Saeid Amiri

I am PhD student at AIR Lab, SUNY Binghamton, where I work on knoweldge-based robotics sequential decision making algorithms. More specifically, I am interested in leveraging commonsense knowledge in POMDPs and Reinforcement Learning.

I am also a research educator for the Freshman Research Immersion (FRI) program, where I teach first-year students and mentor their AI research projects. Previously, I did an internship with ABB Robotics on vision-based deep RL. I got my Masters and Bachelors in Mechanical Engineering with a focus on control theory.

Email  /  Google Scholar  /  Github

profile photo
Research

I'm interested in AI symbolic planning under uncertainty and Reinforcement Learning. Much of my research is about developing sequential decision making frameworks under partial observability. Representative papers are highlighted.

Reasoning with Scene Graphs for Robot Planning under Partial Observability
Saeid Amiri, Kishan Chandan, Shiqi Zhang

ICRA, 2022
paper / demo / webpage / presentation / slides
Guiding Robot Exploration in Reinforcement Learning via Automated Planning
Yohei Hayamizuk, Saeid Amiri, Kishan Chandan, Seiki Takadama, Shiqi Zhang

ICAPS, 2021
paper / demo / poster

Using action knowledge to guide the model-based RL.

Learning and Reasoning for Robot Sequential Decision Making under Uncertainty
Saeid Amiri, Mohammad S. Shirazi, Shiqi Zhang

AAAI, 2020   (Oral Presentation)
paper / demo / code / slides / poster

Using supervised learning and automated reasoning to guide a POMDP-based symbolic planner

Augmenting Knowledge through Statistical,Goal-oriented Human-Robot Dialog
Saeid Amiri, Sujay Bajracharya, Cihangir Goktolga, Jesse Thomason, Shiqi Zhang
IROS, 2019
paper / arxiv / demo / code / slides / interview with Texplore

A robotic dialogue system that simultanuously identifies human intention and auigments its knowledge base.

Multi-modal Predicate Identification using Dynamically Learned Robot Controllers
Saeid Amiri, Suhua Wei, Jesse Thomason, Jivko SInapov, Shiqi Zhang, Peter Stone
IJCAI, 2018
paper / slides / code / poster

Leveraging Multi-Sensory data to guide a robot to identify object properties.

Related Work Experience
Robotics Gradute Research Intern

ABB Robotics, 2020

Vision-bsaed grasping using deep reinforcement learning

Research Educator

Freshman Research Immersion program at SUNY Binghamton, 2020 & 2021

Course website

Teaching First-year students AI and robotics and mentor them in their research projects.

Service
Program committee, AAAI-21, IJCAI-20, AAMAS-22, FLAIRS-22

Reviewer for ICRA-21 and IROS-20

Resources
  • Paper writing:
    1. "Writing a technical paper" in robotics by Stefanie Tellex.
    2. "Stanford scientific writing course".
    3. "Academic-Writing-Check tool".
    4. "Latex tips and tricks".
  • Paper reading:
    1. "How to read a paper" by Stefanie Tellex.
    2. Another video from Andrew Ng in CS230.
  • Submission/review:
    1. "How to write rebuttals" by Devi Parikh.
    2. "How to write a good review", the CVPR20 tutorial.
    3. AAAI reviewing guidelines.
    4. Handy "Chrome extension" for finding Bibtex faster by Anthony Chen.
  • Probability:
    1. "Review of Probability Theory" from CS229 at Stanford.


  • Template Source