2. Midterm Harder than last final Less time than final No recital But: less than 3/3.5 need to work! Understand midterm => good shape for finals
3. Last 2 week’s exercises Ratslife Tasks Vision Mapping Navigation Planning Strategy Share the load: 1 or 2 tasks per student Present your plan in 2 weeks in class – be specific
5. Error Propagation Intuition: the more sensitive the estimated quantity is to perception error, the more this sensor should be weighted Covariance matrix Representing output uncertainties Function relating sensor input to output quantities Covariance matrix representing input uncertainties
6. Today Sensors for localization Error propagation for localization Position representation Planning
8. Localization Gyroscope Odometry Control input GPS Landmarks Sensor input with different uncertainties. What is the overall uncertainty of the estimate?
11. How does the error build up? Ingredient 1: variance on wheel-speed / slip Ingredient 2: variance on previous position estimate Relation between wheel-speed and position Derivative wrt error Derivative wrt position
23. Reactive vs. Deliberative Planning So far Move randomly Use heuristics (follow wall, spiral, …) Use landmarks (infrared beacons, magnet wire) Use gradients / feedback control (Exercise 2) Today Deliberative planning Reason on abstract representation
24. Exercise: Navigation Algorithms Find the shortest path from A to B Choose the map representation Devise an algorithm to extract path