SLAC.js Indoor localisation using Javascript
Simultaneously Localisation and Configuration (SLAC) of indoor Wireless Sensor Networks and their users built upon FastSLAM.
With SLAC we aim to simultaneously locate both the user and the devices of a system deployed in an indoor environment. The algorithm is privacy-aware and is an online localisation method; i.e. localisation starts whenever a user starts moving inside a building. Moreover, for the SLAC system we focus on a solution that can be deployed in smart spaces without additional hardware requirements besides users’ mobile phones and the components of the space. By utilising a mobile phone we remove the need for a application-dependent device that the user needs to keep.
Contents
See for more information SLACjs on Github.
W. Bulten, A. C. V. Rossum and W. F. G. Haselager, “Human SLAM, Indoor Localisation of Devices and Users,” 2016 IEEE First International Conference on Internet-of-Things Design and Implementation (IoTDI), Berlin, 2016, pp. 211-222. doi: 10.1109/IoTDI.2015.19 Online publicationPresentation
The presentation below describes the general idea of SLACjs and why we built it. It also shows the mathetical background and explains how particle filters and extended Kalman filters are used for the localisation.
Live demonstration
The demo is unavailable after an website update. For information please contact me.
Other demos
Some other demos are also available online showing specific parts of the algorithm. A few of the demo's run an older version of the SLAC algorithm.
- Movie of SLACjs and moving devices (on YouTube). The movie shows what happens when two devices are swapped and how the algorithm manages to find the new locations.
- EKF initalisation (demo disabled). Demo showing the dedicated particle filter that is used to initialize a new device. It finds a rough estimate of the device's position using a particle filter. This version does not yet contain the improved resampling function that is used in the newest version of SLACjs.
- Older version of the algorithm on random data (demo disabled). The world and movement is fully random.
- Replay version of a live tests (demo disabled). Data has been recorded inside a real building with 7 bluetooth beacons used as landmarks. The demo version runs a slightly older version and does not show the maximum attainable localisation performance.