A Practical Approach to Understanding Robot Consciousness

Transcription

1 A Practical Approach to Understanding Robot Consciousness Kristin E. Schaefer 1, Troy Kelley 1, Sean McGhee 1, & Lyle Long 2 1 US Army Research Laboratory 2 The Pennsylvania State University Designing a Conscious Robot Workshop, Tucson, AZ, 25 April 2016

2 Can a robot be conscious? OR Is it the degree to which the human interacting with the robot perceives it to be trustworthy?

3 Can a robot be conscious? CONSCIOUSNESS is MORE than just INTELLIGENCE Kelley, T. D., & Long, L. N. (2010). Deep Blue cannot play checkers: The need for generalized intelligence for mobile robots. Journal of Robotics.

4 Can a robot be conscious? Is CONSCIOUSNESS the same thing as AWARENESS? Subjectivity: Meaning derived from ones own ideas, moods, and sensations Unity: All sensor modalities melded into one experience Ex Machina, Universal Pictures Intentionality: Experiences have future meaning Others? Kelley, T. D., & Long, L. N. (2010). Deep Blue cannot play checkers: The need for generalized intelligence for mobile robots. Journal of Robotics.

5 Can a robot be conscious? If a robot exhibits emotions, does that make it conscious? Emotions such as fear, anger, sadness, happiness, disgust, and surprise can be modeled theoretically, and vary due to rewards and punishments. Eight emotions that vary with time Fixed coefficients that define temperament Positive and negative reinforcement Long, Lyle N., Kelley, Troy D., and Avery, Eric S., "An Emotion and Temperament Model for Cognitive Mobile Robots," 24th Conference on Behavior Representation in Modeling and Simulation (BRIMS), March 31-April 3, 2015, Washington, DC

6 Practical Example BUT, is trying to design a conscious robot a practical approach? Example of a MARCbot Is it the degree to which the human interacting with the robot perceives it to be trustworthy? Photo: / Photo: Mark Crosby (2015) My Robot Helper

7 A Practical Approach Never trust anything that can think for itself if you can't see where it keeps its brain. ~ J. K. Rowling Data Sensors The Black Box Action Most people do not know how a robot makes decisions So, is it really seeing the brain, or our perception of the robot and the actions associated with the decisions that can impact our trust? TO TRUST OR NOT TO TRUST

8 Human-Robot Trust People form expectations before ever interacting with a robot. Physical Form affects perceptions of trustworthiness Stimuli: 49 pictures different real-world robots, 7 robot domains Participants: Over 200 novice participants Findings: Ratings of perceived intelligence (PI), robotness (RC), and negative social influence (SI) can be used to predict trustworthiness of a robot from providing no other information than a picture of the robot Ŷ trustworthiness = Constant + PI + RC SI Schaefer, K.E., Sanders, T.L. Yordon, R.E., Billings, D.R. & Hancock, P.A. (2012, September). Classification of Robot Form: Factors Predicting Perceived Trustworthiness. Proceedings of the 56th Annual Human Factors and Ergonomics Society (pp ). Boston, MA.

9 Human-Robot Trust Societal Influence Pre-Interaction Trust HRI Information HRI Tasking Attitudes toward robot Expectations Human ure Cult Trust Propensity Previous Experience Team Members Robot Reputation Society Ŷtrustworthiness = Constant + PI + RC SI Gather Information about HRI task Expectancy Robot Capabilities LOA Intelligence Mode of communication Human States Initial Trust Boston Dynamics, BigDog Schaefer, KE (2013) The Perception and ment of Human-Robot Trust. Doctoral Thesis. Figure 14

10 Human-Robot Trust Societal Influence HRI Information Pre-Interaction Trust HRI Post -Interaction Trust Environment: Team & Task Attitudes toward robot Society Human Robot Human Culture Trust Propensity Team Members Previous Experience Reputation Gather Information about HRI task Robot Expectancy Robot Capabilities LOA Intelligence Mode of communication Human States Initial Trust Robot Capabilities LOA Intelligence Mode of communication HRI Human States Post- Interaction Trust Perceived Risk <<interaction complete>> <<additional interaction with robot>> (Schaefer, 2013; Figure 14)

11 Give me a robot that acts like my bird dog ~MG William Hix, Deputy Director, ARCIC A Paradigm shift - from Tool to Team Member From teleoperation towards autonomous operation An Unmanned System that Understands its environment Conducts useful activity Acts independently, but Acts within prescribed bounds Learns from experience Adapts to dynamic situations Possesses a shared mental model Communicates naturally

12 Robot Design Goal: Move away from over-specialized design to more generalizable decision-making capabilities A theoretical approach for designing the underlying information processing architecture Long, L.N., & Kelley, T.D. (2010). Review of Consciousness and the Possibility of Conscious Robots. Journal of Aerospace Computing, Information, and Communication, 7,

13 Example Algorithms Is there a link between the underlying computational architecture and the associated perceptions of the person? Two Algorithms to identify novel events and enhance episodic indexing Benefits of this approach: This allows associative cues to be set to novel information Allows the anticipation of future novel events following one exposure to new stimuli New Approach: This provides the computational justification for episodic indexing of information as a post hoc process Provides justification for certain robot behaviors Novel Event Event Cue Event Cue

14 Novelty Algorithm Let α = vector of observations Let β = number of observations in α Let µ = matrix of observation correlations Let T = threshold value for a correlation Let B = % of T, give set of observations Let γ = number of correlations that exceed the threshold T γ 0 for i = 0 β 1 for j = 0 β 1 if i == j continue µ i,j correlation(α i, α j) if µ i,j > T then γ γ + 1 end end ): or, where x = correlation(α i, α j): β 1 γ = # f(x) > T i,j =0 i j Let τ = percentage % of correlations of correlations that exceed that exceed the threshold the boredom τ = γ/ ((β 2 β)/2) β 1 γ = # f(x) i,j =0 i j > T Kelley, T. D., & McGhee, S. (2013, May). Combining metric episodes with semantic event concepts within the Symbolic and Sub-Symbolic Robotics Intelligence Control System (SS-RICS). In SPIE Defense, Security, and Sensing (pp L-87560L). if τ > B then RobotStatus else RobotStatus end Nothing has changed BORED Novel event occurred NOT BORED

15 Episodic Indexing Logic Flow Episodic indexing allows anticipation of future novel events following one exposure to new stimuli Identify the event prior to the novel event (3e) Create New Episode (ne) starting with the event just prior to the novel event (ne) = (3e:6e) Convert 3e to symbolic information based on current goal (g) and current symbolic perceptual (p) information (ne) = (e i (g,p):6e) Convert Novel events (4e:5e)= to symbolic (s) event information (ne) = (e i (g,p):(s):6e) Convert 6e to reinforcement information (R) (ne) = (e i (g,p):(s):r) Repeat until the end of collected episodes resulting in Episode (E) = set of events (1e:ne) Last event before novel Event (3e) Novel Events (4e:5e) Reinforcement (R)..n {ne ne = e n (goal/perception):(s):r} Kelley, Troy D., (2014), Robotic Dreams: A Computational Justification for the Post-Hoc Processing of Episodic Memories, Intl. Jnl. of Machine Consciousness, Vol. 6, No. 2, pp

16 Trust Calibration Episodic Indexing could help calibrate trust Do expected behaviors match actual behaviors? Improving the underlying architecture could be linked to outward robot behaviors that exude the capability to learn How does the person know that the robot knows what is going on? Appropriate feedback is important to enhancing situation awareness and calibrating trust (Schaefer & Straub, 2016) If it is possible to identify early event cues, then it could be possible to provide better feedback timing. Example: Why did the driverless vehicle stop? Schaefer, KE, & Straub, E. (2016). Will passengers trust driverless vehicles? Removing the steering wheel and pedals. In Proc. IEEE CogSIMA. San Diego, CA. The New Yorker, Nov 2013

17 Conclusion Practical Approach: Near-term robots that can make appropriate decisions in novel, high-risk environments Successful Human-Robot Interaction: This is based in part on the trust perceptions of the person interacting with the system Individuals may have very limited knowledge of how a robot makes decisions or processes information All they know is based on the behaviors of the robot and the feedback from the robot Possible Considerations: Information processing approach to robot design is fast and relatively simple Episodic indexing was found to be efficient process for recognizing novel events and helping to store memories Trust Calibration: The concept of episodic indexing could be linked to the timing of robot feedback

18 Contact Information Trust: Kristin E Schaefer kristin.e.schaefer2.ctr@mail.mil Novelty Algorithm: Sean McGhee sean.m.mcghee.ctr@mail.mil Intelligence/Episodic Indexing: Troy Kelley troy.d.kelley6.civ@mail.mil Information Processing/Robot Emotions: Lyle Long lnl@psu.edu