© sebastian thrun, CMU, CS226 Statistical Techniques In Robotics Paper Style Guide Sebastian Thrun and Rahul Biswas Office: Gates 154, Office hours: Monday 1:30-3pm

© sebastian thrun, CMU, A Brief Guide to Writing Papers  …this is extremely ad hoc

© sebastian thrun, CMU, A Conference Paper Layout On-A-Slide  Abstract (short is sweet!) Problem, gap, approach, key results  Introduction Broad problem and impact “scientific gap” (what technical aspects have not yet been solved) summary approach (should include reference to technical gap) key results  Approach Background tutorial (if necessary) Your technical innovation (might be multiple pages/sections, with repeated reference to scientific gap)  Results Main questions that are being investigated in experiments, ref to gap possibly with main results highlighted Data sets, simulator, implementation details Empirical results (might be multiple pages)  Related Work Don’t just say what’s been done. Point out how prior work relates to yours and to the scientific gap you set forth in the intro.  Summary/Discussions/Conclusion Summary problem, approach, result, in past tense Discuss open questions, promising research directions  References

© sebastian thrun, CMU, Lesson # 1  Put yourself into the position of the reader!

© sebastian thrun, CMU, Lesson # 2  Motivate your problem Why does it matter? Why is it not solved yet? What impact would a solution have? What contribution did you make?

© sebastian thrun, CMU, Lesson # 3  It doesn’t matter how you got there “We tried A, it didn’t work, therefore we tried B”  “B works. To see, let us consider an obvious alternative A, and show A does not work”  Document progress, not just achievement “B works”  “B improves over A (current techniques) by X, which is important because of …”

© sebastian thrun, CMU, Reviewer Background Expertise Reviewers may not be familiar with your area: Problem motivation State of the art Background material Notation Measures for evaluation Significant application domains

© sebastian thrun, CMU, Reviewers are Overworked Don't expect them to pay attention to details Don't expect them to read small fonts Motivate problem, explain why open, why interesting Present one idea, not two, three,... Pick informative title A picture is worth 1000 words Be concise! Get to the point! Run a spell/grammar checker Use terminology consistently Define abbreviations, avoid them if possible Convince reader that experiments fit claims/problem Make sure the paper “flows”

© sebastian thrun, CMU, Summary CS226  Bayes Filter (BN representation, update formula) Kalman filter, EKF Information filter, EIF Particle filter Binary Bayes filter, Histogram filter  Localization, specifically MCL Probabilistic kinematics (motion model) Probabilistic sensor models  SLAM Classical EKF solution Information representation (sparse, lazy) Particle filter solution (FastSLAM, Rao-Blackwellization) Data association: Lazy; particles  Planning and Control Dynamic programming for MDPs Dynamic programming for POMDPs (piecewise linear, convex) Approximation techniques (belief state compression via PCA)

© sebastian thrun, CMU, Lessons learned (?)  How to extract information from sensors  How to