Developing reinforcement learning algorithms that satisfy safety constraints is becoming increasingly important in real-world applications. In multi-agent reinforcement learning …
W Luo, W Sun, A Kapoor - Advances in Neural Information …, 2020 - proceedings.neurips.cc
Safety in terms of collision avoidance for multi-robot systems is a difficult challenge under uncertainty, non-determinism, and lack of complete information. This paper aims to propose …
A Peruffo, D Ahmed, A Abate - … conference on tools and algorithms for the …, 2021 - Springer
We introduce an automated, formal, counterexample-based approach to synthesise Barrier Certificates (BC) for the safety verification of continuous and hybrid dynamical models. The …
This paper presents two new control approaches for guaranteed safety (remaining in a safe set) subject to actuator constraints (the control is in a convex polytope). The control signals …
Ö Özkahraman, P Ögren - 2020 59th IEEE Conference on …, 2020 - ieeexplore.ieee.org
Robot missions typically involve a number of desired objectives, such as avoiding collisions, staying connected to other robots, gathering information using sensors and returning to the …
S Yi, Z Temel, K Sycara - 2021 IEEE International Conference …, 2021 - ieeexplore.ieee.org
Robot swarms have been shown to improve the ability of individual robots by inter-robot collaboration. In this paper, we present the PuzzleBots-a low-cost robotic swarm system …
W Xiao, Y Lyu, J Dolan - arXiv preprint arXiv:2304.06281, 2023 - arxiv.org
Multi-Agent Reinforcement Learning (MARL) discovers policies that maximize reward but do not have safety guarantees during the learning and deployment phases. Although shielding …
In this work, we study verification and synthesis problems for safety specifications over unknown discrete-time stochastic systems. When a model of the system is available, barrier …
R Wajid, AU Awan, M Zamani - Learning for Dynamics and …, 2022 - proceedings.mlr.press
Formal synthesis of controllers for stochastic control systems with unknown models is a challenging problem. In this paper, we focus on safety controller synthesis for nonlinear …