Zobrazeno 1 - 10
of 6 652
pro vyhledávání: '"CACCAMO, A."'
Real-world accidents in learning-enabled CPS frequently occur in challenging corner cases. During the training of deep reinforcement learning (DRL) policy, the standard setup for training conditions is either fixed at a single initial condition or un
Externí odkaz:
http://arxiv.org/abs/2412.13224
Autor:
Theile, Mirco, Dirnberger, Lukas, Trumpp, Raphael, Caccamo, Marco, Sangiovanni-Vincentelli, Alberto L.
Deep reinforcement learning (DRL) has had success across various domains, but applying it to environments with constraints remains challenging due to poor sample efficiency and slow convergence. Recent literature explored incorporating model knowledg
Externí odkaz:
http://arxiv.org/abs/2412.04327
This paper proposes the SeC-Learning Machine: Simplex-enabled safe continual learning for safety-critical autonomous systems. The SeC-learning machine is built on Simplex logic (that is, ``using simplicity to control complexity'') and physics-regulat
Externí odkaz:
http://arxiv.org/abs/2409.05898
We compute probabilistic controlled invariant sets for nonlinear systems using Gaussian process state space models, which are data-driven models that account for unmodeled and unknown nonlinear dynamics. We investigate the relationship between robust
Externí odkaz:
http://arxiv.org/abs/2407.11256
Autor:
Betz, Tobias, Wen, Long, Pan, Fengjunjie, Kaljavesi, Gemb, Zuepke, Alexander, Bastoni, Andrea, Caccamo, Marco, Knoll, Alois, Betz, Johannes
The automotive industry is transitioning from traditional ECU-based systems to software-defined vehicles. A central role of this revolution is played by containers, lightweight virtualization technologies that enable the flexible consolidation of com
Externí odkaz:
http://arxiv.org/abs/2404.12683
In reinforcement learning (RL), exploiting environmental symmetries can significantly enhance efficiency, robustness, and performance. However, ensuring that the deep RL policy and value networks are respectively equivariant and invariant to exploit
Externí odkaz:
http://arxiv.org/abs/2403.12856
The rigid gang task model is based on the idea of executing multiple threads simultaneously on a fixed number of processors to increase efficiency and performance. Although there is extensive literature on global rigid gang scheduling, partitioned ap
Externí odkaz:
http://arxiv.org/abs/2403.10726
The interactive decision-making in multi-agent autonomous racing offers insights valuable beyond the domain of self-driving cars. Mapless online path planning is particularly of practical appeal but poses a challenge for safely overtaking opponents d
Externí odkaz:
http://arxiv.org/abs/2403.07129
Autor:
Evans, Benjamin David, Trumpp, Raphael, Caccamo, Marco, Jahncke, Felix, Betz, Johannes, Jordaan, Hendrik Willem, Engelbrecht, Herman Arnold
The F1TENTH autonomous driving platform, consisting of 1:10-scale remote-controlled cars, has evolved into a well-established education and research platform. The many publications and real-world competitions span many domains, from classical path pl
Externí odkaz:
http://arxiv.org/abs/2402.18558
Autor:
Sun, Binqi, Roy, Debayan, Kloda, Tomasz, Bastoni, Andrea, Pellizzoni, Rodolfo, Caccamo, Marco
Cache partitioning techniques have been successfully adopted to mitigate interference among concurrently executing real-time tasks on multi-core processors. Considering that the execution time of a cache-sensitive task strongly depends on the cache a
Externí odkaz:
http://arxiv.org/abs/2310.02959