Shen Li

= Ph.D. candidate at MIT, advised by Prof. Julie Shah.
Interactive Robotics Group, CSAIL.

Previously,
← M.S. in Robotics at CMU,
       Co-advised by Prof. Siddhartha Srinivasa + Prof. Stephanie Rosenthal.
       ∈ Personal Robotics Lab (now at UW), Robotics Institute.
← Internship at CMU, advised by Prof. Katia Sycara.
← B.S. in Computer Science + Psychology at Penn State.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github

profile photo
Research

Research vision = enable robots to safely interact with humans and efficiently accomplish collaborative tasks.

Favorite quote from Prof. Julie Shah: Our vision is to harness the relative strengths of humans and robots to accomplish what neither can do alone.

I develop human-robot collaborative systems, usually in 2 steps:
1. Construct a (data-driven) human model that can be used to predict future human behavior.
2. Develop a decision-making algorithm that enables a robot to efficiently accomplish collaborative tasks while ensuring human physical + psychological safety, based on the human model.

Decision-Making for human-robot (mutual) adaptation
Decision-Making for Bidirectional Communication in Sequential Human-Robot Collaborative Tasks
Vaibhav Unhelkar*, Shen Li*, Julie Shah
HRI 2020 (23.6%)
PDF / video (2:16) / talk video (9:27) / ZDNet news

Robot decision-making on if, when, and what to communicate during collaboration.

Semi-Supervised Learning of Decision-Making Models for Human-Robot Collaboration
Vaibhav Unhelkar*, Shen Li*, Julie Shah
CoRL 2019, Oral Presentation (5%)
PDF / video (4:16)

Semi-supervised human model learning => low efforts on parameter specification & high performance on robot collaborative decision-making.

Fast Online Segmentation of Activities from Partial Trajectories
Tariq Iqbal, Shen Li, Christopher Fourie, Bradley Hayes, Julie Shah
ICRA 2019
PDF / video (2:49) / poster / PBS NewsHour (from 2:58)

Fast online human activity recognition + robot assistance at the appropriate time.

Trust of Humans in Supervisory Control of Swarm Robots with Varied Levels of Autonomy
Changjoo Nam, Huao Li, Shen Li, Michael Lewis, Katia Sycara,
SMC 2018
PDF / project page

Trust and performance in supervisory control of swarm robots with varied levels of autonomy.

Motion Planning for Safe and Efficient Collaboration
Safe and Efficient High Dimensional Motion Planning in Space-Time with Time Parameterized Prediction
Shen Li, Julie Shah
ICRA 2019
PDF / poster

Robot motion-planning for safe (via collision avoidance) and efficient (via planning in both space-time) human-robot collaboration.

Learning Task Specifications from Human Demonstrations
Planning With Uncertain Specifications (PUnS)
Ankit Shah, Shen Li, Julie Shah
RA-L & ICRA 2020
PDF / video (2:11) / MIT news

Robot decision-making under uncertain & non-Markovian task specifications.

Bayesian Inference of Temporal Task Specifications from Demonstrations
Ankit Shah, Pritish Kamath, Shen Li, Julie Shah
NeurIPS 2018
PDF / project page / video (3:05) / poster

Robot learning non-Markovian task specifications from human demonstrations.

Supervised Bayesian Specification Inference from Demonstrations
Ankit Shah, Pritish Kamath, Shen Li, Julie Shah
IJRR (in submission)

Robot learning non-Markovian task specifications from human demonstrations.

Interpretable Robot Behavior
Natural Language Instructions for Human-Robot Collaborative Manipulation
Rosario Scalise*, Shen Li*, Henny Admoni, Stephanie Rosenthal, Siddhartha Srinivasa
IJRR 2018
PDF / project page

A dataset of natural language instructions for object specification in manipulation scenarios (1582 individual written instructions from online crowdsourcing).

Evaluating Critical Points in Trajectories
Shen Li*, Rosario Scalise*, Henny Admoni, Stephanie Rosenthal, Siddhartha Srinivasa
RO-MAN 2017
PDF

Effectiveness of critical way-points that can convey information about robot objectives.

Spatial References and Perspective in Natural Language Instructions for Collaborative Manipulation
Shen Li*, Rosario Scalise*, Henny Admoni, Stephanie Rosenthal, Siddhartha Srinivasa
RO-MAN 2016
PDF / slides / CMU SEI blog

Correlations between clarity of spatial reference instructions and 1) perspective taking 2) spatial features.

Perspective in Natural Language Instructions for Collaborative Manipulation
Shen Li*, Rosario Scalise*, Henny Admoni, Stephanie Rosenthal, Siddhartha Srinivasa
R:SS Workshop on Model Learning for Human-Robot Communication 2016
PDF / slides / poster

Theses
Automatically Evaluating and Generating Clear Robot Explanations
Shen Li
Master's thesis. Carnegie Mellon University. 2017
PDF / slides

Thesis committee: Prof. Siddhartha Srinivasa (co-chair), Prof. Stephanie Rosenthal (co-chair), Prof. Reid Simmons, Prof. Stefanos Nikolaidis

Webpage design courtesy of Jon Barron
Accessibility