CS 980: Planning for Robots

Professor Wheeler Ruml

This graduate seminar is focused on research in the area of planning, which is the part of AI concerned with deciding what to do. The exact topic will be determined by the interests of the participants. Student from prior years are welcome to take the class again and either extend their previous work or choose a new topic. Examples of possible topics include:

Projects can be implemented in simulation or on the CS department's three mobile robots. These platforms include high-quality laser rangefinders, 7-DOF arms, and RGB-D sensors. Projects are encouraged to be done in teams. The main student deliverables will be brief written responses to the papers each week and a substantial research paper reporting on the project at the end of the semester. Prior exposure to algorithms (eg, CS 758/858) and artificial intelligence (eg, CS 730/830) is recommended but not required. Advanced undergraduates in CS and graduate students outside of CS are welcome but should probably check with me before enrolling.

Meeting time and place: For Spring 2017, we are scheduled to meet Tuesdays and Thursdays 2:10-3:30pm in Kingsbury N233. Let me know if you can't make it at those times and we can try to find a time that works for everyone.

Starting in fall 2017, the seminar will switch to being offered every fall semester.

Schedule for Spring 2017

on deck: velocity obstacles (ICRA, 2008), CL-RRTs (IEEE Trans Control Sys Tech, 2009), Hooker (J Heuristics, 1996), PRMs, Dynamic Controllability (CPAIOR-14); DyKnow, Stanley (JFR, 2006), Boss (JFR, 2008), driving (ICRA 2011), STEHS (IROS 2015), anytime SIP (IROS, 2012), humans collision cones (CDC, 2015), trajectory generation (Auton. Rob., 2015)

Tues Apr 25: variable level-of-detail planning (ECAI, 2010)

Tue Apr 11: TBL (ICRA, 2009)

Tues Mar 21: architecture

Tue Feb 28: D*lite (IEEE TRO, 2005)

Tue Feb 14: MP-RRT (ICRA, 2007)

Tue Feb 7: PLRTA* (AI Comm, 2014)

Thu Feb 2: ARA* (NIPS, 2003)

Tue Jan 31: Planning Long Dynamically Feasible Maneuvers (IJRR, 2009)

Thu Jan 26: We'll talk about what topics we want to cover and the hardware we have to play with. To prepare, you might want to browse around ROS.org and review How to Read a Paper and The Task of the Referee.


Schedule for Spring 2016

Thu May 5: Mo'RTS (SoCS, 2015)

[ Tue May 3: no class, Wheeler away ]

Thu Apr 27: AEES (SoCS, 2012)

Tue Apr 26: PLRTA* (AI Comm, 2014)

Thu Apr 21: TBA* (ICRA, 2009)

Tue Feb 9: implementing heuristic search algorithms in C++ (SoCS, 2012) and in Java (IBM devWorks, 2013)

Thu Feb 4: Dynamic f hat (JAIR, 2015)

Tue Feb 2: real-time search (AIJ, 1990) - might require being on UNH network

Thu Jan 28: ARA* (NIPS, 2003)

Tue Jan 26: We'll talk about what topics we want to cover and look over the hardware we have to play with. To prepare, you might want to browse around ROS.org and review How to Read a Paper and The Task of the Referee.


Schedule from Fall 2014

The queue: RTAA* (AAMAS, 2006); Field D* (JFR, 2007); Implementing RRTs and PRMs (ICRA, 2012); RRT* (IJRR, 2011); HPN with uncertainty (IJRR, 2013), planning modulo theories (ICAPS 2012), Hauser (AAAI ws 2010), GTP (ICRA, 2014), RRT-connect (ICRA, 2000), optimality in robot motion (CACM, 2014), POMCP (NIPS, 2010)

Wed Dec 17, 10am: Final papers (1 hardcopy and an emailed PDF), videos (preferably mp4), and source code (emailed tarball) due at Wheeler's office.

Fri Dec 12, noon (NOTE NEW TIME): final paper presentations (15-20 min talk + 10 min discussion each). Be sure to bring a video of your system working.

Wed Dec 10: Discussion of final papers (25 min each). Bring 3 copies of each of your reviews to class.

Mon Dec 8: Review version of final papers due - bring 4 hardcopies. Here's a link to ICRA format for LaTeX. No other reading due.

Wed Dec 3: multi-heuristic A* (RSS, 2014)

Mon Dec 1: autonomous quadcopters (RAM 2014)

[ Wed Nov 26 is a "Friday" ]

Mon Nov 24: CIRCA (AIJ, 1995)

Wed Nov 19: NAMO (WAFR, 2012)

Mon Nov 17: quick status update presentations. Also, give Wheeler a hardcopy outline of your final paper, including a title and full abstract.

Wed Nov 12: SMAP (ICRA 2010)

Mon Nov 10: nearest neighbors (PAMI, 2014). If you haven't seen k-d trees, background is here (TOMS, 1977). And FYI, adapting k-d trees for motion planning (TRO 2007)

Wed Nov 5: grasping from vision (IROS, 2005)

Mon Nov 3: manipulation (IJRR, 2004)

Wed Oct 29: informed RRT* (IROS, 2014)

Mon Oct 27: ATS+EB (Auton Robots, 2012)

Wed Oct 22: quick status update presentations Also, f-biased RRT (extended version of SoCS, 2012)

Mon Oct 20: [ special meeting place for today: CEPS Dean's conference room (W290?) ] particle filters (UAI invited talk, 2002)

Wed Oct 15: [ special meeting place for today: ECE conference room: Kingsbury W208 ] multipartite RRTs (ICRA, 2007)

Mon Oct 13: RR-GP (Auton Robots, 2013)

Wed Oct 8: model-predictive motion planning (R&AMag, 2014)

Mon Oct 6: pose references (extended version of ICRA, 2014)

Wed Oct 1: PLRTA* (AICom, 2014)

Mon Sep 29: SPARSE-RRT (IROS 2013)

Wed Sep 24: RRT (IJRR, 2001)

Mon Sep 22: Planning Long Dynamically Feasible Maneuvers (IJRR, 2009)

Wed Sep 17: HPN (ICRA, 2011)

Mon Sep 15: aSyMov (IJRR, 2009)

Wed Sep 10: hybrid search (AAAI, 2013)

Mon Sep 8: ARA* (NIPS, 2003)

Wed Sep 3: We'll talk about what topics we want to cover and look over the hardware we have to play with. To prepare, you might want to browse around ROS.org and review How to Read a Paper and The Task of the Referee.


Other resources


Valid HTML 4.01 Transitional