Multi-agent Pose-Graph Sensor Fusion - from "Multi-robot Coordination with Agent-Server Architecture for Autonomous Navigation in Partially Unknown Environments", IROS 2020
I'm tring to run voxblox multi agent in a real world demo, but I also want to do it without gps i.e using pure VIO. I want to let those agents to gradually merge into one map like ccm-slam or covins did. And I find pose_graph_backend is capable of doing this, because it has a map merging function.
So Luca, do you have any suggestions on how to modify this? Or is there some way I can fake this gps thing using pure visual-inertial odometry?
I'm really looking forward to your rely! Thank you!
Hello, I am trying to adapt this repo in my work, but it feels like it's not really polished. In debug, I found the ThreadSafeQueue's methods like PushIfBlocking block very offen, feels like some lock issue. I need to changed them to nonblock one to make it work. And also LoopDetection::addKeyFrame blocks, won't return. Is this somehow I use this repo in a wrong way, or you hanve some futher update for it not yet pushed?
I'm trying to build a project on top of pose_graph_backend, but somehow I can not initialize the node i.e can not establish topics.
So when i am debugging, I find that whole system got stuck at "params.voc_ptr = std::make_shared(bow_voc_file)" in parameter-reader.cpp, I don't know what happened, could you please help me on this?
By the way, I'm using Ubuntu 20 noetic.Really looking forward to your reply!
I'm trying to understand the comm_msgs between client and server, in comm_msgs::keyframe I find "connections" message type, but I don't know the meaning of it, why do we need this message and how it works separately in the client side and server side.
This really confuses me, I'm really looking forward to your reply! Thank you!