1

Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning
This paper describes a method to exploit environmental symmetries in reinforcement learning by constructing equivariant policies and invariant value functions without specialized neural network components. We show how equivariant ensembles and regularization benefit sample efficiency and performance in a map-based path planning case study.
Mirco Theile, Hongpeng Cao, Marco Caccamo, Alberto L. Sangiovanni-Vincentelli
PDF Cite Code Project Video DOI
Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning
Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learning
We develop a cloud-edge architecture that allows for decoupled inference and training when controlling a system using computationally constrained hardware.
Hongpeng Cao, Mirco Theile, Federico G. Wyrwal, Marco Caccamo
PDF Cite Project Video DOI
Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learning
UAV Path Planning using Global and Local Map Information with Deep Reinforcement Learning
We show that UAV path planning can be made scalable by presenting the agent with a coarse but complete global map and a precise but incomplete local map of the environment.
Mirco Theile, Harald Bayerlein, Richard Nai, David Gesbert, Marco Caccamo
PDF Cite Code Project DOI
UAV Path Planning using Global and Local Map Information with Deep Reinforcement Learning
Autonomous hierarchical multi-level clustering for multi-uav systems
Jonathan Ponniah, Mirco Theile, Or D. Dantsker, Marco Caccamo
Cite DOI
Integrated Power Simulation for a Solar-Powered, Computationally-Intensive Unmanned Aircraft
Or D. Dantsker, Mirco Theile, Marco Caccamo, Seongyong Hong
Cite Project
Long Endurance Flight Testing Results for the UIUC-TUM Solar Flyer
Or D. Dantsker, Mirco Theile, Marco Caccamo
Cite Project
UAV Path Planning for Wireless Data Harvesting: A Deep Reinforcement Learning Approach
Autonomous deployment of unmanned aerial vehicles (UAVs) supporting next-generation communication networks requires efficient …
Harald Bayerlein, Mirco Theile, Marco Caccamo, David Gesbert
PDF Cite Code Project DOI
UAV Path Planning for Wireless Data Harvesting: A Deep Reinforcement Learning Approach
UAV Coverage Path Planning under Varying Power Constraints using Deep Reinforcement Learning
Coverage path planning (CPP) is the task of designing a trajectory that enables a mobile agent to travel over every point of an area of …
Mirco Theile, Harald Bayerlein, Richard Nai, David Gesbert, Marco Caccamo
PDF Cite Code Project DOI
UAV Coverage Path Planning under Varying Power Constraints using Deep Reinforcement Learning
Latency-Aware Generation of Single-Rate DAGs from Multi-Rate Task Sets
Modern automotive and avionics embedded systems integrate several functionalities that are subject to complex timing requirements. A …
Michaela Verucchi, Mirco Theile, Marco Caccamo, Marko Bertogna
PDF Cite Project DOI
Continued development and flight testing of a long-endurance solar-powered unmanned aircraft: Uiuc-tum solar flyer
Or D. Dantsker, Mirco Theile, Marco Caccamo, Simon Yu, Moiz Vahora, Renato Mancuso
Cite Project