Multi Robot
Multi-robot systems research focuses on coordinating multiple robots to achieve complex tasks more efficiently than single robots could. Current research emphasizes developing robust algorithms for tasks like collaborative mapping, target tracking, and exploration, often employing techniques like distributed optimization, reinforcement learning, and neural networks (including diffusion models and transformers) to handle challenges such as communication constraints, environmental uncertainties, and adversarial conditions. These advancements are significant for improving efficiency and reliability in various applications, including logistics, search and rescue, and environmental monitoring.
Papers
Task-priority Intermediated Hierarchical Distributed Policies: Reinforcement Learning of Adaptive Multi-robot Cooperative Transport
Yusei Naito, Tomohiko Jimbo, Tadashi Odashima, Takamitsu Matsubara
Combining Safe Intervals and RRT* for Efficient Multi-Robot Path Planning in Complex Environments
Joonyeol Sim, Joonkyung Kim, Changjoo Nam
Multi-Robot Collaborative Navigation with Formation Adaptation
Zihao Deng, Peng Gao, Williard Joshua Jose, Hao Zhang
Optimal Integrated Task and Path Planning and Its Application to Multi-Robot Pickup and Delivery
Aman Aryan, Manan Modi, Indranil Saha, Rupak Majumdar, Swarup Mohalik
Shaping Multi-Robot Patrol Performance with Heterogeneity in Individual Learning Behavior
Connor York, Zachary R Madin, Paul O'Dowd, Edmund R Hunt