CS 591: Intelligent Assistive Robotics

Spring 2018 | Fridays | 10:45am - 1:15pm

Instructor Siddharth Srivastava

Office hours Tuesdays and Wednesdays 2-3pm, BYENG 592

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.

Course format

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.

Projects 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

Tentative Schedule

To be refined during the first few classes.

Weeks Topics
1-2 Introduction, recap of task planning and motion planning
  • Basics of robotics simulation packages
  • Recent/pathbreaking papers on
    • Extensions of motion planning to handle logic
    • Advances in robot perception for object manipulation
    • Human factors in assistive robotics
6 Project proposals due (following 1x1 discussions with instructor)
7-13 Recent papers: integrated reasoning, perception, learning and execution in robotics
  • Integrated task and motion planning for mobile manipulation
  • Applications of statistical reasonnig in mobile manipulation
14-16 Papers selected based on student interest; project presentations