Robotics

Robotics

Agents
1. Autonomous Robots
  1. Architecture
    1. Rebellion
      1. Brittle
        Computationally Expensive
        Slow (NP-Hard or worse)
      2. Subsumption - Brooks
        Stateless Behavior-Based Architectures
        Agent Ignores sensor, does hard-coded thing "always go forward"
        Act based on sensor, no memory
        Arbitration
        Voting
        Simultaneous
        Precedence
        Subsumption
        Stateful Behavior Based Architectures
        Need memory if environment doesn't include all clues needed to make decisions
        Subsumption Architecture
        Parallel
        Arbitration
        Message Passing
        Inhibit
        Hybrid - hierarchical with subsumption behaviors
    2. 3 tiered
      1. The Wrangler
        Deliberator
        Executive
        Control
        Effectors
        World
        Sensors
        Feature Selection
  2. Agent with real world environment
2. Continuous Behavior
3. FSA Macros
4. Motor Schema Behaviors
5. Multiagent Systems
  1. Cooperative
  2. Competitive
  3. Multiagent Learning
    1. Team Learning
      1. Learning a solution for multiple agents
    2. Collaborative Learning
      1. Multiple agents learning solutions
6. Self Contained (no joystick)
7. Environmental Feedback
Bayes Filters
1. Kalman
  1. Gaussian distribution defines where robot is located
2. Particle
  1. Distribution is a random sample of points in your space. Use EC like fitness-based selection to choose parents for next generation of points
3. Tell where the robot is probably located
4. Prior Prob of Robots State
5. Transition Model
6. Sensor Model

Siguiente

Descripción

Resumen del Recurso

Similar

	Creado por Jonathan Zinger hace más de 10 años