Download presentation
Presentation is loading. Please wait.
Published byEmmeline Heath Modified over 9 years ago
1
1 29-8-2015 Socio-Cognitive Robot Architectures Koen V. Hindriks 15-12-2010 An Exploratory Overview Lorentz Centre HART Workshop work in progress Contact: k.v.hindriks@tudelft.nlk.v.hindriks@tudelft.nl Webpage: http://mmi.tudelft.nl/SocioCognitiveRoboticshttp://mmi.tudelft.nl/SocioCognitiveRobotics
2
2 Goal of this presentation Collect your feedback about some preliminary ideas about designing / developing a socio-cognitive robot control architecture I’d also like to collect some lessons learned based on your robot development experience; e.g. which pitfalls should be avoided. Please jump in! I’d appreciate teamwork ;-)
3
3 Overview Exploratory overview of cognitive robot control architectures Basic Abstract Architecture Design Summarizing: Current understanding of some key challenges
4
4 Towards Socio-Cognitive Robot Architectures Challenge for cognitive architectures: real time autonomous processing needed to interact with dynamic world we live in. Need for socio-cognitive architectures pushed by humanoid robots that interact with humans in a multi-modal fashion. Towards an architecture for social interaction and teamwork Klein, G., Woods, D. D., Bradshaw, J. M., Hoffman, R. R., & Feltovich, P. (2004). Ten challenges for making automation a "team player" in joint human-agent activity. IEEE Intelligent Systems 19(6): 91-95. Here we look at various current state-of-the-art approaches, and take cognitive robot architectures as a starting point.
5
5 Cognition is the process of acquiring and using knowledge about the world for goal-oriented purposes, such as survival. Cognitive robotics is then is aimed at providing a robot with a processing architecture that will allow it to learn and reason about how to behave in response to complex goals in a complex world. Robotic cognitive capabilities include: perception processing, attention allocation, anticipation, planning, complex motor coordination, reasoning about other agents and their own mental states. Source: http://en.wikipedia.org/wiki/Cognitive_robotics.http://en.wikipedia.org/wiki/Cognitive_robotics (biased towards ‘animal cognition’ instead of AI techniques…) MIT’s Cog Robot
6
Challenge the future Delft University of Technology Cognitive Robot Control Architectures An Exploratory (and Necessarily Brief) Overview
7
7 A Plethora of Architectures Subsumption architecture (Brooks 1985) BDL (Rochwerger et al. 1994) RAP (Firby 1994) TCA (Simons et al. 1997). SSS (Connell 1991) ATLANTIS (Gat 1991) 3T (Bonasso 1991) Saphira (Konolige 1996) CLARAty (Volpe et al 2001) CoSy schemas (Hawes et al 2007) Soar ACT-R (SS-RICS, …) ADAPT …
8
8 Architecture Types Pipeline Architectures Based on a horizontal decomposition of functional components Classic architecture, also used for symbolic robot control architectures. Potential to exploit parallelism, but hard and (typically?) not used in practice. Stanford Cart Environment Robot Platform Sensors Motors VisionModelPlanExecuteControl
9
9 Architecture Types Behavior-Based Architectures Based on a vertical decomposition of behavior components Environment Robot Platform Sensors Motors Behavior 1, e.g. Wander Components are in competition, run in parallel and outputs are filtered by some technique. Reactive architectures typically do not support cognitive functions and seem to have a “capability ceiling” (Gat 1998). Behavior 2, e.g. Avoid obstacle Behavior 3, e.g. Explore Behavior 4, e.g. Build Map filter Hannibal(MIT AI Lab) filter
10
10 Architecture Types 3T or Layered Architectures Based on a vertical decomposition of components Environment Robot Platform Sensors Motors Controller (Low-level layer; skills, feedback control loops) Classic examples: SSS (Connell 1991), ATLANTIS (Gat 1991), 3T (Bonasso 1991) High-level typically declarative techniques, low-level typically procedural techniques Sequencer (Middle layer; conditional sequencing, sequencing constructs/language) Deliberator (High-level layer; planning, reasoning, …) Alfred B12
11
11 Rationalizing 3T Architectures Erann Gat (1998) rationalized three-layer architectures by arguing there is a correspondence between layers and the role of internal state. Deliberator: state reflecting predictions about the future Sequencer: state reflecting memories about the past Controller: no state (stateless sensor-based algorithms) Responsiveness, time scale also varies over components.
12
12 BIRON The Bielefeld Robot Companion (2004)
13
13 Care-O-bot II/3 Care-O-bot 3 (Fraunhofer IPA, 2008) (JAM Agents) (FF) (MySQL) (Realtime Framework; RTF) Instruction model
14
14 Armar (Univ. of Karlsruhe) Armar Low-level can also access GKB
15
15 Saphira Architecture “No overt planning” No third (high-level) layer LPS = Local Perceptual Space
16
16 Pioneer Saphira/Aria Architecture Saphira/Aria is a robot control architecture for mobile robots. Lower-level routines have been implemented as a separate software system, called Aria (blue parts). Aria is a system architecture and provides the basic operating system for robot control. See: http://www.cs.jhu.edu/~hager/Public/ICRAtutorial/Konolige-Salphira/saphira.pdfhttp://www.cs.jhu.edu/~hager/Public/ICRAtutorial/Konolige-Salphira/saphira.pdf State reflector = abstract view of the robot’s internal state Colbert = robot programming language Local Perceptual Space (LPS) = egocentric coordinate system a few meters in radius centered on the robot Global Map Space (GMS) = representation of objects part of the robot’s environment in absolute coordinates Saphira = red parts in picture
17
17 CLARAty Architecture Two-layered architecture developed at JPL/NASA CLARA = Coupled Layered Architecture for Robotic Autonomy Observations: No standard no leverage of robotics’ community efforts Issues: “not invented here” “fear of unknown” “learning curve” … Observation: 3T: dominant layer? access to info? obscures hierarchy within layers Two layers blend declarative and procedural techniques
18
18 Workshop on Measures and Procedures for the Evaluation of Robot Architectures and Middleware
19
19 CoSy Architecture Schema B21r + Katana arm integration mechanisms = architectural schema + binding information Need for easy methods for linking modules using different forms of representation, without excessive run-time overhead
20
Challenge the future Delft University of Technology Summarizing: Some key challenges
21
21 Key Problem: Integration Challenge Observation: Over time more and more components have been integrated into cognitive robot architectures. Q:Q: How many layers? A Socio-Cognitive Architecture only adds to this challenge. Any ideas / approaches for effective design approaches for integrating e.g. new components for social interaction and coordination both with humans and other robots?
22
22 Key Problem: Access to Data/Information/KB Observation: After classical 3T architectures, all cognitive robot architectures have a common database shared by all layers Q:Q: Which data needs to be shared? Mainly localization information? It seems that all three-layered architectures require sharing of data by all layers. Do 2-layered architectures require this?
23
23 Key requirements that architecture should support: easy to interface to external environments through a large number of sensors (inputs) and motors/servos (outputs). requires scalability (in terms of inputs/outputs) Support for mix of reactive, deliberative, and reflective behaviours (e.g. obstacle avoidance) Learning new capabilities and knowledge (+ sharing) Support for collaboration (working together) Support for interaction with other (onboard) software (and hardware) components Ease of use of the architecture.
24
24 Well-defined Robot Architecture Q: Do general software architectural principles apply? What is a well-defined robot architecture? Any criteria? Example principles: partition architecture into layers with well-defined interfaces partition code into functional blocks with well-defined inputs and outputs … A well-defined architecture facilitates reuse and parallel development
25
Challenge the future Delft University of Technology Basic Abstract Architecture Design Reducing the complexity?
26
26 Abstract Architecture (1/2) Based on a vertical decomposition into functional layers Environment Robot Platform Sensors Motors Behavioral Layer P1, P2, … = process 1, process 2, …; B1, B2, … = behavior 1, behavior 2, … Cognitive functions supported in cognitive layer, e.g. reasoning, planning, memory, … Cognitive Layer P1P2 … B1B2 …
27
27 Abstract Architecture (2/2) Simple interface between cognitive and behavioral layer Behavioral Layer … Cognitive Layer P1P2 … B1B2 … Stop … Activate … … behavior Override … Symbolicrepresentations
28
28 Emotion expression using gestures Which emotion is expressed?
29
29 The End I reached the end ;-) Any additional questions comments suggestions ?
30
30 TODO TeradaEtAl2008, A Cognitive Robot Architecture based on Tactile and Visual Information Architectures don’t discuss plan repair, …?
31
GOAL Agent Programming Language August 29, 201531 GOAL agent program GOAL agent architecture See also: http://mmi.tudelft.nl/~koen/goal.html.http://mmi.tudelft.nl/~koen/goal.html
32
32 DOD Levels of Autonomy http://www.fas.org/irp/program/collect/uav_roadmap2005.pdf http://www.fas.org/irp/program/collect/uav_roadmap2005.pdf
33
33 Tooth: http://www.kipr.org/robots/tooth.htmlhttp://www.kipr.org/robots/tooth.html Rocky III: http://www.kipr.org/robots/rocky.htmlhttp://www.kipr.org/robots/rocky.html Herbert: http://www.ai.mit.edu/projects/mobilerobots/veterans.htmlhttp://www.ai.mit.edu/projects/mobilerobots/veterans.html Robbie: http://www.magneticpie.com/LEGO/roverHistory/roverSize.html http://www.magneticpie.com/LEGO/roverHistory/roverSize.html B12 (Alfred): http://srufaculty.sru.edu/sam.thangiah/B12Robot.htmhttp://srufaculty.sru.edu/sam.thangiah/B12Robot.htm
34
34 Cognitive Architectures Overview Scott D. Hanford, Oranuj Janrathitikarn, and Lyle N. Long, 2009, Control of Mobile Robots Using the Soar Cognitive Architecture Soar
35
35 ACT-R 6.0 Architecture Motor Modules Current Goal Perceptual Modules Declarative Memory Pattern Matching And Production Selection Check Retrieve Modify Test Check State Schedule Action Identify Object Move Attention ACT-R 6.0 Environment
36
36 Cognitive Architectures Overview SS-RICS = Symbolic and Subsymbolic Robotics Intelligence Control System An extension of ACT-R U.S. Army Research Laboratory, Aberdeen (Kelley and Avery) SS-RICS (2006)
37
37 Cognitive Architectures Overview ADAPT (Benjamin, Lyons, and Lonsdale 2004) ADAPT (2004) Benjamin, P., Lyons, D., and Lonsdale, D., “Designing a Robot Cognitive Architecture with Concurrency and Active Perception,” Proceedings of the AAAI Fall Symposium on the Intersection of Cognitive Science and Robotics, October, 2004.
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.