Despite current innovations in the field of robotics, most robots are either expensive or have very limited functionality. However, a significant part of the world population own smartphones, which are equipped with powerful CPUs, cameras, GPS, Wi-Fi and other technologies. A recent study suggests using a smartphone for computation and sensing of a robot.
OpenBot: system overview. Image credit: Matthias Müller, Vladlen Koltun, arXiv:2008.10631
The authors of the study propose an electric vehicle which is able to perform simple tasks such as person following or real-time autonomous navigation. The robot can navigate along a new route and recognise new obstacle configurations not included in the training. It can also recognise dynamic obstacles and withstand motion blur due to vibrations. The equipment relies on readily available electronics (like Arduino Nano board) and 3D printing for its chassis. A single body for the robot costs $50 and the price can be reduced in the case of mass production.
Current robots are either expensive or make significant compromises on sensory richness, computational power, and communication capabilities. We propose to leverage smartphones to equip robots with extensive sensor suites, powerful computational abilities, state-of-the-art communication channels, and access to a thriving software ecosystem. We design a small electric vehicle that costs $50 and serves as a robot body for standard Android smartphones. We develop a software stack that allows smartphones to use this body for mobile operation and demonstrate that the system is sufficiently powerful to support advanced robotics workloads such as person following and real-time autonomous navigation in unstructured environments. Controlled experiments demonstrate that the presented approach is robust across different smartphones and robot bodies. A video of our work is available at this https URL