http://www.cs.utexas.edu/~pstone/Papers/bib2html-links/LPNMR15-zhang.pdf"
links="<a href="https://youtu.be/-QpFj7BbiRU">[Demo Video]</a>",
}

2014

Piyush Khandelwal, Fankgai Yang, Matteo Leonetti, Vladimir Lifschitz, and Peter Stone, “Planning in Action Language ${\cal BC}$ while Learning Action Costs for Mobile Robots,” in International Conference on Automated Planning and Scheduling (ICAPS), 2014.
[Bibtex]

@InProceedings{ICAPS2014-khandelwal,
author = "Piyush Khandelwal and Fangkai Yang and Matteo Leonetti and Vladimir Lifschitz and Peter Stone",
title = "Planning in Action Language ${\cal BC}$ while Learning Action Costs for Mobile Robots",
booktitle = "International Conference on Automated Planning and Scheduling (ICAPS)",
url="http://www.cs.utexas.edu/users/piyushk/papers/itsc2012-dcarlino.pdf",
year = "2014",
url="http://www.cs.utexas.edu/~pstone/Papers/bib2html-links/ICAPS14-khandelwal.pdf"
}

Piyush Khandelwal and Peter Stone, “Multi-Robot Human Guidance using Topological Graphs,” in AAAI Spring Symposium on Qualitiative Representation for Robots, 2014.
[Bibtex]

@InProceedings{AAAIsymp14-khandelwal,
author = "Piyush Khandelwal and Peter Stone",
title = "Multi-Robot Human Guidance using Topological Graphs",
booktitle = "AAAI Spring Symposium on Qualitiative Representation for Robots",
year = "2014"
}

Fankgai Yang, Piyush Khandelwal, Matteo Leonetti, and Peter Stone, “Planning in Answer Set Programming while Learning Action Costs for Mobile Robots,” in AAAI Spring Symposium on Knowledge Representation and Reasoning in Robotics, 2014.
[Bibtex]

@InProceedings{AAAIsymp14-yang,
author = "Fangkai Yang and Piyush Khandelwal and Matteo Leonetti and Peter Stone",
title = "Planning in Answer Set Programming while Learning Action Costs for Mobile Robots",
booktitle = "AAAI Spring Symposium on Knowledge Representation and Reasoning in Robotics",
year = "2014"
}

Shiqi Zhang, Fankgai Yang, Piyush Khandelwal, and Peter Stone, “Mobile Robot Planning using Action Language ${\cal BC}$ with Hierarchical Domain Abstractions,” in The 7th Workshop on Answer Set Programming and Other Computing Paradigms (ASPOCP), 2014.
[Bibtex]

@InProceedings{ASPOCP14-zhang,
author = {Shiqi Zhang and Fangkai Yang and Piyush Khandelwal and Peter Stone},
title = {Mobile Robot Planning using Action Language ${\cal BC}$ with Hierarchical Domain Abstractions},
booktitle = {The 7th Workshop on Answer Set Programming and Other Computing Paradigms (ASPOCP)},
location = {Vienna, Austria},
month = {July},
year = {2014},
abstract = {
Action language ${\cal BC}$ provides an elegant way of formalizing robotic
domains which need to be expressed using default logic as well as indirect
and recursive action effects. However, generating plans efficiently for
large domains using ${\cal BC}$ can be challenging, even when
state-of-the-art answer set solvers are used. In this paper, we investigate
the computational gains achieved by describing task planning domains at
different abstraction levels using ${\cal BC}$, where lower levels describe
more domain details by adding fluents not included in higher levels and
actions at different levels are formalized independently. Two algorithms are
presented to efficiently calculate the near-optimal short and low-cost plans
respectively. We present a case study where at least an order of magnitude
speedup was achieved in a robot mail collection task using hierarchical
domain abstractions.
},
}

Samuel Barrett, Katie Genter, Yuchen He, Todd Hester, Piyush Khandelwal, Jacob Menashe, and Peter Stone, “The 2012 UT Austin Villa Code Release,” in RoboCup-2013: Robot Soccer World Cup XVII, Berlin, 2014.
[Bibtex]

@InProceedings{LNAI13-BarrettCodeRelease,
author = {Samuel Barrett and Katie Genter and Yuchen He and Todd Hester and Piyush Khandelwal and Jacob Menashe and Peter Stone},
title = {The 2012 {UT Austin Villa} Code Release},
booktitle = {{R}obo{C}up-2013: Robot Soccer World Cup {XVII}},
Publisher="Springer Verlag",
address="Berlin",
year = {2014},
series="Lecture Notes in Artificial Intelligence",
abstract={
In 2012, UT Austin Villa claimed the Standard Platform League championships at both the US Open and the 2012 RoboCup competition held in Mexico City. This paper describes the code release associated with the team and discusses the key contributions of the release. This release will enable teams entering the Standard Platform League and researchers using the Naos to have a solid foundation from which to start their work as well as providing useful modules to existing researchers and RoboCup teams. We expect it to be of particular interest because it includes the architecture, logic modules, and debugging tools that led to the team's success in 2012. This architecture is designed to be flexible and robust while enabling easy testing and debugging of code. The vision code was designed for easy use in creating color tables and debugging problems. A custom localization simulator that is included permits fast testing of full team scenarios. Also included is the kick engine which runs through a number of static joint poses and adapts them to the current location of the ball. This code release will provide a solid foundation for new RoboCup teams and for researchers that use the Naos.},
url="http://www.cs.utexas.edu/users/piyushk/papers/LNAI13-BarrettCodeRelease.pdf",
links="<a href=http://www.cs.utexas.edu/~AustinVilla/?p=downloads/source_code_and_binaries>[Code]</a>"
}

2013

Samuel Barrett, Katie Genter, Yuchen He, Todd Hester, Piyush Khandelwal, Jacob Menashe, and Peter Stone, “UT Austin Villa 2012: Standard Platform League World Champions,” in RoboCup-2012: Robot Soccer World Cup XVI, X. Chen, Peter Stone, L. E. Sucar, and T. V. der Zant, Eds., Berlin: Springer Verlag, 2013.
[Bibtex]

@incollection{LNAI13-Barrett,
author = {Samuel Barrett and Katie Genter and Yuchen He and Todd Hester and Piyush Khandelwal and Jacob Menashe and Peter Stone},
title = {UT Austin Villa 2012: Standard Platform League World Champions},
booktitle= "RoboCup-2012: Robot Soccer World Cup {XVI}",
Editor={Xiaoping Chen and Peter Stone and Luis Enrique Sucar and Tijn Van der Zant},
Publisher="Springer Verlag",
address="Berlin",
year="2013",
series="Lecture Notes in Artificial Intelligence",
abstract= {
In 2012, UT Austin Villa claimed Standard Platform League
championships at both the US Open and RoboCup 2012 in Mexico
City. This paper describes the key contributions that led to the team's
victories. First, UT Austin Villa's code base was developed on a solid
foundation with a flexible architecture that enables easy testing
and debugging of code. Next, the vision code was updated this year to
take advantage of the dual cameras and better processor of the new V4
Nao robots. To improve localization, a custom localization
simulator allowed us to implement and test a full team solution to
the challenge of both goals being the same color. The 2012 team made
use of Northern Bites' port of B-Human's walk engine, combined with
novel kicks from the walk. Finally, new behaviors and
strategies take advantage of opportunities for the robot to take time to
setup for a long kick, but kick very quickly when opponent robots are
nearby. The combination of these contributions led to the team's victories
in 2012.},
url="http://www.cs.utexas.edu/users/piyushk/papers/LNAI13-Barrett.pdf",
links="<a href=http://www.cs.utexas.edu/~AustinVilla/?p=downloads/source_code_and_binaries>[Code]</a>"
}

2012

Matthew Hausknecht, Piyush Khandelwal, Risto Miikkulainen, and Peter Stone, “Hyper-NEAT-GGP: A HyperNEAT-based Atari General Game Player,” in Genetic and Evolutionary Computation Conference (GECCO), 2012.
[Bibtex]

@InProceedings{GECCO12-Hausknecht,
title={Hyper-NEAT-GGP: A HyperNEAT-based Atari General Game Player},
author={Matthew Hausknecht and Piyush Khandelwal and Risto Miikkulainen
and Peter Stone},
booktitle={Genetic and Evolutionary Computation Conference (GECCO)},
url="http://www.cs.utexas.edu/users/piyushk/papers/GECCO12-Hausknecht.pdf",
year={2012},
abstract={This paper considers the challenge of enabling agents to
learn with as little domain-specific knowledge as possible.
The main contribution is HyperNEAT-GGP, a HyperNEAT-
based General Game Playing approach to Atari games. By
leveraging the geometric regularities present in the Atari
game screen, HyperNEAT ectively evolves policies for play-
ing two diㄦent Atari games, Asterix and Freeway. Results
show that HyperNEAT-GGP outperforms existing bench-
marks on these games. HyperNEAT-GGP represents a step
towards the ambitious goal of creating an agent capable of
learning and seamlessly transitioning between many diㄦ-
ent tasks.},
links="<a href=http://www.cs.utexas.edu/users/piyushk/papers/GECCO12-Hausknecht-slides.pdf>[Slides]</a>"
}

Dustin Carlino, Mike Depinet, Piyush Khandelwal, and Peter Stone, “Approximately Orchestrated Routing and Transportation Analyzer: Large-scale Traffic Simulation for Autonomous Vehicles,” in IEEE Intelligent Transportation Systems Conference (ITSC), 2012.
[Bibtex]

@InProceedings{ITSC2012-dcarlino,
author = {Dustin Carlino and Mike Depinet and Piyush Khandelwal and Peter Stone},
title = {Approximately Orchestrated Routing and Transportation Analyzer: Large-scale Traffic Simulation for Autonomous Vehicles},
booktitle = {IEEE Intelligent Transportation Systems Conference (ITSC)},
location = {Anchorage, Alaska, USA},
month = {September},
year = {2012},
abstract = {Autonomous vehicles have seen great advancements in recent years, and such
vehicles are now closer than ever to being commercially available. The advent of
driverless cars provides opportunities for optimizing traffic in ways not
possible before. This paper introduces an open source multiagent microscopic
traffic simulator called AORTA, which stands for Approximately
Orchestrated Routing and Transportation Analyzer, designed for optimizing
autonomous traffic at a city-wide scale. AORTA creates scale simulations of the
real world by generating maps using publicly available road data from
OpenStreetMap (OSM). This allows simulations to be set up through
AORTA for a desired region anywhere in the world in a matter of minutes. AORTA
allows for traffic optimization by creating intelligent behaviors for
individual driver agents and intersection policies to be followed by these
agents. These behaviors and policies define how agents interact with one
another, control when they cross intersections, and route agents to their
destination. This paper demonstrates a simple application using AORTA through
an experiment testing intersection policies at a city-wide scale.},
url="http://www.cs.utexas.edu/users/piyushk/papers/itsc2012-dcarlino.pdf",
links="<a href=http://code.google.com/p/road-rage/>[Code]</a> <a href=http://www.cs.utexas.edu/users/piyushk/papers/itsc2012-dcarlino-slides.pdf>[Slides]</a>"
}

Samuel Barrett, Katie Genter, Todd Hester, Piyush Khandelwal, Michael Quinlan, Peter Stone, and Mohan Sridharan, “Austin Villa 2011: Sharing is Caring: Better Awareness through Information Sharing,” The University of Texas at Austin, Department of Computer Sciences, AI Laboratory, UT-AI-TR-12-01, 2012.
[Bibtex]

@TechReport{UTAITR1201-sbarrett,
author="Samuel Barrett and Katie Genter and Todd Hester and Piyush
Khandelwal and Michael Quinlan and Peter Stone and Mohan Sridharan",
title="{A}ustin {V}illa 2011: Sharing is Caring: Better Awareness
through Information Sharing",
institution="The University of Texas at Austin, Department of Computer
Sciences, AI Laboratory",
number="UT-AI-TR-12-01",
year="2012",
month="January",
url="http://www.cs.utexas.edu/users/piyushk/papers/UTAITR1201-sbarrett.pdf",
note="Technical Report.",
abstract = {In 2008, UT Austin Villa entered a team in the ﬁrst Nao competition of the
Standard Platform League of the RoboCup competition. The team had previous
experience in RoboCup in the Aibo leagues. Using this past experience, the team
developed an entirely new codebase for the Nao. In 2009, UT Austin combined
forces with Texas Tech University, to form TT-UT Austin Villa. Austin Villa
won the 2009 US Open and placed fourth in the 2009 RoboCup competition
in Graz, Austria. In 2010 Austin Villa successfully defended our 1st place at
the 2010 US Open and improved to ﬁnish 3rd at RoboCup 2010 in Singapore.
Austin Villa reached the quarterﬁnals at RoboCup 2011 in Istanbul, Turkey
before falling to the eventual champions, B-Human. This report describes the
algorithms used in these tournaments, including the architecture, vision, motion,
localization, and behaviors.},
}

Piyush Khandelwal and Peter Stone, “A Low Cost Ground Truth Detection System Using the Kinect,” in RoboCup-2011: Robot Soccer World Cup XV, T. Roefer, N. M. Mayer, J. Savage, and U. Saranli, Eds., Berlin: Springer Verlag, 2012.
[Bibtex]

@incollection{LNAI11-piyush,
author = {Piyush Khandelwal and Peter Stone},
title = {A Low Cost Ground Truth Detection System Using the Kinect},
booktitle= "{R}obo{C}up-2011: Robot Soccer World Cup {XV}",
Editor={Thomas Roefer and Norbert Michael Mayer and Jesus Savage
and Uluc Saranli},
Publisher="Springer Verlag",
address="Berlin",
year="2012",
series="Lecture Notes in Artificial Intelligence",
abstract = {Ground truth detection systems can be a crucial step in
evaluating and improving algorithms for self-localization on mobile
robots. Selecting a ground truth system depends on its cost, as well
as on the detail and accuracy of the information it provides. In this
paper, we present a low cost, portable and real-time solution
constructed using the Microsoft Kinect RGB-D Sensor. We use this
system to find the location of robots and the orange ball in the
Standard Platform League (SPL) environment in the RoboCup competition.
This system is fairly easy to calibrate, and does not require any
special identifiers on the robots. We also provide a detailed
experimental analysis to measure the accuracy of the data provided by
this system. Although presented for the SPL, this system can be adapted
for use with any indoor structured environment where ground truth
information is required.},
url="http://www.cs.utexas.edu/users/piyushk/papers/LNAI11-piyush.pdf",
links="<a href=http://www.ros.org/wiki/austinvilla>[Code]</a> <a href=http://www.cs.utexas.edu/users/piyushk/papers/LNAI11-piyush-poster.pdf>[Poster]</a>",
}

2011

Samuel Barrett, Katie Genter, Matthew Hausknecht, Todd Hester, Piyush Khandelwal, Juhyun Lee, Michael Quinlan, Aibo Tian, Peter Stone, and Mohan Sridharan, “Austin Villa 2010 Standard Platform Team Report,” The University of Texas at Austin, Department of Computer Sciences, AI Laboratory, UT-AI-TR-11-01, 2011.
[Bibtex]

@TechReport{UTAITR1101-spl10,
author="Samuel Barrett and Katie Genter and Matthew Hausknecht and
Todd Hester and Piyush Khandelwal and Juhyun Lee and Michael Quinlan
and Aibo Tian and Peter Stone and Mohan Sridharan",
title="{A}ustin {V}illa 2010 Standard Platform Team Report",
institution="The University of Texas at Austin, Department of Computer
Sciences, AI Laboratory",
number="UT-AI-TR-11-01",
year="2011",
month="January",
abstract={In 2008, UT Austin Villa entered a team in the first
Nao competition of the Standard Platform League of the RoboCup
competition. The team had previous experience in RoboCup in the Aibo
leagues. Using this past experience, the team developed an entirely new
codebase for the Nao. In 2009, UT Austin combined forces with Texas Tech
University, to form TT-UT Austin Villa1. Austin Villa won the 2009 US
Open and placed fourth in the 2009 RoboCup competition in Graz, Austria.
In 2010 Austin Villa successfully defended our 1st place at the 2010 US
Open and improved to finish 3rd at RoboCup 2010 in Singapore. This
report describes the algorithms used in these tournaments, including the
architecture, vision, motion, localization, and behaviors.},
url="http://www.cs.utexas.edu/users/piyushk/papers/UTAITR1101-spl10.pdf",
note="Technical Report.",
}

2010

Piyush Khandelwal, Matthew Hausknecht, Juhyun Lee, Aibo Tian, and Peter Stone, “Vision Calibration and Processing on a Humanoid Soccer Robot,” in The Fifth Workshop on Humanoid Soccer Robots at International Conference on Humanoid Robots, 2010.
[Bibtex]

@InProceedings{HUMANOIDS10-khandelwal,
author = "Piyush Khandelwal and Matthew Hausknecht and Juhyun Lee
and Aibo Tian and Peter Stone",
title = "Vision Calibration and Processing on a Humanoid Soccer Robot",
booktitle = "The Fifth Workshop on Humanoid Soccer Robots at International Conference on Humanoid Robots",
location = "Nashville, TN",
month = "December",
year = "2010",
abstract = {In RoboCup, the problem of quickly and accurately
processing visual data continues to pose a signiﬁcant challenge.
The Aldebaran Nao, currently used by the Standard Platform League,
has two cameras for visual input, of which only one has been typically
used. The integration of both cameras presents a new opportunity but
also a challenge. While it is possible to obtain better information
using both cameras, more cameras require more work to calibrate. We
propose a novel camera calibration algorithm which automatically tunes
a camera such that its color perceptions match those of another camera.
Additionally, recent vision challenges introduced in RoboCup have
necessitated the use of higher resolution images. We build on existing
work in color based segmentation and present novel extensions to
facilitate the move to higher resolution images, including memory
optimizations, fast line and curve detection, and differentiation via
robot pose based transformations. All work presented in this paper was
successfully used by the UT Austin Villa Robot Soccer team, which
secured 3rd place overall and 2nd place in the technical challenges at
RoboCup 2010.},
url="http://www.cs.utexas.edu/users/piyushk/papers/HUMANOIDS10-khandelwal.pdf",
}