Vision-based SLAM Mobile Robot Localization And Mapping With Uncertainty using Scale-Invariant Visual Landmarks -e,lowe, Little Vikash Mansinghka Spren Riisgaard Outline

Defining problem and model so| ution: Minimizing localization error Comb imize gain in explored map bined Information Utilities Integrated Adaptive Information-based Exploration Algorithm

Partially Observable Markov Decision Processes Part II Additional reading: Anthony R. Cassandra. Exact and Approximate Algorithms for Partially Observable Markov Decision Processes. Ph. D. Thesis. Brown University Department of Computer Science, Providence, RI

Handout 2: Gain and Phase margins Eric Feron Feb6,2004 Nyquist plots and Cauchy's principle Let H(s) be a transfer function. eg H(s)= s2+s+1 (s+1)(s+3) Evaluate H on a contour in the s-plane. (your plots here)

Handout 5: Control System Design Principles Eric Feron Feb20,2004 The standard feedback loop Draw the feedback loop here Tracking requirements:

Handout 1: Bode plot rules reminder Eric Feron Feb4,2004 General: Bode plot is to plot magnitudes using logarithm scale, phases using log scales. Indeed:

Review: Constraint-based Interval Planning Simple Temporal Networks Schedulability and Scheduling Review: Temporal, Model-based Programming Managing Execution Uncertainty Execution with Dynamic Scheduling Execution with Explicit Models of Uncertainty

Outline Lightning Summary Black Box Model of SIFT SLAM Vision System Challenges in Computer Vision What these challenges mean for visual SLAM How SIFT extracts candidate landmarks How landmarks are tracked in SIFT SLAM Alternative vision-based SLAM systems Open questions

Leslie Pack Kaelbling, Michael. Littman and Anthony R. Cassandra, \Planning and Acting in Partially Observable Stochastic Domains,\ Artificial Intelligence, Vol. 101, 1998. j. Pineau,g. Gordon&s. Thrun\Point-based- value iteration: An anytime algorithm for POMDPs\. International Joint Conference on Artificial Intelligence(JCAI) Acapulco, Mexico. Aug

Fast Solutions to CSp's Based on PROSSER, P. Hybrid algorithms for the constraint satisfaction problem. Computational Intelligence