Code
We are commited to open sourcing and we will try to contribute our most succesful work. To be always updated check our github page: https://github.com/unr-arl
|
Motion Primitives-based Exploration Path Planner (MBPlanner)
We release our Motion Primitives-based exploration path planner (MBPlanner) developed for the DARPA Subterranean Challenge as part of the R&D activities of Team CERBERUS (https://www.subt-cerberus.org/) and tested/verified with both conventional and collision-tolerant aerial robots.
Repository: https://github.com/unr-arl/mbplanner_ros
Overview summary: https://www.autonomousrobotslab.com/subtplanning.html
Graph-based Exploration Path Planner (GBPlanner)
We release our Graph-based exploration path planner (GBPlanner) developed for the DARPA Subterranean Challenge as part of the R&D activities of Team CERBERUS (https://www.subt-cerberus.org/) and tested/verified with both aerial (traditional and collision-tolerant) and legged (ANYmal) robots.
Repository: https://github.com/unr-arl/gbplanner_ros
Overview summary: https://www.autonomousrobotslab.com/subtplanning.html
Image Brighten
ROS node implementing low light image enhancement. The output image will have the same header as the input image. The node will run at the parameterized rate, always processing the latest image. In the event computation speed cannot keep up with the desired rate, additional images will be dropped.
Repository: https://github.com/unr-arl/image_brighten_ros
History-aware Free Space Detection
This package is capable of proposing appropriate directions for exploration by utilizing a sliding-window history of the robot’s pose estimates and the depth measurements of the environment to identify the directions of probable unobservable free space in enclosed environments. More specifically, the method finds areas of sparse sensor returns near the end of the robot’s perception in the vicinity of areas with no sensor returns and determines the directions to these areas to be the probable directions of free space due to the consistency of the lack of sensor readings with the shape of the environment. In tunnel like environments, the probable direction of free space is likely to be the center of the tunnel, while in other cases it may be the center of an open room or closer to a wall that is more heavily observed by the robot’s sensors this is because we cannot assume that merely the lack of sensor readings is the same as free space. This method can be used to assist a path planner by determining the directions of probable free space for efficient exploration.
Repository: https://github.com/unr-arl/hfsd
Visual Saliency-aware Exploration Planner
This is the ROS package of our Visual Saliency-aware Exploration planner. This planner employs a 2-step optimization paradigm according which it first identifies a finite-depth path that maximizes the volumetric exploration gain, while the way towards the first viewpoint of that path is calculated through a second planning step that optimizes for the observation of salient regions.
Repository: https://github.com/unr-arl/vseplanner
Receding Horizon Exploration and Mapping Planner
This is the ROS package of our Localization Uncertainty-aware Receding Horizon Exploration and Mapping planner. This planner employs a 2-step optimization paradigm according which it first identifies a finite-depth path that maximizes the volumetric exploration gain, while the way towards the first viewpoint of that path is calculated through a second planning step that optimizes for minimized expected localization uncertainty.
Repository: https://github.com/unr-arl/rhem_planner
Motion Analysis Cortex Mocap ROS Brige
This is a ROS bridge for the Motion Analysis motion capture system and its software framework Cortex.
Repository: https://github.com/unr-arl/cortex_ros_bridge
Next-Best-View Exploration Planner
The Receding Horizon Next-Best-View Exploration planner is a ROS package that iteratively computes maximum information gain exploratory trajectories, executes the first step and repeats the whole process in a receding horizon fashion. No prior knowledge of the world is required.
Repository: https://github.com/unr-arl/nbvplanner
Structural Inspection Planner
The Structural Inspection Planner is a ROS package provides efficiently computed full coverage path given a prior model of the structure to be inspected, and motion constraints of the robot as well as its sensor model.
Repository: https://github.com/unr-arl/StructuralInspectionPlanner
Control for Rotary-Wing Micro Aerial Vehicles with ROS
A ROS-based set of control structures (Linear and Nonlinear MPC as well as PID) for Micro Aerial Vehicles
Repository: https://github.com/ethz-asl/mav_control_rw
Robust Model Predictive Control
This is a MATLAB implementation of Robust MPC which further supports code generation.
Repository: https://github.com/unr-arl/rmpc_mav
Dubins Airplane Solver
This is a python implementation of the Dubins Airplane boundary value solver
Repository: https://github.com/unr-arl/DubinsAirplane
Lin-Kerninghan-Helsgaun TSP Solver
This is a python wrapper of the freely available Lin-Kerninghan-Helsgaun TSP Solver
Repository: https://github.com/unr-arl/LKH_TSP
We release our Motion Primitives-based exploration path planner (MBPlanner) developed for the DARPA Subterranean Challenge as part of the R&D activities of Team CERBERUS (https://www.subt-cerberus.org/) and tested/verified with both conventional and collision-tolerant aerial robots.
Repository: https://github.com/unr-arl/mbplanner_ros
Overview summary: https://www.autonomousrobotslab.com/subtplanning.html
Graph-based Exploration Path Planner (GBPlanner)
We release our Graph-based exploration path planner (GBPlanner) developed for the DARPA Subterranean Challenge as part of the R&D activities of Team CERBERUS (https://www.subt-cerberus.org/) and tested/verified with both aerial (traditional and collision-tolerant) and legged (ANYmal) robots.
Repository: https://github.com/unr-arl/gbplanner_ros
Overview summary: https://www.autonomousrobotslab.com/subtplanning.html
Image Brighten
ROS node implementing low light image enhancement. The output image will have the same header as the input image. The node will run at the parameterized rate, always processing the latest image. In the event computation speed cannot keep up with the desired rate, additional images will be dropped.
Repository: https://github.com/unr-arl/image_brighten_ros
History-aware Free Space Detection
This package is capable of proposing appropriate directions for exploration by utilizing a sliding-window history of the robot’s pose estimates and the depth measurements of the environment to identify the directions of probable unobservable free space in enclosed environments. More specifically, the method finds areas of sparse sensor returns near the end of the robot’s perception in the vicinity of areas with no sensor returns and determines the directions to these areas to be the probable directions of free space due to the consistency of the lack of sensor readings with the shape of the environment. In tunnel like environments, the probable direction of free space is likely to be the center of the tunnel, while in other cases it may be the center of an open room or closer to a wall that is more heavily observed by the robot’s sensors this is because we cannot assume that merely the lack of sensor readings is the same as free space. This method can be used to assist a path planner by determining the directions of probable free space for efficient exploration.
Repository: https://github.com/unr-arl/hfsd
Visual Saliency-aware Exploration Planner
This is the ROS package of our Visual Saliency-aware Exploration planner. This planner employs a 2-step optimization paradigm according which it first identifies a finite-depth path that maximizes the volumetric exploration gain, while the way towards the first viewpoint of that path is calculated through a second planning step that optimizes for the observation of salient regions.
Repository: https://github.com/unr-arl/vseplanner
Receding Horizon Exploration and Mapping Planner
This is the ROS package of our Localization Uncertainty-aware Receding Horizon Exploration and Mapping planner. This planner employs a 2-step optimization paradigm according which it first identifies a finite-depth path that maximizes the volumetric exploration gain, while the way towards the first viewpoint of that path is calculated through a second planning step that optimizes for minimized expected localization uncertainty.
Repository: https://github.com/unr-arl/rhem_planner
Motion Analysis Cortex Mocap ROS Brige
This is a ROS bridge for the Motion Analysis motion capture system and its software framework Cortex.
Repository: https://github.com/unr-arl/cortex_ros_bridge
Next-Best-View Exploration Planner
The Receding Horizon Next-Best-View Exploration planner is a ROS package that iteratively computes maximum information gain exploratory trajectories, executes the first step and repeats the whole process in a receding horizon fashion. No prior knowledge of the world is required.
Repository: https://github.com/unr-arl/nbvplanner
Structural Inspection Planner
The Structural Inspection Planner is a ROS package provides efficiently computed full coverage path given a prior model of the structure to be inspected, and motion constraints of the robot as well as its sensor model.
Repository: https://github.com/unr-arl/StructuralInspectionPlanner
Control for Rotary-Wing Micro Aerial Vehicles with ROS
A ROS-based set of control structures (Linear and Nonlinear MPC as well as PID) for Micro Aerial Vehicles
Repository: https://github.com/ethz-asl/mav_control_rw
Robust Model Predictive Control
This is a MATLAB implementation of Robust MPC which further supports code generation.
Repository: https://github.com/unr-arl/rmpc_mav
Dubins Airplane Solver
This is a python implementation of the Dubins Airplane boundary value solver
Repository: https://github.com/unr-arl/DubinsAirplane
Lin-Kerninghan-Helsgaun TSP Solver
This is a python wrapper of the freely available Lin-Kerninghan-Helsgaun TSP Solver
Repository: https://github.com/unr-arl/LKH_TSP