In the proposed method, GPU-based SIFT features is used to realize real-time detection and matching between consecutive frames, their corresponding 3D points are optimized by comparing and fusing IMU data to improve odometry estimation stability, then keyframes are selected for incremental mapping, the graph optimization and moving least squares algorithm are applied to the dense reconstruction. To achieve a full 3D model of indoor environment, we realize the registration for over-lapped models by combining the features of key-frames and Simplified-ICP algorithm.
We plan to use the improved 3D SIFT feature points detection method, which combine with 3D RoPs feature descriptor to realize the estimation for the extrinsic parameters of over-lapped models, the K-Nearest Neighbor and Random Sample Consensus algorithms are used to optimize the accuracy of matched 3D feature points. We will make our code publicly available soon.
paper video code(coming soon...)
MicROS-cloud is a cloud robotic platform which supports the direct deployment of ROS software packages onto the cloud. Basically, it can be regarded as a PAAS platform which adopts the ROS application model. A ROS package can be converted into a cloud service automatically. The robotic applications can access the cloud service remotely in an on-demand style through a WebSocket protocol.
The service access is purely based on a cloud service paradigm, which means that you need not concern ROS master and other configurations. Multiple robots can access a service simultaneously, for example, to build their own map respectively. The robotic applications which access the cloud services also need no modification, because Cloudrid can generate a stub ROS package with the same interface of the original ROS package, which acts as a local proxy of the remote cloud service.
By adopting the docker container technology in the back-end, a ROS package which is orignally designed for a single robot can serve multiple robots simultaneously by dynamically instantiation of the servant in the cloud. And by specifying the resource demand of the ROS package (e.g., mem, CPU, etc.), the quaility of a service can be assured by the internal mechanisms of MicROS-cloud.
Please contact us through firstname.lastname@example.org or email@example.com. Any feedback would be greatly appreciated.
This is an announcement for micros_swarm_framework, developed by Xuefeng, Yanzhen, and Xiaodong. It is a ROS-based programming framework for swarm robotics. Its goal is to facilitate ROS users in developing applications of robot swarms, by providing essential mechanisms, such as abstraction of swarms, swarm management, various communication tools, and a runtime environment, within the standard ROS ecosystem.
Documentation can be found on ROS Wiki: https://wiki.ros.org/micros_swarm_framework. Source code for the framework and demos in the Stage simulator can be found on GitHub: https://github.com/xuefengchang/micros_swarm_framework.
Two papers from the micROS Team were accepted to PRICAI 2016:
2) Multi-level occupancy grids
More details can be found on the Publication and Projects pages.