Until Robotics

Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 84

Basic Cognitive Process

Framework

There are several frameworks for studying cognition, each providing a


unique perspective on how the mind processes information and
functions. These frameworks help researchers and psychologists
understand various aspects of human cognition. Here are some notable
frameworks for studying cognition:
Information Processing Approach:

• This framework views the mind as a complex information-processing


system, much like a computer.
• It focuses on how sensory input is encoded, stored, and retrieved
from memory.
• The approach emphasizes attention, perception, memory, problem-
solving, and decision-making as key components of cognitive
processes.
Connectionist or Neural Network
Approach:

• This framework is inspired by the structure and functioning of neural


networks in the brain.

• It proposes that cognition arises from the activation and interaction of


interconnected processing units (neurons or nodes) that process
information in parallel.

• Learning occurs through the adjustment of connection strengths based on


experience.
Cognitive Neuroscience:

• Cognitive neuroscience combines cognitive psychology with


neuroscience to study the neural basis of cognition.
• It aims to understand how brain structures and processes underlie
cognitive functions.
• Techniques like functional magnetic resonance imaging (fMRI) and
electroencephalography (EEG) are used to examine brain activity
during cognitive tasks.
Ecological Approach:

• This framework emphasizes the interaction between the individual


and the environment in understanding cognition.
• It considers how cognition is adapted to the ecological context in
which it occurs.
• The ecological approach is concerned with real-life situations and how
cognition aids in problem-solving and decision-making in natural
environments.
Embodied Cognition:

• Embodied cognition posits that cognitive processes are deeply rooted


in the body and its interactions with the environment.
• It suggests that bodily experiences, sensations, and motor actions
influence cognitive processes and are integral to cognition.
• This approach challenges the traditional view of cognition as purely
brain-bound.
Distributed Cognition:

• Distributed cognition proposes that cognition is not confined to an


individual's brain but extends to the surrounding environment and
social interactions.
• It emphasizes how cognitive tasks can be distributed across
individuals, artifacts, and tools to achieve better problem-solving and
memory retention.
Evolutionary Psychology:

• This framework examines cognition from an evolutionary perspective,


exploring how cognitive processes have evolved to solve adaptive
problems.
• It considers how certain cognitive abilities might have conferred
advantages in the survival and reproduction of our ancestors.
Cognitive Developmental Approach:

• This framework focuses on how cognitive processes change and


develop over the lifespan.
• It examines how children's cognitive abilities progress from simple to
complex and how cognitive changes influence learning and problem-
solving.
• These frameworks complement and enrich each other, providing
diverse insights into the workings of the human mind. Researchers
often combine multiple approaches to gain a comprehensive
understanding of cognition from various angles.
The Emergence of Modern Cognitive Psychology

• When was this new approach actually ‘‘born’’?

• The birth of cognitive psychology can be listed as 1956.

• Influential books and articles on attention, memory, language,


concept formation, and problem solving.

• The growing support for the cognitive approach has sometimes been
called the ‘‘cognitive revolution’’
Factors Contributing to the Rise of Cognitive
Psychology
• Disappointment with behaviorism's dominance in psychology.

• Shift from animal learning to human memory research (Baddeley et al., 2009;
Bower, 2008).

• Difficulty explaining complex human behavior with behaviorist concepts (G.


Mandler, 2002; Neisser, 1967).

• Behaviorism lacks insight into thoughts, strategies, and problem-solving


(Bechtel et al., 1998).
Linguistics and Language Complexity

• New linguistics developments challenged behaviorism (Bargh &


Ferguson, 2000; Bower, 2008).

• Noam Chomsky emphasized language complexity (Chomsky, 1957).

• Humans possess innate ability for language (Chomsky, 2004).

• Contradiction to behaviorist view on language acquisition.


Human Memory Research

• Growing disillusionment with behaviorism.

• Memory research expanded in late 1950s.

• Memory models revealed alterations due to prior knowledge (Bargh


& Ferguson, 2000).

• Behaviorism's reinforcement principles insufficient.


Children's Thought Processes and
Developmental Psychology

• Jean Piaget's impact on developmental psychology.

• Active exploration by children to understand concepts.

• Changing cognitive strategies during maturity.

• Piaget's influence on shaping psychological perspectives.


Cognitive Approach's Dominance

• Research in linguistics, memory, and developmental psychology


fueled cognitive growth.

• By mid-1970s, cognitive psychology replaced behaviorism as


dominant theory (Robins et al., 1999).
Information-Processing Approach

• Enthusiasm for information-processing approach.

• Focus on cognitive processes as information processing.

• Strengthened understanding of human cognition.


• Cognitive psychology emerged due to limitations of behaviorism.

• Research in linguistics, memory, and developmental psychology


propelled its growth.

• Information-processing approach further solidified cognitive


psychology's prominence.
This information-processing
approach argued
(a) our mental processes are similar to the operations of a computer,

(b) information progresses through our cognitive system in a series of


stages, one step at a time (reconsider this comparison between mental
processes and computers).
The Information-Processing Approach
The Atkinson-Shiffrin Model of Memory
• Introduction to the Atkinson-Shiffrin information-processing model of
memory.
• Explanation of the model's stages: sensory memory, short-term
(working) memory, and long-term memory.
Sensory Memory

• Description of sensory memory's function: storing information for a


brief period (2 seconds or less).

• Example of auditory memory in action.

• Mention of the transient nature of sensory memory.


Short-Term (Working) Memory
• Explanation of short-term memory as actively used information.
• Mention of its fragility and the possibility of loss within about 30
seconds.
• Transition from sensory to short-term memory.
Long-Term Memory
• Introduction to long-term memory's capacity and permanence.
• Contrast with working memory's limited capacity and temporary
nature.
• Mention of long-term memory's storage of memories from various
timeframes.
Application of the Model
• Illustration of how the model applies to current tasks.
• Explanation of how external input progresses through sensory, short-
term, and long-term memory.
• Challenge: Asking the audience to recall specific details from the
presented information.
Model's Influence and Critiques
• Discussion of the Atkinson-Shiffrin model's dominance in memory
research.
• Mention of diminished influence due to evolving perspectives.
• Questioning the clear distinction between short-term and long-term
memory.
Reevaluation of Memory
• Overview of dividing memory topics for convenience.
• Introduction of "working memory" as a more current term.
• Mention of upcoming chapters exploring various aspects of long-term
memory.
Overview
• Recap of key points discussed about the Atkinson-Shiffrin model.
• Acknowledgment of evolving views on memory.
• Emphasis on the complexity of memory processes.
Classic Works in Information Processing
• Alan Turing's "On Computable Numbers" (1936):
• Introduced the concept of a Turing Machine, a theoretical model of computation.
• Paved the way for understanding the limits of computation and the basis for modern computers.
• Norbert Wiener's "Cybernetics" (1948):
• Introduced the term "cybernetics" to describe systems of control and communication in animals and machines.
• Laid the groundwork for understanding feedback mechanisms, self-regulation, and information flow in complex
systems.
• an automatic pilot or a controller that maintains a constant temperature in a room, electronic computers, the
human brain, biological populations, as well as human society.
• Claude Shannon's "A Mathematical Theory of Communication" (1948):
• Established the foundation of Information Theory, quantifying information and communication.
• Introduced concepts like entropy, data compression, and coding theory.
• Significance of these works:
• Shaped our understanding of information processing, communication, and computation.
• Formed the basis for modern computing, communication systems, and artificial intelligence.
Turing test

• https://youtu.be/3wLqsRLvV-c?feature=shared

• Turing test and chat GPT


https://youtu.be/_GCTLciqT0A?feature=shared

Can machines think :


https://youtu.be/yYN6I4Dzg4Y?feature=shared
Why did Alan Turing invent the Turing test?

• To avoid prejudicial rejection of evidence of machine intelligence,


Turing suggested the “imitation game,” now known as the Turing test:
a remote human interrogator, within a fixed time frame, must
distinguish between a computer and a human subject based on their
replies to various questions posed by the interrogator.
The Turing Test
• Turing Test proposed by Alan Turing in 1950:
• A test to determine a machine's ability to exhibit intelligent behavior indistinguishable
from that of a human.
• Involves a human judge interacting with both a human and a machine without visual cues.
• Concept of the Turing Test:
• Raises questions about the nature of intelligence and the possibility of machine cognition.
• Shifts the focus from "what is thinking?" to "what does thinking look like?"
• Criticisms and debates:
• Searle's Chinese Room Argument: Argues that following instructions doesn't imply true
understanding.
• Debates about understanding vs. simulating intelligence: Can machines truly comprehend
or only mimic behavior?
Animal Cognition and Thinking
• Historical perspectives on animal cognition:
• B.F. Skinner's Behaviorism: Emphasized observable behaviors and
conditioning.
• Wolfgang Kohler's studies on insight learning: Challenged behaviorism with
evidence of higher-level thinking in animals.
• Contemporary research on animal cognition:
• Tool use by primates: Shows problem-solving skills and adaptability.
• Language learning by dolphins and parrots: Suggests a level of symbolic
communication.
• Theory of mind in certain species: Understanding others' mental states.
Sultan Insight Experiment
Insight learning theory - Sultan
• https://youtu.be/WmSe7ZmzD2c?feature=shared
Arguments Against Animal Thinking

Arguments against attributing complex thinking to animals:


• Lack of evidence for abstract reasoning: Some animal behaviors can be
explained through certain stimuli.
• Absence of symbolic communication: Animals may not possess a language
system comparable to humans. (Speech, sign language, writing)
• Dependency on instincts and conditioning: Critics argue that animal behaviors
are driven by biological factors rather than conscious thought.
Machine Intelligence: Can Machines
Think?
• Evolution of AI and machine learning:
• Early expert systems: Rule-based systems for problem-solving.
• Deep learning and neural networks: Simulating aspects of human brain
functioning.
• AI debate: Strong AI vs. Weak AI:
• Strong AI asserts that machines can genuinely think and understand.
• Weak AI argues that machines simulate intelligent behavior without true
understanding.
The Chinese Room Argument
• John Searle's Chinese Room Argument:
• Challenges the idea of strong AI.
• Imagines a person in a room following instructions to manipulate Chinese
symbols, without comprehending the language.
• Implications:
• Raises questions about whether syntax (symbol manipulation) implies
semantics (true understanding).
• Contemplates the difference between information processing and conscious
understanding.
Can Machines Be Creative?
• Exploring machine creativity:
• Algorithmic generation of art, music, literature: Examples of machine-
generated content.
• Role of human input and machine processing: Debate on where creativity
originates.
• Debates on machine creativity:
• Can machines truly exhibit originality and imagination?
• Is creativity merely the result of complex algorithms?
Ethical and Philosophical Implications
• Ethical concerns related to animal cognition and machine thinking:
• Animal rights and treatment: Implications for how we view and treat non-
human animals.
• Responsibility and accountability of intelligent machines: Ethical
considerations when AI systems make decisions.
• Need for careful consideration:
• As technology advances, ethical dilemmas and societal impacts increase.
Key points discussed
• The influence of classic works on information processing.
• The Turing Test and debates around machine intelligence.
• Perspectives on animal cognition and the challenges of attributing thinking to
animals.
• Implications of the Chinese Room Argument and machine creativity.
• Ethical and philosophical considerations in animal and machine thinking.
• Ongoing debates and evolving understanding:
• Both animal and machine thinking remain areas of active research and discussion.
• Encouragement to explore further:
• Attendees are encouraged to continue exploring these captivating topics that
bridge the realms of philosophy, science, and technology.
Human and Animal Cognition:

• Human cognition is characterized by its complexity, depth, and


versatility, allowing for advanced language, abstract thinking, and
complex reasoning.
• Animal cognition varies across species, with some animals
demonstrating impressive cognitive abilities that approach certain
aspects of human cognition.
• However, the extent and depth of these abilities tend to be more
constrained, often focused on immediate needs and adaptations to
specific environments.
• Comparing human and animal cognition offers insights into the
evolutionary origins and variations in cognitive processes across species.
Complexity of Thought and Reasoning:

• Humans have highly developed cognitive abilities, including advanced


reasoning, abstract thinking, and complex problem-solving.
• Animals exhibit varying degrees of cognitive abilities; some species,
like dolphins, primates, and certain birds, show evidence of problem-
solving and rudimentary reasoning.
Language and Communication:
• Humans have developed complex languages that allow for intricate
communication, abstract concepts, and storytelling.
• While animals use communication methods like vocalizations, body
language, and gestures, their communication tends to be more
limited and focused on immediate needs.
Symbolic Representation:
• Humans can use symbols and abstract representations (like words and
mathematical symbols) to convey complex meanings and concepts.
• Animals may use limited symbolic representations, such as bees
communicating the location of food through dance or apes using
symbols to represent basic concepts.
Planning and Future Thinking:
• Humans can engage in long-term planning and envision future
scenarios, which requires a higher level of cognitive processing.
• Some animals show rudimentary planning abilities, such as caching
food for later, but this is often based on immediate needs and is less
complex than human planning.
Tool Use and Innovation:
• Humans exhibit extensive tool use and innovation, creating and
adapting tools for various tasks.
• Some animals, particularly primates and certain birds, demonstrate
basic tool use, but the complexity and range of tools are generally
limited compared to human capabilities.
Self-Awareness and Theory of Mind:
• Humans possess a high level of self-awareness and the ability to
understand that others have thoughts, beliefs, and desires (theory of
mind).
• While some animals, like chimpanzees and elephants, exhibit limited
forms of self-awareness and social cognition, the depth of
understanding is not as advanced as in humans.
Learning and Adaptation:
• Both humans and animals learn from experience and adapt their
behaviors to changing environments.
• Humans can engage in more complex forms of learning, such as
abstract reasoning and hypothesis testing, whereas animals often rely
on simpler learning mechanisms.
Memory and Recall:
• Humans have a sophisticated memory system that allows for episodic
memory (remembering specific events) and semantic memory
(remembering facts and concepts).
• Animals also have memory systems, with varying capacities for
recalling information, but the depth and complexity of memory types
may differ.
Cultural Transmission:
• Humans exhibit cultural transmission, passing down knowledge, skills,
and traditions through generations.
• While some animals show evidence of social learning and passing on
behaviors, the cultural transmission observed in humans is more
extensive and diverse.
Abstract Concepts and Creativity:
• Humans can grasp abstract concepts, create art, and engage in
creative problem-solving that goes beyond immediate survival needs.
• While animals may show some creative behaviors, their creativity is
often limited to solving specific challenges rather than expressing
abstract ideas.
Source Information
Books:
• "The Comparative Psychology of Human and Non-Human Animals: A Guide" by Sara J.
Shettleworth
• "Are We Smart Enough to Know How Smart Animals Are?" by Frans de Waal
• "The Animal Mind: An Introduction to the Philosophy of Animal Cognition" by Kristin
Andrews
Research Journals:
• Journal of Comparative Psychology
• Animal Cognition
• Cognitive Science
• Psychological Science
Online Resources:
• Stanford Encyclopedia of Philosophy: Entry on "Animal Cognition"
• Encyclopedia of Animal Behavior
MACHINE LEARNING (ML)
Machine Learning (ML) is a subset of AI where
computers learn from data and enhance their
performance on tasks without explicit programming. It
involves algorithms and models that find patterns in
data, allowing machines to make better decisions over
time.
Machine Learning and Cognitive
Psychology:
• Machine learning (ML) techniques are being increasingly applied in
cognitive psychology to analyze complex cognitive processes.
• ML provides tools to process large datasets, identify patterns, and
uncover insights that enhance our understanding of human cognition.
Perception and ML
• Image Recognition and Perception:
• ML algorithms, such as Convolutional Neural Networks (CNNs), can replicate
human visual perception tasks.
• These algorithms learn to identify objects and patterns in images, mirroring
human visual recognition.
• Auditory Perception Analysis:
• ML techniques process auditory data, helping uncover patterns in sound
recognition and localization, contributing to auditory perception studies.
Learning and Memory with ML
• Pattern Recognition in Memory:
• ML models can analyze memory recall data, identifying patterns in how
humans retrieve information.
• Insights from ML can aid in understanding human memory storage and
retrieval mechanisms.
• Predictive Learning Models:
• ML algorithms, including Long Short-Term Memory (LSTM) networks, can
simulate human cognitive learning processes.
• These models predict sequence elements, offering insights into language
learning and knowledge acquisition.
Reasoning and Decision Making
• Modeling Human Decision Making:
• ML algorithms replicate cognitive psychology experiments on decision making
under uncertainty.
• Insights from ML help understand the interplay of rational and heuristic
decision-making strategies.
• Analyzing Cognitive Biases:
• ML techniques can analyze decision data to uncover cognitive biases that
influence human judgments.
• These findings contribute to cognitive psychology research on judgment and
decision-making processes.
Language Processing and ML
• Natural Language Processing (NLP):
• ML-powered NLP models analyze language data, aiding in understanding
human language processing.
• These models can simulate linguistic experiments and uncover semantic and
syntactic patterns.
• Sentiment Analysis and Emotion Detection:
• ML techniques in sentiment analysis can reveal emotional responses from
language, contributing to emotion studies in cognitive psychology.
Cognitive Development and ML
• Simulating Cognitive Development:
• ML models can simulate cognitive developmental stages by learning from
data.
• These simulations offer insights into how cognitive abilities evolve over time.
• Child-Computer Interaction Studies:
• ML-powered robots or virtual agents provide platforms to study child-
computer interactions, aiding cognitive development research.
Future Directions and Challenges
• Neural Network Models:
• Future research may involve advanced neural network models that better
emulate human cognitive processes.
• Improved models can offer more accurate simulations and predictions.
• Ethical Considerations:
• As ML techniques play a larger role in cognitive psychology, addressing ethical
concerns regarding data privacy and bias becomes crucial.
Applications and Implications
• Cognitive Disorder Diagnosis:
• ML algorithms analyze cognitive data to detect patterns indicative of cognitive
disorders, aiding early diagnosis.
• Educational Technologies:
• ML-powered educational platforms adapt content to individual learning
styles, enhancing educational outcomes.
Collaboration and Insights
• Interdisciplinary Collaboration:Collaboration between cognitive
psychologists and ML experts generates novel insights and
methodologies.
• Combined expertise advances both fields, leading to more
comprehensive research.
Conclusion
• Enhancing Cognitive Psychology with ML:
• Machine learning enriches cognitive psychology by providing powerful tools
to analyze complex cognitive processes.
• Insights gained from ML applications contribute to a deeper understanding of
human cognition.
• Unlocking New Discoveries:
• The synergy between machine learning and cognitive psychology opens new
avenues for research, shaping the future of cognitive science.
Source Citations
• Anderson, J. R. (1990). The Adaptive Character of Thought. Psychology Press.
• Yarkoni, T., & Westfall, J. (2017). Choosing Prediction Over Explanation in Psychology:
Lessons From Machine Learning. Perspectives on Psychological Science, 12(6), 1100-1122.
• Norman, K. A., & O’Reilly, R. C. (2003). Modeling Hippocampal and Neocortical
Contributions to Recognition Memory: A Complementary Learning Systems Approach.
Psychological Review, 110(4), 611-646.
• Ranganath, C., & Ritchey, M. (2012). Two Cortical Systems for Memory-Guided Behaviour.
Nature Reviews Neuroscience, 13(10), 713-726.
• Poldrack, R. A., Halchenko, Y. O., & Hanson, S. J. (2009). Decoding the Large-Scale
Structure of Brain Function by Classifying Mental States Across Individuals. Psychological
Science, 20(11), 1364-1372.
• LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep Learning. Nature, 521(7553), 436-444.
• Sutton, R. S., & Barto, A. G. (2018). Reinforcement Learning: An Introduction.
MIT Press.
• Mitchell, T. M. (1997). Machine Learning. McGraw-Hill.
• Gazzaniga, M. S., Ivry, R. B., & Mangun, G. R. (2018). Cognitive Neuroscience:
The Biology of the Mind. W. W. Norton & Company.
• Russel, S., & Norvig, P. (2016). Artificial Intelligence: A Modern Approach.
Pearson.
• Bengio, Y., Courville, A., & Vincent, P. (2013). Representation Learning: A
Review and New Perspectives. IEEE Transactions on Pattern Analysis and
Machine Intelligence, 35(8), 1798-1828.
• Murphy, K. P. (2012). Machine Learning: A Probabilistic Perspective. MIT Press.
Robotics Scope
"Robotics in cognitive psychology involves merging robotic
technology with principles of cognitive psychology to study
human cognition and behavior. This interdisciplinary approach
uses robots to simulate real-life scenarios, providing insights
into decision-making, perception, and social interactions. It
also explores creating robots inspired by human cognition.
This integration aids in refining cognitive theories and
advancing intelligent robotic systems."
Robotics Scope
• Robotics and Basic Cognitive Processes: Robotics involves the design,
creation, and operation of robots that can mimic and interact with
basic cognitive processes, leading to the development of machines
capable of intelligent behaviors.
Intersection of Robotics and Cognitive
Psychology:
• Robotics and cognitive psychology intersect to explore how robots can
simulate and interact with human cognitive processes.
• This collaboration enhances our understanding of both human
cognition and machine intelligence.
Perception and Cognitive Psychology
• Visual Perception Studies:
• Robots can recreate experiments in visual perception, analyzing how they
process and interpret visual data.
• Findings contribute to insights into human vision and object recognition.
• Sensory Integration Experiments:
• By emulating tasks related to sensory integration, robots offer data on how
humans combine sensory inputs for coherent perceptions.
• Insights aid cognitive psychologists in understanding multisensory integration
mechanisms.
Learning and Memory in Cognitive
Psychology
• Memory Recall Experiments:
• Robots simulating memory recall tasks offer insights into memory storage,
retrieval, and forgetting processes.
• Comparative analysis helps in understanding the dynamics of human memory.
• Cognitive Learning Models:
• Incorporating cognitive psychology models into robot learning algorithms
enhances adaptive behaviors and decision-making.
• Insights contribute to the development of cognitive robots that learn from
experiences.
Reasoning and Decision Making
• Heuristic Reasoning Studies:
• Robots replicating human heuristic decision-making experiments reveal
cognitive biases and shortcuts.
• Insights aid in understanding human judgment and decision-making
processes.
• Decision-Making Algorithms:
• Implementing cognitive psychology findings in robot decision-making
algorithms improves their ability to make rational choices.
• Robots can apply cognitive principles to optimize their decisions in uncertain
environments.
Language and Communication in
Cognitive Psychology
• Language Processing Experiments:
• Robots simulating language comprehension studies contribute to
understanding human language processing.
• Insights into cognitive aspects of language aid both cognitive psychology and
robotics.
• Human-Robot Interaction Research:
• Interactions between humans and robots inform cognitive psychology
research on communication, social interaction, and empathy.
• Insights from robot-human interactions offer new perspectives on cognitive
processes related to social behaviors.
Cognitive Development Studies
• Developmental Psychology Insights:
• Robots emulating developmental psychology experiments aid in
understanding cognitive milestones and mechanisms.
• Comparative studies reveal parallels between robot learning and human
cognitive development.
• Child-Robot Interaction:
• Robots as interactive tools help investigate how children learn and interact
with technology, offering insights into cognitive processes during
development.
• Understanding child-robot interaction can inform educational strategies.
Future Avenues and Challenges
• Neuro-Inspired Robotics:
• Future research might involve designing robots based on neural principles,
advancing both cognitive psychology and robotics.
• Robotic models of neural processes could offer insights into human cognition.
• Ethical Considerations:
• As robots become involved in cognitive research, addressing ethical concerns
surrounding human-robot interactions becomes essential.
• Safeguarding participants' well-being and privacy is crucial.
Applications and Implications
• Cognitive Rehabilitation:
• Cognitive robots can aid in therapeutic interventions for cognitive
rehabilitation.
• Robots can provide interactive exercises and tasks to help individuals regain
cognitive functions after injuries or illnesses.
• Education and Learning Enhancement:
• Robots can serve as educational tools, offering a unique platform to study
how interactions with robots influence learning and cognitive development in
children.
• Insights can improve educational strategies and curriculum design.
Collaboration and Insights
• Interdisciplinary Collaboration:
• Collaborative efforts between cognitive psychologists and roboticists provide
unique insights into human cognition and advance cognitive robotics.
• Combining expertise leads to holistic research outcomes.
• Modeling Human Cognition:
• Robots serve as valuable models for testing cognitive theories and validating
research hypotheses in cognitive psychology.
• Robotic simulations offer controlled environments to study cognitive
phenomena.
Scope
• Advancing Cognitive Psychology and Robotics:
• The intersection of robotics and cognitive psychology enriches both fields by
deepening our understanding of human cognition and driving innovation in
robotics.
• Collaboration leads to a mutually beneficial exchange of insights and
methodologies.
• Exploring New Frontiers:
• The collaboration between cognitive psychology and robotics opens new
research avenues that can transform our understanding of intelligence,
perception, and interaction.
• Future advancements in cognitive robotics hold promise for AI and human-
robot interactions.
Source Citation’s
• Corke, P. (2017). Robotics, Vision and Control: Fundamental Algorithms in MATLAB.
Springer.
• Anderson, J. R. (2010). Cognitive Psychology and Its Implications. Worth Publishers.
• Thrun, S., Burgard, W., & Fox, D. (2005). Probabilistic Robotics. MIT Press.
• Crystal, D. (2001). Language and the Internet. Cambridge University Press.
• Oudeyer, P. Y., & Smith, L. B. (2016). How Evolution May Work through Curiosity-
Driven Developmental Process. Topics in Cognitive Science, 8(2), 492-502.
• Russel, S., & Norvig, P. (2016). Artificial Intelligence: A Modern Approach. Pearson.
• Breazeal, C. (2003). Toward Sociable Robots. Robotics and Autonomous Systems,
42(3-4), 167-175.

You might also like