Researchers are developing advanced robots which will be helpful in various sectors like transportation, manufacturing, healthcare, among others. Open-sourced robotic platforms bring the whole community of robot enthusiasts together in one platform in order to gain successful outcomes in a certain project. It has truly changed the way of traditional research.
In this article, we list down seven platforms where anyone can build and test robotic applications.
1| Google ROBEL
Recently, researchers of Google Brain and UC Berkeley introduced ROBEL (Robotics Benchmarks for Learning with Low-Cost Robots) to the world. ROBEL is an open-source platform of cost-effective robots and curated benchmarks designed primarily to facilitate research and development on physical hardware in the real world. The robot includes in this platform are low-cost, modular, easy to maintain, and are robust enough to sustain on-hardware reinforcement learning from scratch. According to the researchers, the platform serves as a rapid experimentation platform, supporting a broad range of experimental needs along with the development of important algorithms like reinforcement learning.
2| Microsoft AirSim
Microsoft AirSim (Aerial Informatics and Robotics Simulation) is an open-source robotics simulation platform. This platform has the ability to capture data for models from wheeled robotics, aerial drones to static IoT devices. AirSim provides a realistic simulation tool for designers and developers for a seamless generation of the amount of training data and leverages various computations in order to create real-world simulations. The platform is also designed to integrate with existing machine learning frameworks to generate new algorithms for perception and control tasks.
3| Apollo Baidu
Apollo is an open-source autonomous vehicle technology platform by Beijing tech giant, Baidu. It provides an open, reliable and secure software platform for its partners to develop their own autonomous driving systems through on-vehicle and hardware platforms. Earlier this year, the tech giant launched Apollo Enterprise which includes solutions for highway autonomous driving, autonomous valet parking, fully autonomous mini-buses, DuerOS (Baidu’s voice assistant) for cars, and other such.
4| NVIDIA Isaac
In March this year, NVIDIA presented its Isaac Software Development Kit (SDK) which is a developer toolbox for accelerating the development and deployment of AI-powered robots. The toolkit includes the Isaac Robot Engine which enables high-performance robotics data processing and deep learning algorithms and hardware reference applications. It provides the developers with deep neural networks along with GPU accelerated algorithms, interfaces with robotic platforms such as cobots (collaborative robots), AMRs (autonomous mobile robots), and other services/industrial robots and much more.
5| AWS RoboMaker
AWS RoboMaker is an AWS cloud-based robotics integrated development environment where developers can develop, test and deploy robotics applications as well as build intelligent robotics functions using cloud services. It is a fully managed simulation service for quick and easy testing and a deployment service for the lifecycle management of intelligent robotic applications. The platform has connectivity to AWS services which includes machine learning, monitoring, and analytics services to enable a robot to stream data, navigate, communicate, comprehend, and learn.
6| ROSbot 2.0
ROSbot 2.0 is an autonomous robot platform with robust mechanics, powerful computers, advanced sensors like LiDAR, RGBD camera and expansion ports. It was introduced last year by Husarion, which is a development & management platform for robots, autonomous vehicles, drones, etc. The platform is based on CORE2-ROS with ASUS Tinker Board and consists of two control units.
7| Poppy Project
Poppy Project is an open-sourced platform for developing, deploying and sharing of interactive 3D printed robots. It is basically a community-centred robotic project which targets the needs of a multidisciplinary community such as researchers and other robotic enthusiasts who can share their work and ideas on the same platform. The tools in this platform are designed to be modular, easy to use, and easy to integrate.