no code implementations • 24 Oct 2023 • Gennaro Notomista, Mario Selvaggio, María Santos, Siddharth Mayya, Francesca Pagano, Vincenzo Lippiello, Cristian Secchi
We propose a mathematical representation of such tasks that allows for the execution of more complex and time-varying prioritized stacks of tasks using kinematic and dynamic robot models alike.
no code implementations • 13 Jan 2023 • Gennaro Notomista
This paper presents a constrained-optimization formulation for the prioritized execution of learned robot tasks.
1 code implementation • 11 Oct 2021 • Yousef Emam, Gennaro Notomista, Paul Glotfelter, Zsolt Kira, Magnus Egerstedt
Reinforcement Learning (RL) has been shown to be effective in many scenarios.
Model-based Reinforcement Learning reinforcement-learning +2
no code implementations • 11 Jun 2021 • Gennaro Notomista, Matteo Saveriano
This paper presents an approach to deal with safety of dynamical systems in presence of multiple non-convex unsafe sets.
no code implementations • 26 Aug 2019 • Motoya Ohnishi, Gennaro Notomista, Masashi Sugiyama, Magnus Egerstedt
When deploying autonomous agents in unstructured environments over sustained periods of time, adaptability and robustness oftentimes outweigh optimality as a primary consideration.
no code implementations • 29 Jan 2018 • Motoya Ohnishi, Li Wang, Gennaro Notomista, Magnus Egerstedt
This paper presents a safe learning framework that employs an adaptive model learning algorithm together with barrier certificates for systems with possibly nonstationary agent dynamics.