Learning safe control for multi-robot systems: Methods, verification, and open challenges
In this survey, we review the recent advances in control design methods for robotic multi-
agent systems (MAS), focusing on learning-based methods with safety considerations. We …
agent systems (MAS), focusing on learning-based methods with safety considerations. We …
Physics-informed machine learning for modeling and control of dynamical systems
Physics-informed machine learning (PIML) is a set of methods and tools that systematically
integrate machine learning (ML) algorithms with physical constraints and abstract …
integrate machine learning (ML) algorithms with physical constraints and abstract …
Multi-agent partial observable safe reinforcement learning for counter uncrewed aerial systems
The proliferation of small uncrewed aerial systems (UAS) poses many threats to airspace
systems and critical infrastructures. In recent years, there has been a growing interest in …
systems and critical infrastructures. In recent years, there has been a growing interest in …
Robust mader: Decentralized multiagent trajectory planner robust to communication delay in dynamic environments
K Kondo, R Figueroa, J Rached… - IEEE Robotics and …, 2023 - ieeexplore.ieee.org
Communication delays can be catastrophic for multiagent systems. However, most existing
state-of-the-art multiagent trajectory planners assume perfect communication and therefore …
state-of-the-art multiagent trajectory planners assume perfect communication and therefore …
Safe multi-agent reinforcement learning for formation control without individual reference targets
In recent years, formation control of unmanned vehicles has received considerable interest,
driven by the progress in autonomous systems and the imperative for multiple vehicles to …
driven by the progress in autonomous systems and the imperative for multiple vehicles to …
Safe and efficient multi-agent collision avoidance with physics-informed reinforcement learning
Reinforcement learning (RL) has shown great promise in addressing multi-agent collision
avoidance challenges. However, existing RL-based methods often suffer from low training …
avoidance challenges. However, existing RL-based methods often suffer from low training …
Distributionally robust CVaR-based safety filtering for motion planning in uncertain environments
S Safaoui, TH Summers - 2024 IEEE International Conference …, 2024 - ieeexplore.ieee.org
Safety is a core challenge of autonomous robot motion planning, especially in the presence
of dynamic and uncertain obstacles. Many recent results use learning and deep learning …
of dynamic and uncertain obstacles. Many recent results use learning and deep learning …
Decentralized, Safe, Multiagent Motion Planning for Drones Under Uncertainty via Filtered Reinforcement Learning
We propose a decentralized, multiagent motion planner that guarantees the probabilistic
safety of a team subject to stochastic uncertainty in the agent model and environment. Our …
safety of a team subject to stochastic uncertainty in the agent model and environment. Our …
Safe motion planning and formation control of quadruped robots
Z Ji, Y Dong - Autonomous Intelligent Systems, 2024 - Springer
This paper introduces a motion planning and cooperative formation control approach for
quadruped robots and multi-agent systems. First, in order to improve the efficiency and …
quadruped robots and multi-agent systems. First, in order to improve the efficiency and …
Strategic Decision-Making in Multi-Agent Domains: A Weighted Potential Dynamic Game Approach
In interactive multi-agent settings, decision-making complexity arises from agents'
interconnected objectives. Dynamic game theory offers a formal framework for analyzing …
interconnected objectives. Dynamic game theory offers a formal framework for analyzing …