Loading...
Robotic platform agnostic SLAM
Ledezma, Jesus
Ledezma, Jesus
Citations
Altmetric:
Advisor
Editor
Date
Date Issued
2025-04
Date Submitted
Keywords
Collections
Research Projects
Organizational Units
Journal Issue
Embargo Expires
Abstract
In recent years, Simultaneous Localization and Mapping (SLAM) algorithms are being increasingly implemented in autonomous vehicles to enable real-time environmental mapping and navigation. However, because of relatively recent widespread adoption of these algorithms, well documented and capable hardware platforms that can support SLAM research remain scarce. In order to address this gap, our research group set out with the objective of engineering and assembling a user-friendly and SLAM capable hardware platform, designed for deployment on the Spot, Jackal, and Husky robots. To achieve this goal, we designed a modular sensor “backpack”, including various data collection devices such as a LiDAR sensor, a high-resolution depth camera, a RTK GPS subsystem, and more, capable enough to run SLAM algorithms onboard, yet light enough to stay under the Spot’s 30 lbs carrying capacity. At the heart of our system is an NVIDIA RTX 4070 GPU and 2.2 GHz Intel Core i9 HX 24-core CPU equipped laptop, suitable for supplying the necessary computational resources for SLAM algorithms. To facilitate further research in this area, our system’s technical documentation will be made publicly available, allowing any SLAM enthusiast or research group to replicate and build upon the work that we’ve laid out.
Associated Publications
Rights
Copyright of the original work is retained by the author.