We are excited to host Wenhao Luo from University of Illinois Chicago over zoom for this week's Robotics Seminar! Join us this Friday, March 7th, at 1 pm CT to learn about multi-agent control! Please see the abstract and biography below:
Title: Harmonizing Safety and Resilience for Adaptive Multi-Agent Systems
Abstract: Reliable interactions among robots require safety and resilient operational guarantees that adapt to real-world conditions. However, most current algorithm designs are rigidly optimized for well-defined and predictable environments. This not only renders pre-computed guarantees brittle under uncertainties and failures, but also incentivizes overly conservative robot behaviors that compromise primary task performance. In this talk, I will present our recent work harnessing safety and resilience for robust and jointly optimized multi-agent autonomy. I will first discuss a control-theoretic method to enforce minimally disruptive safe robotic behaviors under uncertainties, and how to leverage the expressivity of control-theoretic analysis to inspire risk-aware, decentralized multi-agent coordination in autonomous driving. In the presence of incomplete information, I will then show a sample-efficient reinforcement learning framework that allows a robot to safely explore with certified predictive confidence while simultaneously optimizing task performance. Finally, I will turn to resilient autonomy through the example of communication-aware multi-robot coordination. A set of communication-motion co-design frameworks will be demonstrated that allow robots to (i) optimize low-level motion constraints for system-level property guarantees, (ii) utilize data for compositional constraints learning in a realistic environment, and (iii) endure or recover from unexpected robot failures, leading to co-optimized system resilience and task efficiency.
Bio: Wenhao Luo is an assistant professor in computer science at the University of Illinois Chicago. His research lies at the intersection of robotics, control theory, artificial intelligence, and machine learning. Specifically, his group develops principled methods for robust and interactive autonomy that enable robots to safely and effectively collaborate with each other and with humans in the physical world. Wenhao received his M.S. and Ph.D. in Robotics from Carnegie Mellon University in 2016 and 2021, respectively, and a B.E. degree with honors from Central South University in 2012. Before joining UIC, he was an assistant professor at UNC Charlotte (2021-2024) and a research intern at Microsoft Research in the summer of 2019 and 2020. Wenhao’s research has received best paper awards and nominations at multiple conferences, including AAMAS, IFAC CPHS, and workshops at ICRA, IROS, and IJCAI. He was also selected for AAAI New Faculty Highlights at AAAI 2023 and RSS Pioneers at RSS 2021. His work has been supported by NSF, USDA, DARPA, ONR, and AFOSR.
Location: We will meet only virtually. Please use the following zoom meeting information to join us:
https://illinois.zoom.us/j/84149708803?pwd=R3JqMnk3VU0wWUZRbGtMd3o1YjZwdz09&from=addon
Meeting ID: 841 4970 8803
Password: 444347