Zobrazeno 1 - 10
of 50
pro vyhledávání: '"Cristian-Ioan Vasile"'
Publikováno v:
Proceedings of the 26th ACM International Conference on Hybrid Systems: Computation and Control.
Autor:
Xiao Li, Guy Rosman, Igor Gilitschenski, Brandon Araki, Cristian-Ioan Vasile, Sertac Karaman, Daniela Rus
Publikováno v:
IEEE Robotics and Automation Letters. 7:984-991
Publikováno v:
IEEE Robotics and Automation Letters. 7:1190-1197
Publikováno v:
IEEE Robotics and Automation Letters. 7:2297-2304
In this work, we focus on decomposing large multi-agent path planning problems with global temporal logic goals (common to all agents) into smaller sub-problems that can be solved and executed independently. Crucially, the sub-problems' solutions mus
Partial Satisfaction of Signal Temporal Logic Specifications for Coordination of Multi-robot Systems
Publikováno v:
Algorithmic Foundations of Robotics XV ISBN: 9783031210891
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::36b7248daa614934e412919da7ae3e02
https://doi.org/10.1007/978-3-031-21090-7_14
https://doi.org/10.1007/978-3-031-21090-7_14
Publikováno v:
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Time-series data classification is central to the analysis and control of autonomous systems, such as robots and self-driving cars. Temporal logic-based learning algorithms have been proposed recently as classifiers of such data. However, current fra
Autor:
Kaier Liang, Cristian-Ioan Vasile
Publikováno v:
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Mobility-on-demand systems are transforming the way we think about the transportation of people and goods. Most research effort has been placed on scalability issues for systems with a large number of agents and simple pick-up/drop-off demands. In th
Autor:
Brandon Araki, Kiran Vodrahalli, Daniela Rus, Thomas Leech, Mark Donahue, Cristian-Ioan Vasile
Publikováno v:
Autonomous Robots. 45:1013-1028
We introduce a method to learn policies from expert demonstrations that are interpretable and manipulable. We achieve interpretability by modeling the interactions between high-level actions as an automaton with connections to formal logic. We achiev
Model-free continuous control for robot navigation tasks using Deep Reinforcement Learning (DRL) that relies on noisy policies for exploration is sensitive to the density of rewards. In practice, robots are usually deployed in cluttered environments,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2c73ec8abf733db821f04508ad329132
Publikováno v:
The International Journal of Robotics Research. 39:1002-1028
We develop a sampling-based motion planning algorithm that combines long-term temporal logic goals with short-term reactive requirements. The mission specification has two parts: (1) a global specification given as a linear temporal logic (LTL) formu