Plymouth 2006

Emotional Robots: 

Emotional Robots Paranoid androids or intelligent agents? Dr Will Browne - Cybernetics

Emotions: 

“The question is not whether intelligent machines can have any emotions, but whether machines can be intelligent without emotions.” Marvin Minsky Emotions This talk aims to show whether emotions can be useful to robots in creating intelligent agents or whether ‘emotions’ will be only superficial for human-robot interaction: a robot that smiles when it opens the door for you…

Plan: 

Plan Background science fiction, robots and AI Why use a cognitive model in a robot? Alternative intelligent approaches for robot control Emotions in animals and robots Experiments with emotional robots Discussion, conclusions and the future… Background science fiction, robots and AI Why use a cognitive model in a robot? Alternative intelligent approaches for robot control Emotions in animals and robots Experiments with emotional robots Discussion, conclusions and the future…

Mobile Robotics: 

Mobile Robotics Dr Susan Calvin obtained her bachelor's degree at Columbia in 2003 and began graduate work in cybernetics. Asimov (1940)

Picture of Lt Commander Data: 

Picture of Lt Commander Data

Slide7: 

The Most Advanced Robot?

Slide8: 

This 1100 spin Bosch machine is incredibly quiet and positively high-end. It has everything you would expect to find on a Bosch including exclusive features like the 3D AquaSpa wash system with Fuzzy Control.

Plan: 

Plan Background science fiction, robots and AI Why use a cognitive model in a robot? Alternative intelligent approaches for robot control Emotions in animals and robots Experiments with emotional robots Discussion, conclusions and the future… Background science fiction, robots and AI Why use a cognitive model in a robot? Alternative intelligent approaches for robot control Emotions in animals and robots Experiments with emotional robots Discussion, conclusions and the future…

Why it is Good to be a Cognitive System!: 

Why it is Good to be a Cognitive System!

It’s not just ducks!: 

It’s not just ducks!

Slide12: 

by being preprogrammed for every possible contingency? No by having learned the consequences for the achievement of the mission of every possible action in every contingency? No by having learned enough to be able to predict the consequences of tried and untried actions, by being able to evaluate those consequences for their likely contribution to the mission, and by selecting a relatively good course of action? Maybe… Owen Holland - University of Essex How could the agent achieve its task (or mission)?

Latent Learning: 

Latent Learning Latent learning has three stages Robot (or Rat) enters the maze and explores it without reward. Robot (or Rat) is then placed in one of the end zones (E,F) and given a reward Robot (or Rat) is then placed at start (S) of maze and must navigate in the shortest path back to the reward state.

Slide14: 

LEARNING CLASSIFIER SYSTEM ACTIONS ENCODING SELECT MATCH PLAUSIBLY BETTER RULES GENERATED RULE DISCOVERY FINAL RULE BASE DECODING TRAINING RULE BASE CONDITIONS ENVIRONMENT INITIAL RULE BASE EFFECT CREDIT UCL 2006 Learning Classifier Systems

Latent Learning: 

Latent Learning Robots not very good at consistently turning at 90° Latent learning environment simplified to N,E,W,S, compass points. After a five-minute run a robot will start getting very close to one wall and will eventually get stuck against it!

Plan: 

Plan Background science fiction, robots and AI Why use a cognitive model in a robot? Alternative intelligent approaches for robot control Emotions in animals and robots Experiments with emotional robots Discussion, conclusions and the future… Background science fiction, robots and AI Why use a cognitive model in a robot? Alternative intelligent approaches for robot control Emotions in animals and robots Experiments with emotional robots Discussion, conclusions and the future…

Robot Embodiment: 

Robot Embodiment

Slide18: 

Stimuli Subsymbolic processing Camera inputs Laser inputs Sound inputs Parallel processing all of the inputs simultaneously Results go to memory Production system operates on memories Semantic network Troy Kelley US Army Research Laboratory “Attention” is the highest level goal

Cartesian Theatre: 

Cartesian Theatre A Homunculus1 watches the individual needs, Thus, Domination through global selection Dennett and Kinsbourne: … a centred locus in the brain Cartesian materialism, because it is the view one arrives at when one discards Descartes’ dualism but fails to discard the associated imagery of a central (but material) theatre where ‘it all comes together. http://wwwcms.brookes.ac.uk/~p0054139/Paper/Decider8.htm 1.’little man’ http://faculty.washington.edu/chudler/flash/hom.html

Global Workspace Architecture: 

Global Workspace Architecture Multiple parallel specialist processes compete and co-operate for access to a global workspace If granted access to the global workspace, the information a process has to offer is broadcast back to the entire set of specialists Murray Shanahan Imperial College London

GWT and the Frame Problem: 

GWT and the Frame Problem Both Fodor and Dennett seem to have a strictly serial architecture in mind when they characterise the frame problem This certainly looks computationally infeasible Murray Shanahan Imperial College London

Subsumption Architecture: 

Subsumption architectures are hybrid: Subsumption Architecture

Example Architectures: 

Distributed Architecture for Mobile Navigation (DAMN) (Rosenblatt 1995) Agents vote for the actions, and the action which receives the most votes is executed. Similar to Maximise Collective Happiness Allows voting for actions other than their first choice. Mobile Autonomous Robot Software (Mars) (Carnegie Mellon University, Veloso) Example Architectures

SOAR (1): 

SOAR (1) Developed by Allen Newell and others Purely Symbolic General Cognitive Architecture – Symbolic All information held in production rules Rules relating to the problem brought to working memory; a decision process then decides which rule to use Learning achieved through the resolution of impasses

SOAR (2): 

SOAR (2) Taken from: J. Lehman, J. Laird, P. Rosenbloom, “A Gentle introduction to SOAR: 2006 update”, http://ai.eecs.umich.edu/soar/sitemaker/docs/misc/GentleIntroduction-2006.pdf, 2006

ACT-R (1): 

ACT-R (1) Developed by John Anderson et al. at Carnegie Mellon University Hybrid Symbolic/Subsymbolic General Cognitive Architecture Procedural (production system) and Declarative (subsymbolic) Memory systems “Goal Stack” – a stack of goals of the system; only the top (current) goal visible Achieved goals form a new item in declarative memory Limited “Attentional Resource”

ACT-R (2): 

ACT-R (2) Taken from: M. C. Lovett, L. M. Reder, and C. Lebiere, "Modeling Working Memory in a unified Architecture," in Models of Working Memory: Mechanisms of active maintenance and executive control, A. Miyake and P. Shah, Eds. Cambridge: Cambridge University Press, 1999, pp. 135-182.

Perspective Taking: A tale of two systems: 

Perspective Taking: A tale of two systems ACT-R/S (Schunn & Harrison, 2001) Our perspective-taking system using ACT-R/S is described in Hiatt et al. 2003 Three Integrated VisuoSpatial buffers Focal: Object ID; non-metric geon parts Manipulative: grasping/tracking; metric geons Configural: navigation; bounding boxes Polyscheme (Cassimatis) Computational Cognitive Architecture where: Mental Simulation is the primitive Many AI methods are integrated Our perspective-taking using Polyscheme is described in Trafton et al., 2005 Alan Schultz Naval Research Laboratory

Slide29: 

Computational Cognitive Neuroscience Models Healthy performance on frontal tasks. Prolonged frontal developmental period. Monkey lesion data. Human frontal damage patient performance. Autistic peformance. (Rougier, Noelle, Braver, Cohen, and O'Reilly, 2005) David Noelle University of California

Slide30: 

Robotic Working Memory The highly limited capacity of working memory, along with its tight coupling with deliberation mechanisms, might alleviate the need for costly memory searches. Information needed to fluently perform the current task is temporarily kept “handy” in the working memory store. Could robot control systems benefit from the inclusion of a working memory system? Can computational neuroscience models of the working memory mechanisms of the human brain shed light on the design of a robotic working memory system? The adaptive working memory toolkit (WMtk) in C++ David Noelle University of California

Slide31: 

We’re trying to build a robot that has an internal model of itself and an internal model of the world, and that uses them to predict the outcomes of novel or untried actions. And maybe the IAM will be conscious… Owen Holland University of Essex

Plan: 

Background science fiction, robots and AI Why use a cognitive model in a robot? Alternative intelligent approaches for robot control Emotions in animals and robots Experiments with emotional robots Discussion, conclusions and the future… Plan

Emotions - Neuroscience: 

Rolls, defines emotions as “the states elicited by reward and punishers, including changes in those rewards and punishments”, by which “a reward is anything for which an animal will work, i.e. a Positive Reinforcer” and “a punishment is anything that an animal will work to escape or avoid, i.e. a Negative Reinforcer”. Damasio, stimulus – good/bad evaulation Emotions are based on experiences and help guide future actions. Emotions - Neuroscience

Extending attention model with amygdala : 

Extending attention model with amygdala Simulate by extending attention model with amygdala: John Taylor Kings College London

Slide36: 

ISAC – by Kaz Kawamura Short-term Memory Working Memory System Long-term Memory Haikonen’s System Reactions Theory of Emotions: Sensations - Reactions

Slide37: 

http://info.fysik.dtu.dk/Brainscience/people/rodney.html

Other Emotional Architectures: 

Other Emotional Architectures ASD (Maes 1990) Action selection dynamics ALEC DARE (Marcia et al. 2001) EBII AD with ECS (Malfaz et al.) emotional control Motives (goals) interact with beliefs (predictions) to produce emotions. Cf. Sloman Feelings arise after enaction of emotions.

Plan: 

Plan Background science fiction, robots and AI Why use a cognitive model in a robot? Alternative intelligent approaches for robot control Emotions in animals and robots Experiments with emotional robots Discussion, conclusions and the future… Background science fiction, robots and AI Why use a cognitive model in a robot? Alternative intelligent approaches for robot control Emotions in animals and robots Experiments with emotional robots Discussion, conclusions and the future…

Augmented Reality: 

Augmented Reality

Augmented Reality: Pacbot demo: 

Augmented Reality: Pacbot demo

Augmented Reality: Emotional Architecture: 

Augmented Reality: Emotional Architecture

Augmented Reality: Emotional Architecture: 

Augmented Reality: Emotional Architecture

Augmented Reality: Normal Explore: 

Augmented Reality: Normal Explore

Augmented Reality: Tight Explore: 

Augmented Reality: Tight Explore

Augmented Reality: Emotional Explore: 

Augmented Reality: Emotional Explore

Augmented Reality: Explore Task: 

Augmented Reality: Explore Task

Explore efficiency: 

Explore efficiency

Explore effectiveness: 

Explore effectiveness

Augmented Reality: Tight Explore: 

Augmented Reality: Tight Explore

Augmented Reality: Very Tight Explore: 

Augmented Reality: Very Tight Explore

Plan: 

Plan Background science fiction, robots and AI Why use a cognitive model in a robot? Alternative intelligent approaches for robot control Emotions in animals and robots Experiments with emotional robots Discussion, conclusions and the future… Background science fiction, robots and AI Why use a cognitive model in a robot? Alternative intelligent approaches for robot control Emotions in animals and robots Experiments with emotional robots Discussion, conclusions and the future…

Discussions: 

Visible Emotions shown useful in human-robot interaction and should speed up robot-robot interaction - However these can be top-down interpretations of internal deterministic states Internal emotions emerge from embodiment and interaction with an environment - “[Reactive mechanisms] make possible alarm-driven primary emotions” while “[Deliberative mechanisms] make possible secondary emotions using global alarm mechanisms linked to deliberative [processes].” Aaron Sloman Discussions

Discussions: 

Discussions What makes emotions useful? Emerge rather than hard coded Generalise across known and unknown situations Episodic and temporal Fast response if necessary Non-linear, non-deterministic and stochastic Emotions act as a warehouse where items can be sorted, grouped and sent appropriately. Rather than every individual manufacturers (internal + external states) delivering to each outlet shop (effective action)

Discussions: 

Discussions What makes emotions useful? Practically: Much less lines of code for better behaviour - 40% Easier to understand code for non-programmers Intuitive behaviours result Difficulties: Emotions levels require tuning Diagnosis and prediction of behaviour difficult When is it justified to call a ‘non-linear controller’ an ‘emotion’?

Concluding Remarks: 

Concluding Remarks Robots need real emotions to successfully complete complex real-world tasks. Emotions can set goals: balance explore vs exploit Emotions can modify existing behaviours Emotions facilitate action in unknown domains

Future: Cognitive Robots?: 

Future: Cognitive Robots? Don’t make cognition hard for ourselves Models are useful, but the mind is not so clear-cut Human cognition is a good model, but desired behaviour may be achieved by other models Increasingly powerful tools assist in advancing cognitive robotics, e.g., computational power, engineering materials and neurological understanding Emotions will play an important part in both Human-Robot interaction and enabling Autonomous Robot behaviour

Cognitive Robots: Balancing Act including Emotions: 

Cognitive Robots: Balancing Act including Emotions

Any Questions?: 

Any Questions?