intelligent agent perception

32
:: Intellig ent Agent Percepti on :: Molly Maymar Columbia University July 2015

Upload: molly-maymar

Post on 14-Aug-2015

260 views

Category:

Technology


1 download

TRANSCRIPT

Page 1: Intelligent Agent Perception

:: IntelligentAgent Perception:: Molly Maymar

Columbia UniversityJuly 2015

Page 2: Intelligent Agent Perception

What is Intelligent Agent Perception?

Perception is the process by which intelligent agents sense, perceive, and interpret their external worlds [8], called domains [4]. Agents use built-in sensors in order to obtain sensory data [2].

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 3: Intelligent Agent Perception

During the perceptual process, an intelligent agent assigns meaning to incoming visual, auditory, olfactory, and/or tactile sensory data [2]. The assignment of meaning can be bottoms-up, by which data significance is drawn directly from sensation, or top-down, by which previously perceived or programmed meanings are recalled and assigned to current data [2]. Perception can be top-down within a single cycle, in that the agent relies on recent recollections of the same data—in the same domain and within the same problem space—to inform data significance in real-time [2].

I. What is Intelligent Agent Perception?

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 4: Intelligent Agent Perception

Perception entails the filtering of sensory information [2]. Through a process called attention—by which the agent determines how to direct its perceptual resources [4] and select the most relevant, urgent, or important information in its world—the agent ignores some sensory data while processing others [2].  The output of the perceptual process is a percept—a categorical judgment or concept that the agent has created as a result of the perceptual process [11,2].

I. What is Intelligent Agent Perception?

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 5: Intelligent Agent Perception

• “Perception tends to be ambiguous and noisy.” [9]

• Noisy sensors interfere with agents’ abilities to perceive their worlds completely and accurately [4]

• Dynamic worlds [4] mean that agents cannot rely on pre-programmed models or sensory information [5] and must undertake more complex data filtering processes [2]

Impediments to the Perceptual Process

I. What is Intelligent Agent Perception?

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 6: Intelligent Agent Perception

The agent combines perceptual data; recognition and categorization of familiar patterns to build a model of its domain and/or the dynamics of that domain, in order that the agent can best sense and act [4,9,2]

An example is an agent using vision to detect features of its world and then using these features to determine its position within the world, as well as the obstacles it will encounter [9]

Situation Assessment

I. What is Intelligent Agent Perception?

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 7: Intelligent Agent Perception

Intelligent agents sense through simple, inexpensive modalities like temperature measurement and/or complex, expensive modalities [4] like stereo vision—seeing in 3D by using two cameras as “eyes” [5]. The input from these modalities can be combined and output as a single assessment [4,11].

How Do Intelligent Agents Perceive?

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 8: Intelligent Agent Perception

The most common method for acquiring sensory data is through sensors.

Sensor data comes in two varieties [10]:

• Data that characterizes the momentary situation

EX: camera images, laser range scans

• Data related to a change in the situation EX: controls, odometer readings

II. How Do Intelligent Agents Perceive?

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 9: Intelligent Agent Perception

Model-based robotics rely on complete and accurate, pre-programmed models of the robot and its environment in order for the robot to perceive and act. This method presents challenges in dynamic or noisy environments, which do not accurately reflect the models [10].

Traditional Approaches to Robotic Perception

II. How Do Intelligent Agents Perceive?

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 10: Intelligent Agent Perception

Behavior-based robotics rely on immediate sensor feedback for determining a robot’s action. This method places physical limits on perceptual process and poses boundaries on the types of task that can be handled using this approach [10].

II. How Do Intelligent Agents Perceive? :: Traditional Approaches

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 11: Intelligent Agent Perception

Bayes’ Theorem Bayes’ Theorem is a rule that is used to determine how an agent filters new data, based on previous knowledge [9,8]. Bayes’ rule is an equation for showing the relationship between a conditional probability (the probability of event1, given that event2 has already occurred) and its reverse form (the probability of event2, given event1) [9]. 

II. How Do Intelligent Agents Perceive?

How is Sensor Data Interpreted?

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 12: Intelligent Agent Perception

Bayes Theorem is as follows [8]:P(A|B) = P(B|A) * P(A)/P(B)  P(A) is the probability of A, independent of BP(B) is the probability of B, independent of AP(A|B) is the probability of A, given that B is trueP(B|A) is the probability of B, given that A is true 

II. How Do Intelligent Agents Perceive? :: Sensor Data :: Bayes’ Rule

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 13: Intelligent Agent Perception

Molly’s Example:

An agent needs to know if an object is a cat P(cat) is the probability of an object being a cat, whether or not it has pointy ears

P(ears) is the probability of an object having pointy ears, whether or not it is a cat

P(cat|ears) is the probability the object is a cat, given it has pointy ears

P(ears|cat) is the probability an object has pointy ears, given that it is a cat 

II. How Do Intelligent Agents Perceive? :: Sensor Data :: Bayes’ Rule

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 14: Intelligent Agent Perception

Molly’s Example:

The agent would determine the probability of whether or not the object is a cat using the following formula: P(cat|ears) = P(ears|cat) * P(cat)/P(ears)

II. How Do Intelligent Agents Perceive? :: Sensor Data :: Bayes’ Rule

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 15: Intelligent Agent Perception

Probabilistic Algorithms Probabilistic algorithms, also called randomized algorithms, account for the inherent uncertainty in intelligent agent perception [10]. Agents use sensors to input data from their environments. As a result of sensor limitations, noise, and environmental dynamism and unpredictability, their input is uncertain. Probabilistic algorithms process sensor data in a way that computes a probability distribution over what might be the case in the agent’s world overall, versus generating a single best guess [10].

II. How Do Intelligent Agents Perceive? :: Sensor Data

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 16: Intelligent Agent Perception

Probabilistic algorithms have proven successful with mobile robot localization—the problem of finding out the robot’s coordinates relative to its environment—and mapping—the problem of generating maps from sensor measurements [10].

II. How Do Intelligent Agents Perceive? :: Sensor Data :: Probabilistic Algorithms

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 17: Intelligent Agent Perception

Probabilistic algorithms are preferable to traditional approaches to robotic perception, like methods associated with model- and behavior-based robotics, in that they are more robust in the face of sensor limitations, noise, and environmental dynamics. They are computationally inefficient in that they consider entire probability densities, so they generate approximate outputs [10].

II. How Do Intelligent Agents Perceive? :: Sensor Data :: Probabilistic Algorithms

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 18: Intelligent Agent Perception

Artificial Neural Networks An artificial neural network (ANN) is an information processing technique inspired by the way that the human nervous system processes information. In human brains, neurons receive signals—electric impulses transmitted by chemical processes—from other neurons, modify the signals, and forward them to their connections. An artificial neuron is a computational unit with many inputs and one output. It forwards signals, or “fires”, based on the input pattern received [5].

II. How Do Intelligent Agents Perceive? :: Sensor Data

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 19: Intelligent Agent Perception

ANNs are comprised of interconnected firing neurons capable of being trained. ANNs consist of three layers: an input layer, a hidden layer, and an output layer. Each sensory input arrives in an input node in the input layer. This input is then provided to every node in the hidden layer, where each connection is assigned a weight. The output value of every hidden node is then provided to the output node, where connections are again weighted and then output as a percept [5,11,2].

II. How Do Intelligent Agents Perceive? :: Sensor Data :: Artificial Neural Networks

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 20: Intelligent Agent Perception

II. How Do Intelligent Agents Perceive?

Machine learning is the science of pattern recognition and computational learning theory in artificial intelligence. Machine learning focuses on the construction and study of algorithms that learn from and make predictions on data [6]. In order to ensure more robust robot perception in light of unpredictable, dynamic, and noisy real-world scenarios, scientists pair machine learning approaches with biologically-inspired sensor systems [5].

Sensors + Machine Learning

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 21: Intelligent Agent Perception

Some Examples:

Visual Sensors + ANN

Researchers working with the iCub humanoid robot sought to show that artificial neural networks can be trained to allow humanoid robot spatial perception in Cartesian (3D) coordinates. Spatial perception is the detection and localization of objects in the robot’s world [5].

II. How Do Intelligent Agents Perceive? :: Sensors + Machine Learning

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 22: Intelligent Agent Perception

The iCub, moving autonomously in a world, obtained visual information from two cameras. The ANN provided the robot with the ability to estimate the position of camera-identified objects relative to itself in this 3D space. The ANN was comprised of three separate neural networks—one trained to predict object position and robot poses along the X axis, one along the Y, and one along the Z. Visual input regarding image coordinates and robot poses arrived in each input node and each output layer provided an estimate of the object and robot’s position along one Cartesian axis [5]. The iCub showed that by training ANNs, artificial agents can learn the skill of estimating object locations based on visual perception [5].

II. How Do Intelligent Agents Perceive? :: Sensors + Machine Learning :: Visual + ANN

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 23: Intelligent Agent Perception

Haptic Sensors + Classification Algorithms

Researchers working with the ALoF robot (autonomous legged robot on four legs) used a classification algorithm—an algorithm that selects the best possible hypothesis based on observed data [1]—to identify the geometric texture shape and surface properties of a robot’s selected footholds based on haptic information, or tactile feedback [3].

II. How Do Intelligent Agents Perceive? :: Sensors + Machine Learning

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 24: Intelligent Agent Perception

Researchers bisected each of ALoF’s legs and placed force sensor resisters at the bisection in order to capture haptic feedback from ALoF’s knee joint movement when it was trodding on different surfaces. The resistors registered the normal force (the force supporting the weight of ALoF’s “femur” on its “tibia”, or tibia on the floor) and moments (the force necessary to rotate the tibia on the knee/axis) in the joint. ALoF “walked” and “scratched” on artificial terrain textured separately in four geometrical shapes, ranging from a Teflon-like surface to a rocky-feeling one [3].

II. How Do Intelligent Agents Perceive? :: Sensors + Machine Learning :: Haptic + Classification

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 25: Intelligent Agent Perception

When trained in real-world walking force and contact force measurement data samples, a special classification algorithm, called a boosting algorithm—which combines a weighted ensemble of weak classifiers into a stronger one, and is slightly more accurate than a probabilistic algorithm—was able to identify surface types based on the haptic feedback [3].

II. How Do Intelligent Agents Perceive? :: Sensors + Machine Learning :: Haptic + Classification

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 26: Intelligent Agent Perception

ALoF showed that robots can use haptics, or tactile sensory information, to identify local surface properties. This will help robots characterize their environment while walking through it, especially when detailed environmental models have not been supplied in advance [3].

II. How Do Intelligent Agents Perceive? :: Sensors + Machine Learning :: Haptic + Classification

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 27: Intelligent Agent Perception

Pressure Sensors + ANN + Offline Planning

Through the integration of sensor-based techniques, offline planning, and an ANN, researchers sought to inform the development of a new breed of safe and intelligent robots that could share a common workspace with humans [7].

II. How Do Intelligent Agents Perceive? :: Sensors + Machine Learning

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 28: Intelligent Agent Perception

Conventional offline planning techniques—preprogrammed automation tasks reliant on complete knowledge of the static environment—require complete knowledge about the static environment. They do not account for human motion, which is unpredictable, and unstructured or time-varying interactive environments [7].

II. How Do Intelligent Agents Perceive? :: Sensors + Machine Learning :: Sensors + ANN + Offline

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 29: Intelligent Agent Perception

In this study, humans stood on mats consisting of pressure-activated nodes. Data collected by the nodes was clustered into subsets corresponding to each foot using a self-organizing map (SOM)—a special class of ANN that discovers salient features in time-varying data sets without any prior training. Using these subsets, each human’s body orientation and location were derived and paired with average human body dimensions in order to obtain a model of each person [7].

II. How Do Intelligent Agents Perceive? :: Sensors + Machine Learning :: Sensors + ANN + Offline

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 30: Intelligent Agent Perception

Researchers will use online information sensed by the mats and interpreted by the SOM to modify robots’ predefined motion paths, in order that the robots can reach their intended goals, or preform their automated functions, while avoiding obstacles. This will allow robots to collaborate safely and amicably with humans [7].

II. How Do Intelligent Agents Perceive? :: Sensors + Machine Learning :: Sensors + ANN + Offline

Intelligent Agent Perception | Molly Maymar | 7.10.2015

Page 31: Intelligent Agent Perception

References [1] Castelli, V. (2005). Lecture 2. Retrieved from: http://www.ee.columbia.edu/~vittorio/Lecture-2.pdf [2] Goertzel, B., & Wang, P. (2007). A foundational architecture for artificial general intelligence. Advances in Artificial General Intelligence: Concepts, Architectures and Algorithms, 6, 36.

[3] Höpflinger, M., Remy, C. D., Hutter, M., Spinello, L., & Siegwart, R. (2010, May). Haptic terrain classification for legged robots. In Robotics and Automation (ICRA), 2010 IEEE International Conference on (pp. 2828-2833). IEEE. [4] Langley, P., Laird, J. E., & Rogers, S. (2009). Cognitive architectures: Research issues and challenges. Cognitive Systems Research, 10(2), 141-160 [5] Leitner, J., Harding, S., Frank, M., Forster, A., & Schmidhuber, J. (n.d.). Artificial neural networks for spatial perception: Towards visual object localisation in humanoid robots. The 2013 International Joint Conference on Neural Networks (IJCNN). [6] Machine Learning (2015, July 3). Wikipedia. Retrieved from:https://en.wikipedia.org/wiki/Machine_learning [7] Najmaei, N., & Kermani, M. R. (2011). Applications of artificial intelligence in safe human–robot interactions. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, 41(2) 448-459. [8] Nilsson, N. J. (2009). The quest for artificial intelligence. Cambridge University Press. [9] Poole, D. L., & Mackworth, A. K. (2010). Artificial Intelligence: foundations of computational agents. Cambridge University Press. [10] Thrun, S. (2000). Probabilistic algorithms in robotics. Ai Magazine, 21(4), 93. [11] Wang, P. (2014). Perception. Introduction to artificial intelligence [online lecture notes]. Retrieved from:http://www.cis.temple.edu/~pwang/3203-AI/Lecture/IO-2.htm

Page 32: Intelligent Agent Perception

:: Thank You

::

All Images obtainedfrom http://sid766.tumblr.com