843727
Description
Mind Map by Jonathan Zinger, updated more than 1 year ago
|
Created by Jonathan Zinger
over 10 years ago
|
|
Robotics
- Agents
- Autonomous
Robots
- Architecture
- Rebellion
- Brittle
- Computationally Expensive
- Slow (NP-Hard or worse)
- Slow (NP-Hard or worse)
- Computationally Expensive
- 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
- Voting
- Agent Ignores sensor, does
hard-coded thing "always go
forward"
- Stateful Behavior
Based
Architectures
- Need memory if environment
doesn't include all clues needed
to make decisions
- Need memory if environment
doesn't include all clues needed
to make decisions
- Subsumption
Architecture
- Parallel
- Arbitration
- Message Passing
- Inhibit
- Parallel
- Hybrid - hierarchical with subsumption behaviors
- Stateless
Behavior-Based
Architectures
- Brittle
- 3 tiered
- The Wrangler
- Deliberator
- Executive
- Control
- Effectors
- World
- Sensors
- Feature Selection
- Feature Selection
- Sensors
- World
- Effectors
- Control
- Executive
- Deliberator
- The Wrangler
- Rebellion
- Agent with real
world
environment
- Architecture
- Continuous Behavior
- FSA Macros
- Motor Schema Behaviors
- Multiagent Systems
- Cooperative
- Competitive
- Multiagent Learning
- Team Learning
- Learning a solution for multiple
agents
- Learning a solution for multiple
agents
- Collaborative Learning
- Multiple agents learning solutions
- Multiple agents learning solutions
- Team Learning
- Cooperative
- Self Contained (no
joystick)
- Environmental
Feedback
- Autonomous
Robots
- Bayes Filters
- Kalman
- Gaussian distribution
defines where robot is
located
- Gaussian distribution
defines where robot is
located
- Particle
- Distribution is a random sample of points
in your space. Use EC like fitness-based
selection to choose parents for next
generation of points
- Distribution is a random sample of points
in your space. Use EC like fitness-based
selection to choose parents for next
generation of points
- Tell where the robot is
probably located
- Prior Prob of Robots
State
- Transition Model
- Sensor Model
- Kalman
Want to create your own Mind Maps for free with GoConqr? Learn more.