Data Flow ORB-SLAM for Real-time Performance on Embedded GPU Boards

The use of embedded boards on robots, including unmanned aerial and ground vehicles, is increasing thanks to the availability of GPU equipped low-cost embedded boards in the market. Porting algorithms originally designed for desktop CPUs on those boards is not straightforward due to hardware limitations. In this paper, we present how we modified and customized the open source SLAM algorithm ORB-SLAM2 to run in real-time on the NVIDIA Jetson TX2. We adopted a data flow paradigm to process the images, obtaining an efficient CPU/GPU load distribution that results in a processing speed of about 30 frames per second. Quantitative experimental results on four different sequences of the KITTI datasets demonstrate the effectiveness of the proposed approach. The source code of our data flow ORB-SLAM2 algorithm is publicly available on GitHub.

Authors

• Stefano Aldegheri
• Nicola Bombieri
• Domenico Daniele Bloisi
• Alessandro Farinelli

Keywords

• Visualization
• Simultaneous localization and mapping
• Codes
• Navigation
• Source coding
• Graphics processing units
• Real-time systems
• Mobile robots
• Software development management
• Pipeline processing
• Flow Data
• Open-source
• Unmanned Aerial Vehicles
• Load Distribution
• KITTI Dataset
• Quantitative Experimental Results
• Synchronization
• Running
• Mean Square Error
• Data Structure
• Quality Of Outcomes
• Parallelization
• Multi-core
• Computational Load
• Monocular
• Mobile Robot
• Directed Acyclic Graph
• Original Implementation
• Desktop PC
• Frames Per Second
• Pipelining
• Level Of Parallelism
• Graph Processing
• GPU Computation
• Parallel Execution
• Feature Extraction Block
• Loop Closure