Abstract: The integration of robotic systems alongside human agents introduces significant challenges in decision-making, planning, and control. In particular, navigation algorithms for robots must account for interactions with humans to ensure safety and efficiency. In this talk, I will present an overview of four research directions we've explored in our work on Interaction-Aware Planning and Decision Making. First, we will explore interactive path planning in environments with dynamic agents, including approaches based on path-speed decomposition and multi-future planning under optimization-based frameworks. Next, I will discuss sampling-based methods for interactive planning, highlighting how neural networks can be incorporated into these frameworks. Third, we will examine strategies for crash mitigation when formal safety guarantees cannot be established. Finally, I will introduce recent efforts on end-to-end predictive planning approaches that aim to unify perception and decision-making.
Bio: Dr. Tariq is a Senior Research Scientist in the Cooperative Intelligence - Mobility Research group at the Honda Research Institute, US. He received his B.Sc. degree in electrical and electronics engineering from the Middle East Technical University, Ankara, Turkey, in 2018. He received his M.S. and Ph.D. degrees in electrical and computer engineering from the University of Maryland, College Park, MD, USA, in 2022 and 2023, respectively. His research interests include the application of control, optimization, and learning techniques to robotic systems, with a focus on real-time decision-making and motion planning for autonomous vehicles. He received the Best Student Paper Award (1st place) at the IEEE International Conference on Intelligent Transportation Systems (ITSC), 2021.
Looking forward to seeing you on Friday! In addition, for full information and recordings of the seminar talks, please check our seminar website below!
Robotics Seminar Team