Goals

- The robot should autonomously navigate, avoid obstacles and interact with objects using a gripper.

- Aside from an initial mapping phase, not require teleoperation or manual user input.

- Be multi-purpose, performing a number of common tasks

License

BSD license on the code and design files unless otherwise specified (eg. apriltags nodelet is GPL)

Overall design

The core function of the robot is to move objects from one point to another. The object may be a target to be transported or a tool that performs some task (eg. a cleaning pad, dusting tool etc). The robot should contain the minimum hardware required to accomplish this.

Mechanical design

I'm using a single DoF arm and simple planar gripper. This has a few advantages over more complex arm/gripper setups:

- can be produced fairly cheaply using 3d printers

- no need for complex inverse kinematics

- reduces flex from joint backlash, higher load capacity, lower weight

The depth camera is mounted at the back to minimize its detection deadzone. As a result, the body of the robot is wedge-shaped so that when the arm is lowered the camera has an unobstructed view. The right side of the robot has a triangular tessellation pattern, this is to somewhat offset the increased weight on that side due to the arm.

Hardware

I've experimented with several iterations of hardware setups and settled on this:

- neato xv11 LIDAR for localization

- intel realsense R200 depth sensor. This provides a depth stream for object detection as well as a 1080p RGB stream to detect fiducials

- Nvidia Jetson TK1 as the main computer. This board has CUDA support, which makes it much easier to deal with computer vision

- Kobuki base robot platform. This is the same base used by the Turtlebot. The base provides gyro, odometry and other sensor output through its USB interface, which runs ROS right out of the box.

- Arduino uno to drive the arm/gripper. Although the TK1 technically has GPIO, linux is not a realtime OS and not really suited to driving motors with PWM.

- Actuonix/Fergelli P16 150mm 22:1 linear actuator to drive the arm

- Polulu VNH5019 motor driver to drive the linear actuator

- MXL AC-404 microphone. I got this one mainly because of the recommendation from the ROS website


Software

I used ROS for the software framework. Most of the really difficult problems for this project has already been solved by various ROS packages. Here are the stock ROS nodes that I used, along with the high-level task that it performs:

gmapping - build a map of the environment using SLAM

robot localization, AMCL - localize within the map via sensor fusion of LIDAR data, wheel odometry and gyro readings

ROS navigation - plan a path to a waypoint on the map

RTAB-map obstacle detection - detect obstacles and plan around them

pi_trees - behaviour tree implementation for high-level decision making

pocket sphinx - speech recognition

and many others.. check out the launch file on github for more.

There are some tasks for which no off-the-shelf package exists, or requires refactoring for speed improvements. In these cases I wrote my own ROS nodes:

gpu_robot_vision - uses the TK1's GPU to perform simple CV tasks, including: image rectification, BW/color conversion, scaling and noise reduction filter

apriltags_nodelet - a nodelet that outputs a list of fiducial markers from the rectified and denoised RGB stream

april_tf - takes those markers as input and outputs the same markers transformed in the map frame. Persist observations by writing them to a file, and outputs a target pose for ROS navigation to plan a path to the marker

april_planner - issue precise movements to the robot based on the relative movement of the detected markers

depth_object_detection - this is mainly used to detect my hand, to open/close the gripper

Installation

- get a spare machine and install ubuntu 14.04

- flash your TK1 and ensure wifi is working

- load custom kernel with UVC for the realsense

- install ROS and realsense drivers (install ROS indigo)

- install these ROS nodes (available via apt-get)

rosserial_python xv_11_laser_driver laser_filters kobuki yocs_velocity_smoother map_server rtabmap_ros amcl pocketsphinx gmapping navigation pi_trees

- setup your ROS environment and create a catkin workspace

- git clone https://github.com/Jack000/bunnybot into your catkin workspace, and catkin_build

- copy the contents of bunnybot/launch into your home directory

- copy bunnybot/launch/bunnybot.py into the package directory of pi_trees_lib


Operation

ssh -X ubuntu@tk1address
roslaunch robot.launch map:=true

the keyop node will run, allowing you to teleoperate the robot with arrow keys. On your spare machine, install ROS indigo and setup the appropriate environment variables so that the TK1 is identified as master. On the client, run

rosrun rviz rviz
to see the map being built, as well as other data from the robot. When mapping is complete, run
rosrun map_server map_saver
on the TK1 to save the map to a file. Any observed fiducials are saved to a file when you cancel out of the ROS process. The next time you run
roslaunch robot.launch
the map and saved fiducials will be used for autonomous operation

older test videos: