QCar
This autonomous vehicle is developed by Quanser company, and the Self-Driving Car Research Studio platform makes it ideal for academic research. Having open-architecture, QCar is an ideal vehicle for validating dataset generation, mapping, navigation, machine learning, artificial intelligence, and other advanced self-driving concepts. It has NVIDIA® Jetson™ TX2 supercomputer, and equipped with a wide range of sensors, Lidar, cameras, encoders, and user-expandable IO. We have several QCars in our lab, making possible to perform some projects based on vehicular communication and collaborative robotics.
Tutlebot 3
TurtleBot3 is the low-cost, personal robot kits with open-source software. It is a small, affordable, programmable, ROS-based mobile robot for use in education, research, hobby, and product prototyping. The Turtlebot can run SLAM (simultaneous localization and mapping) algorithms to build a map and can drive around your room. Two versions of Turtlebot3 are available in our lab (Waffle and Burger). In these robots, the single board computer is Raspberry Pi 3. They are equipped with 2D Lidar, gyroscope, accelerometer, and magnetometer. Waffle also has Raspberry Pi camera for perception.
AWS DeepRacer
It is an autonomous 1/18th scale race car designed to test reinforcement learning (RL) models to control the car in a simulated environment or a physical track. Two forward facing cameras make up the stereo cameras to capture depth information and avoid objects being approached on the track. The LiDAR sensor is backward facing and detects objects behind and beside the car. Apart from these sensors, DeepRacer has integrated accelerometer and gyroscope sensors. It has an Intel Atom™ Processor with 4GB RAM.