cs685-behaviors

cs685-behaviors - Robotic Behaviors Potential field...

Info iconThis preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon
1 Robotic Behaviors Potential field techniques - trajectory generation - closed feedback-loop control Design of variety of behaviors - motivated by potential field based approach – steering behaviors Closed feedback loop systems - no memory - behaviors no representation of the world - world is implicitely encoded in the potential function Motion planning (later) - Representation of the environment - Different choices - Path planning algorithms Jana Kosecka, GMU Potential Field Methods Idea robot is a particle Environment is represented as a potential field (locally) Advantage – capability to generate on-line collision avoidance Compute force acting on a robot – incremental path planning Example: Robot can translate freely , we can control independently Environment represented by a potential function Force is proportional to the gradient of the potential function
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
2 Jana Kosecka, GMU Attractive potential field - Linear function of distance - Quadratic function of distance Combination of two – far away use linear, closer by use parabolic well Jana Kosecka, GMU Repulsive potential field if Minimal distance between the robot and the obstacle else Issues – multiple obstacles – nonconvex obstacles – how to compute distance Can be computed for polygonal and polyhedral obstacles Issues – local minima Heuristics for escaping the local minima Can be used in local and global context Numerical techniques Random walk methods Iterative gradient descent planning Resulting force
Background image of page 2
3 How to do the right thing ? How to do the right thing ? Go from A to B in the context of navigation Taking the environment into account Taking the uncertainty into account Using the model of the environment or not ? The image cannot be displayed. Your computer may not have enough The image cannot be displayed. Your computer may not have enough Perception, Model, Plan, Execute (Motion Controller) © R. Siegwart, I. Nourbakhsh To localize or not? How to navigate between A and B navigation without hitting obstacles detection of goal location Possible by following always the left wall However, how to detect that the goal 5.3 © R. Siegwart, I. Nourbakhsh
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
4 Behavior Based Navigation © R. Siegwart, I. Nourbakhsh Model Based Navigation © R. Siegwart, I. Nourbakhsh
Background image of page 4
5 - no memory – no look-ahead reacts to the current environmental stimuli/ sensory information - reactive behaviors: Feedback controllers are instances of reactive controllers (mappings between situations and actions mapping between state and control input) Can we achieve bigger functionality if we combine them ? Simplest scenario one situation one action: Motivation – biology, V. Braitenberg’s Vehicles one can design simple continuous feedback strategies or sets of if-then rule state rules.
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 6
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 04/07/2010 for the course CS 685 taught by Professor Luke,s during the Fall '08 term at George Mason.

Page1 / 22

cs685-behaviors - Robotic Behaviors Potential field...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online