Safe Autonomy and Risk Management

Autonomous systems such as self-driving cars, robots, and smart manufacturing systems can have transformative impacts on our society. However, safety risk is a critical issue that must be resolved for the trustworthy operation of autonomous systems. Our group is developing risk-aware optimization and safe learning methods to systematically reduce the risk of unsafe events such as collisions while improving the performance of autonomous systems.
Related Publications

Learning-based distributionally robust motion control with Gaussian processes
Astghik Hakobyan, and Insoon Yang

Safe reinforcement learning for probabilistic reachability and safety specifications
Subin Huh, and Insoon Yang

Wasserstein distributionally robust motion control for collision avoidance using conditional value-at-risk
Astghik Hakobyan, and Insoon Yang

Risk-sensitive safety specifications for stochastic systems using conditional value-at-risk
Margaret P. Chapman, Jonathan P. Lacotte, Kevin M. Smith, Insoon Yang, Yuxi Han, Marco Pavone, Clare J. Tomlin

Wasserstein distributionally robust motion planning and control with safety constraints using conditional value-at-risk
Astghik Hakobyan, and Insoon Yang
IEEE International Conference on Robotics and Automation (ICRA), 2020.

Risk-aware motion planning and control using CVaR-constrained optimization
Astghik Hakobyan, Gyeong Chan Kim, and Insoon Yang
IEEE Robotics and Automation Letters, 2019. (Selected for presentation at IROS 19)

A dynamic game approach to distributionally robust safety specifications for stochastic systems
Insoon Yang
Automatica, 2018.

Safety-aware optimal control of stochastic systems using conditional value-at-risk
Samantha Samuelson, and Insoon Yang
American Control Conference (ACC), 2018. (Extended version)

Optimal control of conditional value-at-risk in continuous time
Christopher W. Miller, and Insoon Yang
SIAM Journal on Control and Optimization, 2017.

Variance-constrained risk sharing in stochastic systems
Insoon Yang, Duncan S. Callaway, and Claire J. Tomlin
IEEE Transactions on Automatic Control, 2017.

Reducing electricity price volatility via stochastic storage control
Insoon Yang, and Asuman E. Ozdaglar
American Control Conference (ACC), 2016.

Indirect load control for financial risk management in electricity markets via risk-limiting dynamic contracts
Insoon Yang, Duncan S. Callaway, and Claire J. Tomlin
American Control Conference (ACC), 2015.

Direct load control for electricity market risk management via risk-limiting dynamic contracts
Insoon Yang, Duncan S. Callaway, and Claire J. Tomlin
Allerton Conference on Communication, Control, and Computing, 2014.

One-shot computation of reachable sets for differential games 
Insoon Yang, Sabine Becker-Weimann, Mina J. Bissell, and Claire J. Tomlin
ACM International Conference on Hybrid Systems: Computation and Control (HSCC), 2013.