RIP: Robotic Indoor Plotting

This week, I worked almost entirely in meetings with Shanel and Aditi. We integrated all the subsystems into one central program. This program runs each module in a separate thread: Main thread for control flow and navigation SLAM thread for reading LIDAR data and doing SLAM stitching Movement thread for giving commands to the robot Obstacle thread to interrupt movement when obstacle bumped The SLAM thread is constantly running and updating the map, but we don’t do additional navigation processing…

Read More Read More

This week, most of my work was done in several work sessions with the rest of my team. I made progress on the planning & routing algorithms for the navigation module. I implemented a search that, starting from the current position, expands radially outward until it finds a suitable destination (based on exploredness). Together with Shanel’s implementation of the A* routing algorithm, we now have both components of a navigation algorithm to find a destination as well as plan a…

Read More Read More

This week, I was mostly working on the internal data flow and data structures. The normal BreezySLAM output is a .pgm file, but since we wanted to do extra processing on top of the map, I modified the BreezySLAM script to output a binary file, which is read back in to our data structures. We are working in object-oriented Python, with the bulk of control & data stored in the Map class. The Map class compresses the high-resolution map into…

Read More Read More

My team had several work sessions to combine the different subsystems on a basic level. We decided to ditch Cartographer and ROS SLAM for both complexity and compatibility issues, relying instead on an open source Python package called BreezySLAM. This week, I installed BreezySLAM, ran it through a demo dataset, and extracted the internal data structure representing the SLAM map. I wrote a compression function to reduce the image into a grid heatmap which we plan to do the actual…

Read More Read More

This week, aside from meetings with my team and refactoring the project and the statement of work, I personally primarily worked on getting the Server component up and running. We requested AWS credits which I used to provision an EC2 instance, associated with a file backend also hosted by AWS. I set up my SSH access to the machine, and also a GitHub repo which will be used to store our work and deploy to the server. I did some…

Read More Read More

This week, I flashed Raspbian onto our microSD and got the Pi up and running. In work sessions with Aditi and Shanel, we fleshed out the Design Report, set up Roomba interfacing and control, configured the Pi’s network connection, and installed ROS. We are on track. Work has begun on every component except the server stack, and the design report is basically done. Next week, we hope to set up the Roomba-Pi interface and execute autonomous programs. We will also…

Read More Read More

This week our main focus was on familiarizing ourself with the components. I did some research on the compatibility and specs of the Create 1 model that was available, and concluded that it was not going to be suited for our project, and that we should instead buy a Create 2. The Raspberry Pi we borrowed required some peripherals, but also some setup. For the OS, I would’ve preferred to use Ubuntu Mate, as it is relatively lightweight and very…

Read More Read More

This Week Most of my capstone time was spent doing research on the planned implementations of our components. Specifically, I looked into using a rotating LIDAR as suggested by Tamal, especially its feasibility with an embedded system. One project I found was this one, where someone had used the exact model of sensor we were looking at (RPLidar A1M8) with a Raspberry Pi 3. They even provided their source code, which I’m sure will be very useful to us moving…

Read More Read More