NanoSLAM is a novel, lightweight and optimized end-to-end Simultaneous Localization and Mapping (SLAM) approach designed specifically for centimeter-size robots. It operates on a power budget of only 87.9mW and is deployable on a nano-drone weighing 44g equipped with a novel commercial RISC-V low-power parallel processor called GAP9. The algorithm leverages the parallel capabilities of the RISC-V processing cores and enables mapping of a general environment with an accuracy of 4.5cm and an end-to-end execution time of less than 250ms. This advancement could revolutionize the field of autonomous pocket-size robotic systems and Unmanned Aerial Vehicles (UAVs), creating new possibilities for IoT applications.
Publication date: 21 Sep 2023
Project Page: https://youtu.be/XUSVLHJ87J0
Paper: https://arxiv.org/pdf/2309.12008
