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
Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation
Ria Doshi, Homer Walke, Oier Mees, Sudeep Dasari, Sergey Levine
Bayesian Optimization Framework for Efficient Fleet Design in Autonomous Multi-Robot Exploration
David Molina Concha, Jiping Li, Haoran Yin, Kyeonghyeon Park, Hyun-Rok Lee, Taesik Lee, Dhruv Sirohi, Chi-Guhn Lee
Active Sensing Strategy: Multi-Modal, Multi-Robot Source Localization and Mapping in Real-World Settings with Fixed One-Way Switching
Vu Phi Tran, Asanka G. Perera, Matthew A. Garratt, Kathryn Kasmarik, Sreenatha G. Anavatti
Collaborative Graph Exploration with Reduced Pose-SLAM Uncertainty via Submodular Optimization
Ruofei Bai, Shenghai Yuan, Hongliang Guo, Pengyu Yin, Wei-Yun Yau, Lihua Xie