CS 591: Intelligent Assistive Robotics
Spring 2018 | Fridays | 10:45am - 1:15pm | BYAC 260
Instructor Siddharth Srivastava
Office hours Tuesdays and Wednesdays 2-3pm, BYENG 592
Contact details BYENG 592 | firstname.lastname@example.org | 480-727-7451 (email is strongly preferred)
The focus of this course is on techniques for making robots
intelligent enough to be able to assist humans. This topic
constitutes a very active area of research in academia as well as
industry, with multiple academic and commercial organizations
jumping in to explore and develop the potential of robots that help
humans. We will learn advanced tools for robotics that empower autonomous systems such as self-driving cars and study how they can be extended to enable versatile assitive robots.
This course covers some of the recent advances in
intelligent robotics, particularly focusing on aspects relating to the
theory and practice of getting robots to reason about and accomplish
assistive tasks in indoor environments. Students will have the
opportunity to learn how to use robotics simulators, and to gain an
understanding of this active research area including topics from
motion planning, perception, learning and reasoning under uncertainty
with a special reference to mobile manipulation. Final projects will
be used to apply the learned knowledge and test new ideas in
simulation or on a physical robot.
The course is designed as a seminar class
that will start with a brief recap of the fundamentals and move on to
discussion and evaluation of prominent research papers. Students will
play a key role in the selection of papers in the later half of the
course. Weekly meetings will be organized as instructor and student
led discussions of the selected papers. A detailed schedule of
presentations will be developed with the students at the beginning
of the semester.
Students will propose and implement final projects. Given the
challenging nature of the topic, students will have flexibility in the
design and nature of projects, going from novel algorithmic solutions
for subproblems to implementations of existing techniques on an
application designed by the team.
Project development will be an essential component and students
will be guided from early stages of their projects. Project proposals
will be due 6 weeks from the start of the course. Most projects are
expected to be demonstrated using robotics simulators; exceptionally
performing teams will get the opportunity to demonstrate their work on
a physical robot towards the end of the semester.
Grading and expectations
There will be no midterm or final
exams. Each team will be expected to produce a final report with clear
indications of each team member’s role in the project. Each student
will submit critiques for a subset (to be determined) of the selected
research papers and lead the discussion of at least one of the
selected papers. Grades will be assigned based on students' critiques
and discussion-leads (30%), innovation in the final project’s design
and implementation (35%) and final report (35%).
471 or 571 or Instructor’s Approval
To be refined during the first few classes.
||Introduction, recap of task planning and motion planning
|| Motion planning and Robot simulators
||Going beyond motion planners
Gravot, Fabien, et al. "aSyMov: a planner that deals with intricate symbolic and geometric problems." ISRR 2005.
Plaku, Erion, et al. "Sampling-based motion and symbolic action planning with geometric and differential constraints." ICRA 2010
||Constraint based TMP solvers
Garrett, Caelan, et al. "Sample-based methods for factored task and motion planning." RSS 2017
Dantam, Neil T., et al. "Incremental task and motion planning: a constraint-based approach." RSS 2016.
Marthi, Bhaskara, et al. "Angelic semantics for high-level actions." 2007.
Srivastava, Siddharth, et al. "Metaphysics of planning domain descriptions." AAAI 2016.
Project proposals due
Srivastava, Siddharth, et al. "Combined task and motion planning through an extensible planner-independent interface layer." ICRA 2014.
Konidaris, George, et al. "Constructing symbolic representations for high-level planning." AAAI. 2014.
||Learning and using hierarchies for SDM
Hofmann, Till, et al. "Initial results on generating macro actions from a plan database for planning on autonomous mobile robots" ICAPS 2017.
Nan, Rong, et al. "MDPs with unawareness in robotics." UAI 2016.
||Perception for navigation
Durrant-Whyte, Hugh, et al. "Simultaneous localization and mapping (SLAM): Part I." IEEE RAS magazine,13(2), 99-110.
Bailey, Tim, et al. "Simultaneous localization and mapping (SLAM): Part II." IEEE RAS Magazine, 13(3), 108-117.
Devin, Coline, et al. "Learning modular neural network policies for multi-task and multi-robot transfer." ICRA 2017 [Learning for manipulation]
||Perception for manipulation
Xiang, Yu, et al. "Objectnet3d: A large scale database for 3d object recognition." ECCV 2016.
Mahler, Jeffrey, "Dex-net 1.0: A cloud-based network of 3d objects for robust grasp planning using a multi-armed bandit model with correlated rewards." ICRA 2016
||Learning for manipulation
Vicente, Pedro, et al. "Towards markerless visual servoing of grasping tasks for humanoid robots." ICRA 2017
Fern, Alan et al. "A Decision-Theoretic Model of Assistance", JAIR 2014 [Shared Autonomy]
Javdani, Shervin, et al. "Shared autonomy via hindsight optimization". RSS 2015.
Milliken, Lauren, et al. "Modeling user expertise for choosing levels of shared autonomy." ICRA 2017.
Ribeiro, Marco Tulio, et al. "Why should I trust you?: Explaining the predictions of any classifier". KDD 2016.
Hayes, Bradely, et al. "Improving robot controller transparency through autonomous policy explanation." HRI 2017.
||User-friendly robot control
Coronado, Enrique, et al. "Gesture-based robot control: Design challenges and evaluation with humans." ICRA 2017.
Huang, Justin, et al. "Code3: A system for end-to-end programming of mobile manipulator robots for novices and experts." ICRA 2017.
||Communication and assistive robotics
Huang, Sandy, et al. "Enabling robots to communicate their objectives." RSS 2017.
Broad, Alexander, et al. "Path planning under interface-based constraints for assistive robotics." ICAPS 2016.
||Project reports due
Absence and Make-up Policies
If a student is unable to present on a scheduled date due to extenuating circumstances, an arrangement will be made to reschedule their presentation. Accommodations will be made for religious observances provided that students notify the instructor at the beginning of the semester concerning those dates. Students who expect to miss class due to officially university-sanctioned activities should inform the instructor early in the semester. Alternative arrangements will generally be made for any examinations and other graded in-class work affected by such absences. The preceding policies are based on ACD 304–04, “Accommodation for Religious Practices” and ACD 304–02, “Missed Classes Due to University-Sanctioned Activities.”
Cell phones and pagers must be turned off
during class to avoid causing distractions, unless instructed by the
presenters (e.g., for online polling software). The use of recording
devices is not permitted during class. Any violent or threatening
conduct by an ASU student in this class will be reported to the ASU
Police Department and the Office of the Dean of Students.
All students in this class are subject to ASU’s Academic Integrity Policy (available at http://provost.asu.edu/academicintegrity) and should acquaint themselves with its content and requirements, including a strict prohibition against plagiarism. All violations will be reported to the Dean’s office, who maintain records of all offenses. Students are expected to abide by the FSE Honor Code (http://engineering.asu.edu/integrity/).
Suitable accommodations will be made for students having disabilities and students should notify the instructor as early as possible if they will require same. Such students must be registered with the Disability Resource Center and provide documentation to that effect.
Title IX is a federal law that provides that no person be excluded on the basis of sex from participation in, be denied benefits of, or be subjected to discrimination under any education program or activity. Both Title IX and university policy make clear that sexual violence and harassment based on sex is prohibited. An individual who believes they have been subjected to sexual violence or harassed on the basis of sex can seek support, including counseling and academic support, from the university. If you or someone you know has been harassed on the basis of sex or sexually assaulted, you can find information and resources at https://sexualviolenceprevention.asu.edu/faqs.
As a mandated reporter, I am obligated to report any information I become aware of regarding alleged acts of sexual discrimination, including sexual violence and dating violence. ASU Counseling Services, https://eoss.asu.edu/counseling, is available if you wish discuss any concerns confidentially and privately.
Notice: Any information in this syllabus (other than grading and absence policies) may be subject to change with reasonable advance notice.
Notice: All contents of these lectures, including written materials distributed to the class, are under copyright protection. Notes based on these materials may not be sold or commercialized without the express permission of the instructor. [Note: Based on ACD 304-06.]