Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

NanoSLAM: Enabling Fully Onboard SLAM for Tiny Robots

Vlad Niculescu, Tommaso Polonelli, Michele Magno, Luca Benini

TL;DR

NanoSLAM addresses the challenge of performing accurate SLAM onboard resource-constrained nano-UAVs by integrating a lightweight 2D SLAM pipeline that uses multiple low-power ToF sensors and a parallel GAP9 processor. It stacks small-frame depth measurements into scans, employs ICP-based scan-matching, and executes graph-based SLAM entirely on-device, achieving about 4.5 cm mapping accuracy with end-to-end latency under 250 ms while consuming only 87.9 mW. The approach is validated on a 44 g nano-drone equipped with four VL53L5CX sensors, demonstrating centimeter-level indoor mapping without offloading to external infrastructure. This work enables fully autonomous navigation and robust mapping for nano-UAVs, reducing latency, preserving privacy, and extending flight time by eliminating communication bottlenecks and dependencies on basestations.

Abstract

Perceiving and mapping the surroundings are essential for enabling autonomous navigation in any robotic platform. The algorithm class that enables accurate mapping while correcting the odometry errors present in most robotics systems is Simultaneous Localization and Mapping (SLAM). Today, fully onboard mapping is only achievable on robotic platforms that can host high-wattage processors, mainly due to the significant computational load and memory demands required for executing SLAM algorithms. For this reason, pocket-size hardware-constrained robots offload the execution of SLAM to external infrastructures. To address the challenge of enabling SLAM algorithms on resource-constrained processors, this paper proposes NanoSLAM, a lightweight and optimized end-to-end SLAM approach specifically designed to operate on centimeter-size robots at a power budget of only 87.9 mW. We demonstrate the mapping capabilities in real-world scenarios and deploy NanoSLAM on a nano-drone weighing 44 g and equipped with a novel commercial RISC-V low-power parallel processor called GAP9. The algorithm is designed to leverage the parallel capabilities of the RISC-V processing cores and enables mapping of a general environment with an accuracy of 4.5 cm and an end-to-end execution time of less than 250 ms.

NanoSLAM: Enabling Fully Onboard SLAM for Tiny Robots

TL;DR

NanoSLAM addresses the challenge of performing accurate SLAM onboard resource-constrained nano-UAVs by integrating a lightweight 2D SLAM pipeline that uses multiple low-power ToF sensors and a parallel GAP9 processor. It stacks small-frame depth measurements into scans, employs ICP-based scan-matching, and executes graph-based SLAM entirely on-device, achieving about 4.5 cm mapping accuracy with end-to-end latency under 250 ms while consuming only 87.9 mW. The approach is validated on a 44 g nano-drone equipped with four VL53L5CX sensors, demonstrating centimeter-level indoor mapping without offloading to external infrastructure. This work enables fully autonomous navigation and robust mapping for nano-UAVs, reducing latency, preserving privacy, and extending flight time by eliminating communication bottlenecks and dependencies on basestations.

Abstract

Perceiving and mapping the surroundings are essential for enabling autonomous navigation in any robotic platform. The algorithm class that enables accurate mapping while correcting the odometry errors present in most robotics systems is Simultaneous Localization and Mapping (SLAM). Today, fully onboard mapping is only achievable on robotic platforms that can host high-wattage processors, mainly due to the significant computational load and memory demands required for executing SLAM algorithms. For this reason, pocket-size hardware-constrained robots offload the execution of SLAM to external infrastructures. To address the challenge of enabling SLAM algorithms on resource-constrained processors, this paper proposes NanoSLAM, a lightweight and optimized end-to-end SLAM approach specifically designed to operate on centimeter-size robots at a power budget of only 87.9 mW. We demonstrate the mapping capabilities in real-world scenarios and deploy NanoSLAM on a nano-drone weighing 44 g and equipped with a novel commercial RISC-V low-power parallel processor called GAP9. The algorithm is designed to leverage the parallel capabilities of the RISC-V processing cores and enables mapping of a general environment with an accuracy of 4.5 cm and an end-to-end execution time of less than 250 ms.
Paper Structure (5 sections, 2 equations, 1 figure, 1 table)

This paper contains 5 sections, 2 equations, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Algorithms
  4. Scan Frames and Scans
  5. Scan-matching

Figures (1)

  • Figure 1: Illustration of the four ToF sensors onboard the drone and the coordinate frames of the world, drone, and sensors.