MW 3:00-4:20, ARC G070

**Instructor:**
Tapomayukh Bhattacharjee

OH: Thursday 3-4pm, CSE2 277

**TA:** Brian Hou

**TA:** Aditya Vamsikrishna Mandalika

OH: Monday 2-3pm, CSE2 152; Wednesday 2-3pm, CSE2 276

**Canvas:** https://canvas.uw.edu/courses/1270226

**Piazza:** https://piazza.com/washington/winter2019/cse571

**Prerequisites:**
familiarity with mathematical proofs, probability, linear algebra, programming

**Grading:** Homeworks (60%), Project (30%), Class participation (10%)

**Textbooks (optional):**

Homework assignments will have both written and programming components. Discussion is encouraged, but each student must independently write up and implement their solutions. All collaborators must be listed on each submission.

Assignments are due online by 11:59 PM on the listed date. Each student has four free late days for the two assignments; if an assignment is submitted after exhausting the late days, it is subject to a 10-point penalty for each day over the budget.

- Homework #1, due
**Thursday, Jan. 31**(pdf, tex, code) - Homework #2, due
**Monday, Mar. 11**(pdf, tex, code)

Writeups must be submitted as a PDF via Gradescope. LaTeX is preferred, but other typesetting methods are acceptable. Code for the programming component must be submitted in a zip archive via Canvas.

Research projects will be completed in teams of three. Students are encouraged to explore any ideas related to robotics or from their own research. Project deliverables and suggested project ideas are now available here.

- Proposal, due
**Monday, Jan. 28** - Progress report, due
**Thursday, Feb. 28** - Poster session,
**Thursday, Mar. 21 2:30-4:20pm** - Final report, due
**Friday, Mar. 22**

Project proposals, progress reports, posters, and final reports must be submitted via Gradescope.

- Enhancing Slam with Dynamic Object Attention (Adam Fishman, Junha Roh, Maxwell Horton)
- Generating dance moves in a humanoid from music (Divye Pratap Jain, Akshat Shrivastava, Andrew Li)
- A Multi-functional Car for SLAM & Trajectory Tracking (Anyi Chen, Hui Fu, Hyunjin Cho)
- Local Collision Avoidance for a Nano-drone (Bindita Chaudhuri, Chung Yi Weng, Melanie Anderson)
- Baseball-Bot: Deep RL and Sim-Real Transfer on a Real Robot (Boling Yang, Xiangyun Meng, Felix Leeb)
- Handover System Based on HERB Robot Arm (Chen Gong, Zeyu Jin)
- Wanderer 16: Navigating Around the Basement (Isaac Ahn, Liangwu Yan, Meixin Zhu)
- Selecting Bite Acquisition Strategies from Food Properties and Positions (Gilwoo Lee, Ethan Gordon, Matt Schmittle)
- Embedding Object Labels in the Map for Semantic Mapping on Mobile Robot (Kousuke Ariga, Chi-Heng Hung, Yao-Chung Liang)
- Safe Person Following using the RACECAR (Ken Latimer, Ivan Evtimov)
- End Effector Imitation Learning for Food Manipulation (Liyiming Ke)
- Comparison of Particle Based Filtering Algorithms in Localization (Henry Lu, Kevin Lin, Ricky Zhang)
- A Person-Following Robot (Nansong Yi, Thomas Wang, Ollin Boer Bohan)
- Implementing Markov Decision Process for Path Planning (Niyousha Rahimi)
- Optimizing Motion-Planning Problem Setup via Bounded Evaluation with Application to Following Surgical Trajectories (Sherdil Niyaz)
- Desk Organization via Relational Learning & Multimodal Inputs (Shivam Singhal)

Date |
Topic |
Slides, Notes |
Reading |

Jan 7 | Introduction and Bayesian Filtering | Slides, Notes | PR Ch. 2 |

Jan 9 | Kalman Filtering | Slides, Notes | PR Ch. 3 |

Jan 14 | Particle Filtering | Notes | PR Ch. 4 |

Jan 16 | Mapping | Slides, Notes | PR Ch. 9 |

Jan 21 | No Lecture | --- | --- |

Jan 23 | Simultaneous Localization and Mapping | Slides | PR Ch. 10, Ch. 13 |

Jan 28 | Planning Intro and Search Algorithms | Slides, Notes | PA Ch. 4, A* |

Jan 30 | Sampling-Based Motion Planning | Slides | PA Ch. 5, RRT |

Feb 4 | No Lecture (Snow) | --- | --- |

Feb 6 | Trajectory Optimization | Anca Dragan's Intro Notes, CHOMP Notes | CHOMP, TrajOpt |

Feb 11 | Task and Motion Planning | Slides, Slides 2, Lecture Video | AI Ch. 10, AP Ch. 2, 4 |

Feb 13 | Feedback Control Overview | Notes | FS Ch. 3, Ch. 7-9, Ch. 11 |

Feb 18 | No Lecture | --- | --- |

Feb 20 | Markov Decision Processes (Debadeepta Dey) | Notes, Slides | RL Ch. 1, Ch. 2, Ch. 3 |

Feb 25 | Model-Based RL + Linear Quadratic Regulator and Extensions (Debadeepta Dey) | Policy and Value Iteration Notes, LQR Notes | LQR, RL Ch. 4 |

Feb 27 | Model-Based RL + Linear Quadratic Regulator and Extensions (Debadeepta Dey) | LQR Tracking Notes, Slides | LQR, RL Ch. 4 |

Mar 4 | Model-Free RL (Debadeepta Dey) | ADP Notes, Policy Gradient Notes | RL Ch. 13 |

Mar 6 | Special Topics: Human-Robot Interaction (Maya Cakmak) | Slides | --- |

Mar 11 | Special Topics: Medical Robotics (Blake Hannaford) | Slides | --- |

Mar 13 | Special Topics: Manipulation and Open Problems (Nathan Ratliff) | --- |