MathWorks Sensor Fusion and Tracking Toolbox

MathWorks has introduced Sensor Fusion and Tracking Toolbox, which is now available as part of Release 2018b. The toolbox equips engineers working on autonomous systems in aerospace and defence, automotive, consumer electronics and other industries with algorithms and tools to maintain position, orientation and situational awareness.

Engineers working on the perception stage of autonomous system development need to fuse inputs from various sensors to estimate the position of objects around these systems. Now researchers, developers and enthusiasts can use algorithms for localisation and tracking, along with reference examples within the toolbox, as a starting point to implement components of airborne, ground-based, shipborne and underwater surveillance, navigation and autonomous systems.

The toolbox offers a flexible and re-usable environment, providing capabilities to simulate sensor detections, perform localisation, test sensor fusion architectures and evaluate tracking results. Engineers can explore multiple designs and perform ‘what-if analysis’ without writing custom libraries, and can also simulate fusion architectures in software that can be shared across teams and organisations.

The toolbox includes: multi-object trackers, sensor fusion filters, motion and sensor models, and data association algorithms that can be used to evaluate fusion architectures using real and synthetic data; scenario and trajectory generation tools; synthetic data generation for active and passive sensors, including RF, acoustic, EO/IR and GPS/IMU sensors; system accuracy and performance standard benchmarks, metrics and animated plots; and deployment options for simulation acceleration or desktop prototyping using C-code generation.