Home >Documents >Intelligent Systems Lectures 17 Control systems of robots based on Neural Networks

Intelligent Systems Lectures 17 Control systems of robots based on Neural Networks

Date post:21-Dec-2015
View:236 times
Download:0 times
Share this document with a friend
  • Slide 1
  • Intelligent Systems Lectures 17 Control systems of robots based on Neural Networks
  • Slide 2
  • 15.11.20052 Neuron of MacCallock&Pitts Threshold Logical Unit (TLU)
  • Slide 3
  • 15.11.20053 Geometry of TLU
  • Slide 4
  • 15.11.20054 R-category linear classifier based on TLU
  • Slide 5
  • 15.11.20055 Geometric Interpretation of action of linear classifier
  • Slide 6
  • 15.11.20056 2-layer network Three Planes Implemented by the Hidden Units
  • Slide 7
  • 15.11.20057 Multi Layer Perceptron (MLP) (Feed-forward network)
  • Slide 8
  • 15.11.20058 Kinds of sigmoid used in perceptrons Exponential Rational Hyperbolic tangent
  • Slide 9
  • 15.11.20059
  • Slide 10
  • 10 Formulas for error back propagation algorithm Modification of weights of synapses of j th neuron connected with i th ones, x j state of j th neuron (output) For output layer For hidden layers k number of neuron in next layer connected with j th neuron (1) (2) (3)
  • Slide 11
  • 15.11.200511 Hopfield network X1X1 X2X2 X' 1 X' 2 X N-1 XNXN X' N-1 X' N Y1Y1 Y2Y2 Y N-1 YNYN Features of structure: Every neuron is connected with all others Connections are symmetric, i.e. for all i and j w ij w ji Every neuron may be Input and output neuron Presentation of input is set of state of input neurons
  • Slide 12
  • 15.11.200512 Hopfield network (2) Learning Hebbian rule is used: Weight of link increases for neurons which fire together (with same states) and decreases if otherwise Working (recalling) - iteration process of calculation of states of neurons until convergence will be achieved Each neuron receives a weighted sum of the inputs from other neurons: If the input h j is positive the state of the neuron will be 1, otherwise -1:
  • Slide 13
  • 15.11.200513 Elman Network (SRN). The number of context units is the same as the number of hidden units
  • Slide 14
  • 15.11.200514 Robot-manipulator
  • Slide 15
  • 15.11.200515 Tasks for robot manipulator control system Forward kinematics Kinematics is the science of motion which treats motion without regard to the forces which cause it Within this science one studies the position velocity acceleration and all higher order derivatives of the position variables A very basic problem in the study of mechanical manipulation is that of forward kinematics This is the static geometrical problem of computing the position and orientation of the endeector hand of the manipulator Inverse kinematics This problem is posed as follows given the position and orientation of the endeector of the manipulator calculate all possible sets of joint angles which could be used to attain this given position and orientation This is a fundamental problem in the practical use of manipulators
  • Slide 16
  • 15.11.200516 Tasks for robot manipulator control system (2) Dynamics. Dynamics is a field of study devoted to studying the forces required to cause motion In order to accelerate a manipulator from rest glide at a constant end-effector velocity and finally decelerate to a stop a complex set of torque functions must be applied by the joint actuators In dynamics not only the geometrical properties kinematics are used but also the physical properties of the robot are taken into account. Take for instance the weight inertia of the robotarm which determines the force required to change the motion of the arm. The dynamics introduces two extra problems to the kinematic problems: The robot arm has a memory. Its responds to a control signal depends also on its history (e.g. previous positions speed acceleration) If a robot grabs an object then the dynamics change but the kinematics dont. This is because the weight of the object has to be added to the weight of the arm (thats why robot arms are so heavy making the relative weight change very small)
  • Slide 17
  • 15.11.200517 Tasks for robot manipulator control system (3) Trajectory generation. To move a manipulator from here to there in a smooth controlled fashion each joint must be moved via a smooth function of time. Exactly how to compute these motion functions is the problem of trajectory generation
  • Slide 18
  • 15.11.200518 Camera-robot coordination is function approximation The system we focus on in this section is a work floor observed by a fixed cameras and a robot arm. The visual system must identify the target as well as determine the visual position of the end-effector.
  • Slide 19
  • 15.11.200519 Camera-robot coordination is function approximation (2)
  • Slide 20
  • 15.11.200520 Camera-robot coordination is function approximation (3). Two approach to use neural networks: Usage of feed-forward networks Indirect learning General learning Specialized learning Usage of topology conserving maps
  • Slide 21
  • 15.11.200521 Camera-robot coordination is function approximation (4). feed-forward networks Indirect learning system for robotics. In each cycle the network is used in two different places: first in the forward step then for feeding back the error
  • Slide 22
  • 15.11.200522 Camera-robot coordination is function approximation (5). feed-forward networks (2)
  • Slide 23
  • 15.11.200523 Camera-robot coordination is function approximation (6). feed-forward networks (3) or
  • Slide 24
  • 15.11.200524 Camera-robot coordination is function approximation (7). feed-forward networks (4) The learning rule applied here regards the plant as an additional and unmodiable layer in the neural network The Jacobian matrix can be used to calculate the change in the function when its parameters change where i iterates over the outputs of the plant
  • Slide 25
  • 15.11.200525 Camera-robot coordination is function approximation (8). Topology conserving maps
  • Slide 26
  • 15.11.200526 Camera-robot coordination is function approximation (9). Topology conserving maps (2)
  • Slide 27
  • 15.11.200527 Robot arm dynamics (Kawato et al, 1987)
  • Slide 28
  • 15.11.200528 Robot arm dynamics (2)
  • Slide 29
  • 15.11.200529 Nonlinear transformations used in the Kawato model
  • Slide 30
  • 15.11.200530 Robot arms dynamics (4)
  • Slide 31
  • 15.11.200531 Mobile robots Schematic representation of the stored rooms and the partial information which is available from a single sonar scan
  • Slide 32
  • 15.11.200532 Mobile robots (2) Two problems. The first called local planning relies on information available from the current viewpoint of the robot. This planning is important since it is able to deal with fast changes in the environment. The second situation is called global path planning in which case the system uses global knowledge from a topographic map previously stored into memory Although global planning permits optimal paths to be generated it has its weakness Missing knowledge or incorrectly selected maps can invalidate a global path to an extent that it becomes useless A possible third anticipatory planning combined both strategies the local information is constantly used to give a best guess what the global environment may contain
  • Slide 33
  • 15.11.200533 Mobile robots (3)
  • Slide 34
  • 15.11.200534 Sensor based control
  • Slide 35
  • 15.11.200535 The structure of the network for the autonomous land vehicle
  • Slide 36
  • 15.11.200536 Experiments The network was trained by presenting it samples with as inputs a wide variety of road images taken under different viewing angles and lighting conditions. 1200 Images were presented, 40 times each while the weights were adjusted using the backpropagation principle The authors claim that once the network is trained the vehicle can accurately drive at about km/hour along a path though a wooded area adjoining the Carnegie Mellon campus under a variety of weather and lighting conditions. The speed is nearly twice as high as a non-neural algorithm running on the same vehicle.
  • Slide 37
  • 15.11.200537 Drama
  • Slide 38
  • 15.11.200538 DRAMA (2)
  • Slide 39
  • 15.11.200539 DRAMA (3). Associative module
  • Slide 40
  • 15.11.200540 DRAMA (4)
  • Slide 41
  • 15.11.200541 DRAMA (5)
  • Slide 42
  • 15.11.200542 DRAMA (6) Learning
Popular Tags:

Click here to load reader

Embed Size (px)