Dec-MCTS: Decentralized planning for multi-robot active perception
We propose a decentralized variant of Monte Carlo tree search (MCTS) that is suitable for a
variety of tasks in multi-robot active perception. Our algorithm allows each robot to optimize …
variety of tasks in multi-robot active perception. Our algorithm allows each robot to optimize …
Robotic ecology: Tracking small dynamic animals with an autonomous aerial vehicle
Understanding animal movements that underpin ecosystem processes is fundamental to
ecology. Recent advances in animal tags have increased the ability to remotely locate larger …
ecology. Recent advances in animal tags have increased the ability to remotely locate larger …
Online planning for multi-robot active perception with self-organising maps
We propose a self-organising map (SOM) algorithm as a solution to a new multi-goal path
planning problem for active perception and data collection tasks. We optimise paths for a …
planning problem for active perception and data collection tasks. We optimise paths for a …
Planning-aware communication for decentralised multi-robot coordination
We present an algorithm for selecting when to communicate during online planning phases
of coordinated multi-robot missions. The key idea is that a robot decides to request …
of coordinated multi-robot missions. The key idea is that a robot decides to request …
Multi-robot region-of-interest reconstruction with Dec-MCTS
We consider the problem of reconstructing regions of interest of a scene using multiple robot
arms and RGB-D sensors. This problem is motivated by a variety of applications, such as …
arms and RGB-D sensors. This problem is motivated by a variety of applications, such as …
Contour-based next-best view planning from point cloud segmentation of unknown objects
A novel strategy is presented to determine the next-best view for a robot arm, equipped with
a depth camera in eye-in-hand configuration, which is oriented to autonomous exploration of …
a depth camera in eye-in-hand configuration, which is oriented to autonomous exploration of …
Monte Carlo planning for active object classification
Classifying objects in complex unknown environments is a challenging problem in robotics
and is fundamental in many applications. Modern sensors and sophisticated perception …
and is fundamental in many applications. Modern sensors and sophisticated perception …
Decentralised Monte Carlo tree search for active perception
We propose a decentralised variant of Monte Carlo tree search (MCTS) that is suitable for a
variety of tasks in multi-robot active perception. Our algorithm allows each robot to optimise …
variety of tasks in multi-robot active perception. Our algorithm allows each robot to optimise …
Surfel-based next best view planning
Next best view (NBV) planning is a central task for automated three-dimensional (3-D)
reconstruction in robotics. The most expensive phase of NBV computation is the view …
reconstruction in robotics. The most expensive phase of NBV computation is the view …
Multi-robot path planning for budgeted active perception with self-organising maps
We propose a self-organising map (SOM) algorithm as a solution to a new multi-goal path
planning problem for active perception and data collection tasks. We optimise paths for a …
planning problem for active perception and data collection tasks. We optimise paths for a …