8:45-9:00
Opening remarks
9:00-9:40
Keynote 1: Building Dependable and Verifiable Autonomous Systems
Chuchu Fan, MIT
9:40-10:20
Paper presentation 1
10:20-11:30
Tutorial [slides]
Workshop organizers
11:30-12:30
Lunch break and poster session
12:30-13:10
Keynote 2: Towards Sample-efficient Safe Learning for Online Nonlinear Control under Uncertainty
Wenhao Luo, UNC
13:10-13:50
Keynote 3: Safety via Hamilton-Jacobi Reachability and Reinforcement Learning
Mo Chen, SFU
13:50-14:40
Paper presentation 2
14:40-15:20
Keynote 4: Safety-Critical Control and Learning under Model Uncertainty with Application to Robotics
Koushil Sreenath, UC Berkeley
15:20-16:00
Keynote 5: Prescribed-Time Robust Safety
Miroslav Krstic, UCSD
16:00-17:00
Panel discussion: Yorie Nakahira, Andrew Clark, Chuchu Fan, Wenhao Luo, Mo Chen, Miroslav Krstic
Paper presentation 1
9:40-9:50
Joint Synthesis of Safety Certificate and Safe Control Policy using Constrained Reinforcement Learning [pdf]
Presenter: Haitong Ma
9:50-10:00
A Hierarchical Long Short Term Safety Framework For Efficient Robot Manipulation under Uncertainty [pdf]
Presenter: Suqin He
10:00-10:10
Model-based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian [pdf]
Presenter: Baiyu Peng
10:10-10:20
Q&A
Paper presentation 2
13:50-14:00
Verification and Synthesis of Control Barrier Functions [pdf]
Presenter: Andrew Clark
14:00-14:10
Safe Control in the Presence of Stochastic Uncertainties [pdf]
Presenter: Xiang Wang
14:10-14:20
Model-free Safe Control for Zero-Violation Reinforcement Learning [pdf]
Presenter: Weiye Zhao
14:20-14:30
Safe Control with Neural Network Dynamic Models [pdf]
Presenter: Tianhao Wei
14:30-14:40
Q&A
Suggested citation of papers:
@InProceedings{citation_key,
title = article_title,
author = list_of_authors,
booktitle = MECC Workshop on Safe Control and Learning under Uncertainty,
year = 2021}