20161014IROS_WS

Komei Sugiura
Komei SugiuraAssociate Professor
Cloud Robotics for Building
Conversational Robots
Komei Sugiura
National Institute of Information and Communications Tech., Japan
Beyond the Language Barrier:
NICT’s free software and cloud services
1. Speech to speech translation system: VoiceTra (2010)
>1M downloads.
High performance in translation to/from Asian languages
2. MCML Speech interaction SDK (2013)
The SDK enable the user to build WFST-
based multilingual dialogue systems.
3. Smartphone dialogue apps (2011)
Spoken dialogues and recommendation in tourist
guidance domains
4. Cloud robotics platform rospeex (2013)
40K unique users. Top level quality as dialogue-based TTS
in Japanese.
[New] Automatic captioning SDK for developers
http://www2.nict.go.jp/astrec-ast/mcml-sdk/index_en.html
Free of charge, but authentication required
Video
Motivation:
How can we build communicative robots to help people?
Smartphones and other consumer devices
Speech interfaces give benefit to
consumers
cf. Market size of speech recognition
¥88B@2013→¥170B@2018 (€1.5B)*
Show me today’s
schedule
* Estimation by NEDO, TSC Foresight Vol.8, 2015
Sushi restaurants
around here
Benefit for
QA/search
GPS Contacts Other context
info.
Current communication with robots
Insufficient benefit to consumers
??
??Throw
them away.
Is there any milk
in the fridge?
• Bad recognition accuracy
• User needs to specify [what,
where, how] as well as start/end
conditions
ROSPEEX:
A CLOUD ROBOTICS PLATFORM FOR
MULTILINGUAL SPOKEN DIALOGUES
5
Background: Speech recognition/synthesis is bottleneck
for reducing cost in human-robot interactions
• Synthesized speech sounds
monotonous and unfriendly
• Speech recognition does not work
well than expected
XIMERA 3
(Text-reading)
Voice
talent
Target = Interactions with service robots
Rospeex:
A cloud robotics platform for multilingual spoken dialogues
• >40,000 unique users have used rospeex
• WER =7.9% (accuracy=92.1%) for IWSLT tst2011 (1st Place
Winner in IWSLT12, 13, 14)
• Top-level quality dialogue-oriented TTS
Python & C++ samples
are available
rospeex Search
* Free of charge for research
Rospeex’s positioning in robot dialogue quadrants
8
Cloud APIs
(Google, Microsoft, IBM,
NTT docomo, Wit.ai,…)
Free software
Commercial software
OpenHRI,
PocketSphinx, Festival
Cloud-based
Stand-alone
Robot
middleware-
compatible
Incompatibl
e
Does not work with
very low-spec PCs 
Robotics-specific
logs are lost 
Authentication
Low quality 
Expensive 
8
Distribution of rospeex users
rospeex applications (40k unique users)
Conversational agents in elderly care
facilities, service robots, humanoid,
dialogue agents, speech interface for car
navigation systems or smarthome devices,
…
Analysis: TTS requests depend heavily on individuals
• Question: Do developers use same sentences for TTS? If so, we can
speed up by introducing local cache.
Cache hit
Cache miss
• Analysis on top 88 users
– New requests = 50.4% on average
– An individual uses max. 200 unique sentences
Without a cloud platform, we
cannot conduct large-scale
analysis of robot developers
Introducing cache will
reduce comm. time
MULTIMODAL SPOKEN DIALOGUES
WITH ROBOTS
10
Multimodal language understanding
Kollar+ 2010
HRI 2010 Best Paper
• Input: Text, LRF, Image
• Output: path planning
• E.g. “Go down the hallway”
Iwahashi &
Sugiura+ 2010
• Input: Image and speech
• Output: object manipulation
• E.g. “Place-on Elmo”
Visual QA[2015-] • Input: Image and question
• Output: Answer
• E.g. “How many elephants are there?” -> “2”
Video
LCore: Multimodal Robot Language Acquisition
[Iwahashi, Sugiura, et al 2010]
Key features
• Fully grounded vocabulary
• Imitation learning
• Incremental & interactive learning
• Language independent
• Learning when to ask questions
12
HMM “Place-
on” Place X on Y
Imitation learning for spoken language understanding:
Re-ranking hypotheses using planned trajectories’ likelihood
• Transformation of reference-point-dependent HMMs*
– Input: verb ID, object ID(s)
e.g. <place-on, Object 1, Object 3>
– Transforms HMM from intrinsic coordinate system into world
coordinate system
HMM “Place-on”
World CS
Situation
Place X on Y
* Sugiura et al, IROS 2011 RoboCup Best Paper
HMM-based trajectory generation using dynamic features*
: state sequence
: HMM parameters
: time series of
(position,velocity,acceleration)
Maximum likelihood trajectory
*Tokuda, K. et al, “Speech parameter generation algorithms for HMM-based speech synthesis”, 2000
: vector of mean vectors
: matrix of covariance
matrices of each OPDF
: matrix of coefficients in
difference approximation
: time series of position
ROBOCUP@HOME
BUILDING DOMESTIC SERVICE ROBOTS
15
RoboCup@Home: Benchmark tests for domestic robots
• RoboCup@Home: The largest competition for domestic robots
– One of the major RoboCup leagues
– Focuses on human-robot interaction and mobile manipulation
– Robots are evaluated by 8 standardized and 3 demonstration tasks
• Scientific challenges
– Navigation in unknown environments (e.g. real shop), handling
everyday objects, spoken dialogues in very noisy environments, …
16
RoboCup@Home Standard Platform Leagues start in 2017
• Many teams need low-cost standardized platforms
• Companies know NAO’s success after selected as soccer-
Standard Platform (Softbank bought Aldebaran @100M USD )
Toyota HSR
• Main use case = partner robot for those who need care
• Lease-based
Softbank Pepper
• Already deployed in restaurants and shops
• Very low price
Both compatible with ROS
CFPs for HSR/Pepper users will be open soon
Summary
• Data-driven approaches
• Multimodal spoken dialogue with robots
• RoboCup and domestic service robots
• …and we’re hiring!
1 of 18

Recommended

New challenge in RoboCup 2017 Nagoya: RoboCup@Home Standard Platform by
New challenge in RoboCup 2017 Nagoya: RoboCup@Home Standard PlatformNew challenge in RoboCup 2017 Nagoya: RoboCup@Home Standard Platform
New challenge in RoboCup 2017 Nagoya: RoboCup@Home Standard PlatformKomei Sugiura
832 views7 slides
Cloud Robotics for Human-Robot Dialogues by
Cloud Robotics for Human-Robot DialoguesCloud Robotics for Human-Robot Dialogues
Cloud Robotics for Human-Robot DialoguesKomei Sugiura
495 views8 slides
AI & robotics: Past, Present and Future by
AI & robotics: Past, Present and FutureAI & robotics: Past, Present and Future
AI & robotics: Past, Present and FutureHongmei He
1.1K views45 slides
rospeex: a cloud-based speech communication toolkit for ROS by
rospeex: a cloud-based speech communication toolkit for ROSrospeex: a cloud-based speech communication toolkit for ROS
rospeex: a cloud-based speech communication toolkit for ROSKomei Sugiura
1.8K views9 slides
NLP for Robotics by
NLP for RoboticsNLP for Robotics
NLP for RoboticsUniversity of Colorado at Boulder
2.3K views13 slides
Tutorial on Text Categorization, EACL, 2003 by
Tutorial on Text Categorization, EACL, 2003Tutorial on Text Categorization, EACL, 2003
Tutorial on Text Categorization, EACL, 2003Jose Maria Gomez Hidalgo
1.5K views57 slides

More Related Content

Similar to 20161014IROS_WS

An ontology-based approach to improve the accessibility of ROS-based robotic ... by
An ontology-based approach to improve the accessibility of ROS-based robotic ...An ontology-based approach to improve the accessibility of ROS-based robotic ...
An ontology-based approach to improve the accessibility of ROS-based robotic ...Vrije Universiteit Amsterdam
567 views25 slides
Efficient Intralingual Text To Speech Web Podcasting And Recording by
Efficient Intralingual Text To Speech Web Podcasting And RecordingEfficient Intralingual Text To Speech Web Podcasting And Recording
Efficient Intralingual Text To Speech Web Podcasting And RecordingIOSR Journals
347 views3 slides
An Integrated Prototyping Environment For Programmable Automation by
An Integrated Prototyping Environment For Programmable AutomationAn Integrated Prototyping Environment For Programmable Automation
An Integrated Prototyping Environment For Programmable AutomationMeshDynamics
371 views11 slides
robocity2013-jderobot by
robocity2013-jderobotrobocity2013-jderobot
robocity2013-jderobotMaikel González Baile
271 views25 slides
Iitdmj 1 by
Iitdmj 1Iitdmj 1
Iitdmj 1Ram Yadav
1.1K views17 slides
IRJET- Virtual Vision for Blinds by
IRJET- Virtual Vision for BlindsIRJET- Virtual Vision for Blinds
IRJET- Virtual Vision for BlindsIRJET Journal
15 views4 slides

Similar to 20161014IROS_WS(20)

Efficient Intralingual Text To Speech Web Podcasting And Recording by IOSR Journals
Efficient Intralingual Text To Speech Web Podcasting And RecordingEfficient Intralingual Text To Speech Web Podcasting And Recording
Efficient Intralingual Text To Speech Web Podcasting And Recording
IOSR Journals347 views
An Integrated Prototyping Environment For Programmable Automation by MeshDynamics
An Integrated Prototyping Environment For Programmable AutomationAn Integrated Prototyping Environment For Programmable Automation
An Integrated Prototyping Environment For Programmable Automation
MeshDynamics371 views
Iitdmj 1 by Ram Yadav
Iitdmj 1Iitdmj 1
Iitdmj 1
Ram Yadav1.1K views
IRJET- Virtual Vision for Blinds by IRJET Journal
IRJET- Virtual Vision for BlindsIRJET- Virtual Vision for Blinds
IRJET- Virtual Vision for Blinds
IRJET Journal15 views
Building Robotics Application at Scale using OpenSource from Zero to Hero by Alex Barbosa Coqueiro
Building Robotics Application at Scale using OpenSource from Zero to HeroBuilding Robotics Application at Scale using OpenSource from Zero to Hero
Building Robotics Application at Scale using OpenSource from Zero to Hero
SOFIA - Semantic Technologies and Techniques for Interoperable Information in... by Sofia Eu
SOFIA - Semantic Technologies and Techniques for Interoperable Information in...SOFIA - Semantic Technologies and Techniques for Interoperable Information in...
SOFIA - Semantic Technologies and Techniques for Interoperable Information in...
Sofia Eu527 views
Robots in Human Environments by Andreas Heil
Robots in Human EnvironmentsRobots in Human Environments
Robots in Human Environments
Andreas Heil775 views
Live, Work, Play with Intelligent Robots by NUS-ISS
Live, Work, Play with Intelligent RobotsLive, Work, Play with Intelligent Robots
Live, Work, Play with Intelligent Robots
NUS-ISS122 views
Session 2.1 ontological representation of the telecom domain for advanced a... by semanticsconference
Session 2.1   ontological representation of the telecom domain for advanced a...Session 2.1   ontological representation of the telecom domain for advanced a...
Session 2.1 ontological representation of the telecom domain for advanced a...
MR + AI: Machine Learning for Language in HoloLens & VR Apps by Nick Landry
MR + AI: Machine Learning for Language in HoloLens & VR AppsMR + AI: Machine Learning for Language in HoloLens & VR Apps
MR + AI: Machine Learning for Language in HoloLens & VR Apps
Nick Landry1.7K views
HoloLens.pdf by Vishwas N
HoloLens.pdfHoloLens.pdf
HoloLens.pdf
Vishwas N16 views
Mobility today & what's next. Application ecosystems. by Petru Jucovschi
Mobility today & what's next.Application ecosystems.Mobility today & what's next.Application ecosystems.
Mobility today & what's next. Application ecosystems.
Petru Jucovschi682 views
Figure 1 by butest
Figure 1Figure 1
Figure 1
butest462 views
Figure 1 by butest
Figure 1Figure 1
Figure 1
butest479 views
Figure 1 by butest
Figure 1Figure 1
Figure 1
butest704 views

More from Komei Sugiura

ロボティクスにおける言語の利活用 by
ロボティクスにおける言語の利活用ロボティクスにおける言語の利活用
ロボティクスにおける言語の利活用Komei Sugiura
2.8K views36 slides
生活支援ロボットにおける 大規模データ収集に向けて by
生活支援ロボットにおける大規模データ収集に向けて生活支援ロボットにおける大規模データ収集に向けて
生活支援ロボットにおける 大規模データ収集に向けてKomei Sugiura
1.4K views30 slides
生活支援ロボットのマルチモーダル言語理解技術 by
生活支援ロボットのマルチモーダル言語理解技術生活支援ロボットのマルチモーダル言語理解技術
生活支援ロボットのマルチモーダル言語理解技術Komei Sugiura
1K views33 slides
SuMo-SS: Submodular Optimization Sensor Scattering for Deploying Sensor Netwo... by
SuMo-SS: Submodular Optimization Sensor Scattering for Deploying Sensor Netwo...SuMo-SS: Submodular Optimization Sensor Scattering for Deploying Sensor Netwo...
SuMo-SS: Submodular Optimization Sensor Scattering for Deploying Sensor Netwo...Komei Sugiura
241 views9 slides
ロボットの音声コミュニケーション技術:言葉や能力の壁を越えるデータ指向知能に向けて by
ロボットの音声コミュニケーション技術:言葉や能力の壁を越えるデータ指向知能に向けてロボットの音声コミュニケーション技術:言葉や能力の壁を越えるデータ指向知能に向けて
ロボットの音声コミュニケーション技術:言葉や能力の壁を越えるデータ指向知能に向けてKomei Sugiura
2.5K views37 slides
Spatio-Temporal Pseudo Relevance Feedback for Large-Scale and Heterogeneous S... by
Spatio-Temporal Pseudo Relevance Feedback for Large-Scale and Heterogeneous S...Spatio-Temporal Pseudo Relevance Feedback for Large-Scale and Heterogeneous S...
Spatio-Temporal Pseudo Relevance Feedback for Large-Scale and Heterogeneous S...Komei Sugiura
465 views16 slides

More from Komei Sugiura(19)

ロボティクスにおける言語の利活用 by Komei Sugiura
ロボティクスにおける言語の利活用ロボティクスにおける言語の利活用
ロボティクスにおける言語の利活用
Komei Sugiura2.8K views
生活支援ロボットにおける 大規模データ収集に向けて by Komei Sugiura
生活支援ロボットにおける大規模データ収集に向けて生活支援ロボットにおける大規模データ収集に向けて
生活支援ロボットにおける 大規模データ収集に向けて
Komei Sugiura1.4K views
生活支援ロボットのマルチモーダル言語理解技術 by Komei Sugiura
生活支援ロボットのマルチモーダル言語理解技術生活支援ロボットのマルチモーダル言語理解技術
生活支援ロボットのマルチモーダル言語理解技術
Komei Sugiura1K views
SuMo-SS: Submodular Optimization Sensor Scattering for Deploying Sensor Netwo... by Komei Sugiura
SuMo-SS: Submodular Optimization Sensor Scattering for Deploying Sensor Netwo...SuMo-SS: Submodular Optimization Sensor Scattering for Deploying Sensor Netwo...
SuMo-SS: Submodular Optimization Sensor Scattering for Deploying Sensor Netwo...
Komei Sugiura241 views
ロボットの音声コミュニケーション技術:言葉や能力の壁を越えるデータ指向知能に向けて by Komei Sugiura
ロボットの音声コミュニケーション技術:言葉や能力の壁を越えるデータ指向知能に向けてロボットの音声コミュニケーション技術:言葉や能力の壁を越えるデータ指向知能に向けて
ロボットの音声コミュニケーション技術:言葉や能力の壁を越えるデータ指向知能に向けて
Komei Sugiura2.5K views
Spatio-Temporal Pseudo Relevance Feedback for Large-Scale and Heterogeneous S... by Komei Sugiura
Spatio-Temporal Pseudo Relevance Feedback for Large-Scale and Heterogeneous S...Spatio-Temporal Pseudo Relevance Feedback for Large-Scale and Heterogeneous S...
Spatio-Temporal Pseudo Relevance Feedback for Large-Scale and Heterogeneous S...
Komei Sugiura465 views
言葉や能力の壁を越えるデータ指向知能 by Komei Sugiura
言葉や能力の壁を越えるデータ指向知能言葉や能力の壁を越えるデータ指向知能
言葉や能力の壁を越えるデータ指向知能
Komei Sugiura677 views
20160907rsj16ロボット聴覚OS by Komei Sugiura
20160907rsj16ロボット聴覚OS20160907rsj16ロボット聴覚OS
20160907rsj16ロボット聴覚OS
Komei Sugiura825 views
20160606劣モジュラ性を利用したドローンによるばらまき型センサ配置 by Komei Sugiura
20160606劣モジュラ性を利用したドローンによるばらまき型センサ配置20160606劣モジュラ性を利用したドローンによるばらまき型センサ配置
20160606劣モジュラ性を利用したドローンによるばらまき型センサ配置
Komei Sugiura2.6K views
20160221statistic imitation learning and human-robot communication by Komei Sugiura
20160221statistic imitation learning and human-robot communication20160221statistic imitation learning and human-robot communication
20160221statistic imitation learning and human-robot communication
Komei Sugiura2.8K views
20140513大規模異分野データ横断検索における時空間情報を用いた擬似適合性フィードバック by Komei Sugiura
20140513大規模異分野データ横断検索における時空間情報を用いた擬似適合性フィードバック20140513大規模異分野データ横断検索における時空間情報を用いた擬似適合性フィードバック
20140513大規模異分野データ横断検索における時空間情報を用いた擬似適合性フィードバック
Komei Sugiura2.5K views
20150531Deep Recurrent Neural Networkによる環境モニタリングデータの予測 by Komei Sugiura
20150531Deep Recurrent Neural Networkによる環境モニタリングデータの予測20150531Deep Recurrent Neural Networkによる環境モニタリングデータの予測
20150531Deep Recurrent Neural Networkによる環境モニタリングデータの予測
Komei Sugiura2.6K views
階層型評価構造に基づく観光スポット推薦システムの構築と長期実証実験 by Komei Sugiura
階層型評価構造に基づく観光スポット推薦システムの構築と長期実証実験階層型評価構造に基づく観光スポット推薦システムの構築と長期実証実験
階層型評価構造に基づく観光スポット推薦システムの構築と長期実証実験
Komei Sugiura2.4K views
実世界の意味を扱う理論と機械知能の構築 by Komei Sugiura
実世界の意味を扱う理論と機械知能の構築実世界の意味を扱う理論と機械知能の構築
実世界の意味を扱う理論と機械知能の構築
Komei Sugiura5K views
20151129インテリジェントホームロボティクス研究会 by Komei Sugiura
20151129インテリジェントホームロボティクス研究会20151129インテリジェントホームロボティクス研究会
20151129インテリジェントホームロボティクス研究会
Komei Sugiura5.2K views
Japan Robot Week 2014けいはんなロボットフォーラム by Komei Sugiura
Japan Robot Week 2014けいはんなロボットフォーラムJapan Robot Week 2014けいはんなロボットフォーラム
Japan Robot Week 2014けいはんなロボットフォーラム
Komei Sugiura4.1K views
Language acquisition framework for robots: From grounded language acquisition... by Komei Sugiura
Language acquisition framework for robots: From grounded language acquisition...Language acquisition framework for robots: From grounded language acquisition...
Language acquisition framework for robots: From grounded language acquisition...
Komei Sugiura940 views
Introduction to RoboCup@Home by Komei Sugiura
Introduction to RoboCup@HomeIntroduction to RoboCup@Home
Introduction to RoboCup@Home
Komei Sugiura432 views
ロボカップ@ホーム入門 by Komei Sugiura
ロボカップ@ホーム入門ロボカップ@ホーム入門
ロボカップ@ホーム入門
Komei Sugiura2.8K views

Recently uploaded

Business Analyst Series 2023 - Week 4 Session 7 by
Business Analyst Series 2023 -  Week 4 Session 7Business Analyst Series 2023 -  Week 4 Session 7
Business Analyst Series 2023 - Week 4 Session 7DianaGray10
80 views31 slides
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue by
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlueMigrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlueShapeBlue
96 views20 slides
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P... by
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...ShapeBlue
82 views62 slides
20231123_Camunda Meetup Vienna.pdf by
20231123_Camunda Meetup Vienna.pdf20231123_Camunda Meetup Vienna.pdf
20231123_Camunda Meetup Vienna.pdfPhactum Softwareentwicklung GmbH
46 views73 slides
Confidence in CloudStack - Aron Wagner, Nathan Gleason - Americ by
Confidence in CloudStack - Aron Wagner, Nathan Gleason - AmericConfidence in CloudStack - Aron Wagner, Nathan Gleason - Americ
Confidence in CloudStack - Aron Wagner, Nathan Gleason - AmericShapeBlue
41 views9 slides
Digital Personal Data Protection (DPDP) Practical Approach For CISOs by
Digital Personal Data Protection (DPDP) Practical Approach For CISOsDigital Personal Data Protection (DPDP) Practical Approach For CISOs
Digital Personal Data Protection (DPDP) Practical Approach For CISOsPriyanka Aash
81 views59 slides

Recently uploaded(20)

Business Analyst Series 2023 - Week 4 Session 7 by DianaGray10
Business Analyst Series 2023 -  Week 4 Session 7Business Analyst Series 2023 -  Week 4 Session 7
Business Analyst Series 2023 - Week 4 Session 7
DianaGray1080 views
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue by ShapeBlue
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlueMigrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue
ShapeBlue96 views
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P... by ShapeBlue
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...
ShapeBlue82 views
Confidence in CloudStack - Aron Wagner, Nathan Gleason - Americ by ShapeBlue
Confidence in CloudStack - Aron Wagner, Nathan Gleason - AmericConfidence in CloudStack - Aron Wagner, Nathan Gleason - Americ
Confidence in CloudStack - Aron Wagner, Nathan Gleason - Americ
ShapeBlue41 views
Digital Personal Data Protection (DPDP) Practical Approach For CISOs by Priyanka Aash
Digital Personal Data Protection (DPDP) Practical Approach For CISOsDigital Personal Data Protection (DPDP) Practical Approach For CISOs
Digital Personal Data Protection (DPDP) Practical Approach For CISOs
Priyanka Aash81 views
KVM Security Groups Under the Hood - Wido den Hollander - Your.Online by ShapeBlue
KVM Security Groups Under the Hood - Wido den Hollander - Your.OnlineKVM Security Groups Under the Hood - Wido den Hollander - Your.Online
KVM Security Groups Under the Hood - Wido den Hollander - Your.Online
ShapeBlue102 views
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N... by James Anderson
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...
James Anderson133 views
Extending KVM Host HA for Non-NFS Storage - Alex Ivanov - StorPool by ShapeBlue
Extending KVM Host HA for Non-NFS Storage -  Alex Ivanov - StorPoolExtending KVM Host HA for Non-NFS Storage -  Alex Ivanov - StorPool
Extending KVM Host HA for Non-NFS Storage - Alex Ivanov - StorPool
ShapeBlue40 views
Keynote Talk: Open Source is Not Dead - Charles Schulz - Vates by ShapeBlue
Keynote Talk: Open Source is Not Dead - Charles Schulz - VatesKeynote Talk: Open Source is Not Dead - Charles Schulz - Vates
Keynote Talk: Open Source is Not Dead - Charles Schulz - Vates
ShapeBlue119 views
DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti... by ShapeBlue
DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti...DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti...
DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti...
ShapeBlue46 views
Webinar : Desperately Seeking Transformation - Part 2: Insights from leading... by The Digital Insurer
Webinar : Desperately Seeking Transformation - Part 2:  Insights from leading...Webinar : Desperately Seeking Transformation - Part 2:  Insights from leading...
Webinar : Desperately Seeking Transformation - Part 2: Insights from leading...
Why and How CloudStack at weSystems - Stephan Bienek - weSystems by ShapeBlue
Why and How CloudStack at weSystems - Stephan Bienek - weSystemsWhy and How CloudStack at weSystems - Stephan Bienek - weSystems
Why and How CloudStack at weSystems - Stephan Bienek - weSystems
ShapeBlue111 views
State of the Union - Rohit Yadav - Apache CloudStack by ShapeBlue
State of the Union - Rohit Yadav - Apache CloudStackState of the Union - Rohit Yadav - Apache CloudStack
State of the Union - Rohit Yadav - Apache CloudStack
ShapeBlue145 views
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue by ShapeBlue
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlueCloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue
ShapeBlue46 views
VNF Integration and Support in CloudStack - Wei Zhou - ShapeBlue by ShapeBlue
VNF Integration and Support in CloudStack - Wei Zhou - ShapeBlueVNF Integration and Support in CloudStack - Wei Zhou - ShapeBlue
VNF Integration and Support in CloudStack - Wei Zhou - ShapeBlue
ShapeBlue85 views
Igniting Next Level Productivity with AI-Infused Data Integration Workflows by Safe Software
Igniting Next Level Productivity with AI-Infused Data Integration Workflows Igniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration Workflows
Safe Software344 views
Backroll, News and Demo - Pierre Charton, Matthias Dhellin, Ousmane Diarra - ... by ShapeBlue
Backroll, News and Demo - Pierre Charton, Matthias Dhellin, Ousmane Diarra - ...Backroll, News and Demo - Pierre Charton, Matthias Dhellin, Ousmane Diarra - ...
Backroll, News and Demo - Pierre Charton, Matthias Dhellin, Ousmane Diarra - ...
ShapeBlue83 views

20161014IROS_WS

  • 1. Cloud Robotics for Building Conversational Robots Komei Sugiura National Institute of Information and Communications Tech., Japan
  • 2. Beyond the Language Barrier: NICT’s free software and cloud services 1. Speech to speech translation system: VoiceTra (2010) >1M downloads. High performance in translation to/from Asian languages 2. MCML Speech interaction SDK (2013) The SDK enable the user to build WFST- based multilingual dialogue systems. 3. Smartphone dialogue apps (2011) Spoken dialogues and recommendation in tourist guidance domains 4. Cloud robotics platform rospeex (2013) 40K unique users. Top level quality as dialogue-based TTS in Japanese.
  • 3. [New] Automatic captioning SDK for developers http://www2.nict.go.jp/astrec-ast/mcml-sdk/index_en.html Free of charge, but authentication required Video
  • 4. Motivation: How can we build communicative robots to help people? Smartphones and other consumer devices Speech interfaces give benefit to consumers cf. Market size of speech recognition ¥88B@2013→¥170B@2018 (€1.5B)* Show me today’s schedule * Estimation by NEDO, TSC Foresight Vol.8, 2015 Sushi restaurants around here Benefit for QA/search GPS Contacts Other context info. Current communication with robots Insufficient benefit to consumers ?? ??Throw them away. Is there any milk in the fridge? • Bad recognition accuracy • User needs to specify [what, where, how] as well as start/end conditions
  • 5. ROSPEEX: A CLOUD ROBOTICS PLATFORM FOR MULTILINGUAL SPOKEN DIALOGUES 5
  • 6. Background: Speech recognition/synthesis is bottleneck for reducing cost in human-robot interactions • Synthesized speech sounds monotonous and unfriendly • Speech recognition does not work well than expected XIMERA 3 (Text-reading) Voice talent Target = Interactions with service robots
  • 7. Rospeex: A cloud robotics platform for multilingual spoken dialogues • >40,000 unique users have used rospeex • WER =7.9% (accuracy=92.1%) for IWSLT tst2011 (1st Place Winner in IWSLT12, 13, 14) • Top-level quality dialogue-oriented TTS Python & C++ samples are available rospeex Search * Free of charge for research
  • 8. Rospeex’s positioning in robot dialogue quadrants 8 Cloud APIs (Google, Microsoft, IBM, NTT docomo, Wit.ai,…) Free software Commercial software OpenHRI, PocketSphinx, Festival Cloud-based Stand-alone Robot middleware- compatible Incompatibl e Does not work with very low-spec PCs  Robotics-specific logs are lost  Authentication Low quality  Expensive  8 Distribution of rospeex users rospeex applications (40k unique users) Conversational agents in elderly care facilities, service robots, humanoid, dialogue agents, speech interface for car navigation systems or smarthome devices, …
  • 9. Analysis: TTS requests depend heavily on individuals • Question: Do developers use same sentences for TTS? If so, we can speed up by introducing local cache. Cache hit Cache miss • Analysis on top 88 users – New requests = 50.4% on average – An individual uses max. 200 unique sentences Without a cloud platform, we cannot conduct large-scale analysis of robot developers Introducing cache will reduce comm. time
  • 11. Multimodal language understanding Kollar+ 2010 HRI 2010 Best Paper • Input: Text, LRF, Image • Output: path planning • E.g. “Go down the hallway” Iwahashi & Sugiura+ 2010 • Input: Image and speech • Output: object manipulation • E.g. “Place-on Elmo” Visual QA[2015-] • Input: Image and question • Output: Answer • E.g. “How many elephants are there?” -> “2” Video
  • 12. LCore: Multimodal Robot Language Acquisition [Iwahashi, Sugiura, et al 2010] Key features • Fully grounded vocabulary • Imitation learning • Incremental & interactive learning • Language independent • Learning when to ask questions 12
  • 13. HMM “Place- on” Place X on Y Imitation learning for spoken language understanding: Re-ranking hypotheses using planned trajectories’ likelihood • Transformation of reference-point-dependent HMMs* – Input: verb ID, object ID(s) e.g. <place-on, Object 1, Object 3> – Transforms HMM from intrinsic coordinate system into world coordinate system HMM “Place-on” World CS Situation Place X on Y * Sugiura et al, IROS 2011 RoboCup Best Paper
  • 14. HMM-based trajectory generation using dynamic features* : state sequence : HMM parameters : time series of (position,velocity,acceleration) Maximum likelihood trajectory *Tokuda, K. et al, “Speech parameter generation algorithms for HMM-based speech synthesis”, 2000 : vector of mean vectors : matrix of covariance matrices of each OPDF : matrix of coefficients in difference approximation : time series of position
  • 16. RoboCup@Home: Benchmark tests for domestic robots • RoboCup@Home: The largest competition for domestic robots – One of the major RoboCup leagues – Focuses on human-robot interaction and mobile manipulation – Robots are evaluated by 8 standardized and 3 demonstration tasks • Scientific challenges – Navigation in unknown environments (e.g. real shop), handling everyday objects, spoken dialogues in very noisy environments, … 16
  • 17. RoboCup@Home Standard Platform Leagues start in 2017 • Many teams need low-cost standardized platforms • Companies know NAO’s success after selected as soccer- Standard Platform (Softbank bought Aldebaran @100M USD ) Toyota HSR • Main use case = partner robot for those who need care • Lease-based Softbank Pepper • Already deployed in restaurants and shops • Very low price Both compatible with ROS CFPs for HSR/Pepper users will be open soon
  • 18. Summary • Data-driven approaches • Multimodal spoken dialogue with robots • RoboCup and domestic service robots • …and we’re hiring!