Representations in Robotics
Spring 2018, 4pm-5:15pm, MonWed
204 Transportation Building
Section: RR, CRN: 68136, 4 hours

Instructor: Steve LaValle, University of Illinois (UIUC)


This course considers fundamental questions in robotics, with particular focus on what needs to go into the robot's "brain." To solve a particular task, such as exploring, navigating, manipulating an object, covering an area, or patrolling a building, how much does the robot need to represent about its surrounding world, including itself? How should it be encoded? Should the representation be discrete, continuous, topological, geometric? What is the value of optimality and optimization in these contexts? What can and cannot be solved by building a representation from a machine learning system?

The first part of the course will involve lectures that explain the technical concepts and frame discussions for the remainder of the class. The second part will involve the study of research articles. Students will take turns presenting papers, which includes independent analysis and leading classroom discussions. A student-selected final project will also be required.

Course Calendar:

Class # Date Lecture Topic Reading Annoucements
Week 1
1 1/17 Course overview
Ch 1 handout 
Week 2
2 1/22 Big vs. little brains
3 1/24 Ergodicity, sensors

Reference Materials:

Paper List: (subject to some changes)

  1. Constructing Symbolic Representations for High-Level Planning, George D. Konidaris, Leslie Kaelbling, and Tomas Lozano-Perez, Proceedings of the Twenty-Eighth Conference on Artificial Intelligence, 2014. Download
  2. Learning state representations with robotic priors, Rico Jonschkowski, Oliver Brock, Autonomous Robots October 2015, Volume 39, Issue 3, pp 407428. Download
  3. Human-level control through deep reinforcement learning, Mnih et al., Nature 518, 529533 (26 February 2015) Download
  4. Scale-Free Coordinates for Multi-Robot Systems with Bearing-only Sensors, Alejandro Cornejo, Andrew J. Lynch, Elizabeth Fudge, Siegfried Bilstein, Majid Khabbazian, James McLurkin, Algorithmic Foundations of Robotics X, pp 397-414, 2013 Download
  5. The importance of a suitable distance function in belief-space planning Z Littlefield, D Klimenko, H Kurniawati, KE Bekris - Robotics Research, 2018 Download
  6. Compound behaviors in pheromone robotics, David Payton, Regina Estkowski, Mike Howard, Volume 44, Issues 3-4, 30 September 2003, Pages 229-240 Download
  7. Concise Planning and Filtering: Hardness and Algorithms, J. M. O'Kane, D. Shell, IEEE Transactions on Automation Science and Engineering ( Volume: 14, Issue: 4, 666 - 1681 Oct. 2017) Download
  8. Simple Robots with Minimal Sensing: From Local Visibility to Global Geometry, Subhash Suri, Elias Vicari, Peter Widmayer, The International Journal of Robotics Research, Vol 27, Issue 9, 2008. Download
  9. RatSLAM: Using Models of Rodent Hippocampus for Robot Navigation and Beyond, Michael Milford, Adam Jacobson, Zetao Chen, Gordon Wyeth, Robotics Research pp 467-485, 2016. Download
  10. On comparing the power of robots. J. M. O'Kane and S. M. LaValle. International Journal of Robotics Research, 27(1):5--23, 2008.
  11. Decentralized Control of Partially Observable Markov Decision Processes using Belief Space Macro-actions, Shayegan Omidshafiei, Ali-akbar Agha-mohammadi, Christopher Amato, Jonathan P. How, The International Journal of Robotics Research, Vol 36, Issue 2, 2017. DOWNLOAD
  12. Hilbert maps: Scalable continuous occupancy mapping with stochastic gradient descent, Fabio Ramos, Lionel Ott, The International Journal of Robotics Research, Volume 35, Issue 14, December 2016.Download
  13. Cognitive Mapping and Planning for Visual Navigation, Saurabh Gupta, James Davidson, Sergey Levine, Rahul Sukthankar, Jitendra Malik, Proceedings of the I EEE Conference on Computer Vision and Pattern Recognition, 2017. Download
  14. SMT-Based Synthesis of Integrated Task and Motion Plans from Plan Outlines, Srinivas Nedunuri, Sailesh Prabhu, Mark Moll, Swarat Chaudhuri, Lydia E. Kavraki, Proceedings of the IEEE International Conference on Robotics and Automation, 2014. Download
  15. A Policy Search Method for Temporal Logic Specified Reinforcement Learning Tasks, Xiao Li, Yao Ma, Calin Belta, arXiv preprint, 2017. Download
Presentation guidelines: PDF