IPIN2020

The environment resembles an industrial setting: it includes metal shelves, industrial vehicles and other objects that influence the radio signal propagation in the environment. The stationary anchor nodes are placed around the area and the mobile node is attached to a wooden table to assure a constant height.

The trajectories of the transmitter nodes are in-between the various objects; the size of the area is approximately 15 m × 20 m. The objects in the environment include: metal shelves filled with goods (1) and (3); industrial vehicles (2) and (4); and a large metal box (5).

The anchor positions are the following:

The mobile node was configured as a transmitter and the stationary anchor nodes were configured as receivers. We moved the wooden table throughout the environment at constant speed. Hence, the environment and data resembles a robotic scenario.

In total, we captured about 300,000 channel impulse responses over a time period of approximately 1.5 hours. The sampling interval of the data was about 10 Hz. For clarity, a constant sampling interval is not available, as straightforward re-sampling of CIR data is not possible because of the complexity of the signals. Of these, a temporally coherent set of 230,000 CIRs is available for training purposes, while another coherent set of 70,000 datapoints is used for testing/evaluation. This corresponds to exactly 20 minutes of recording time.

The dataset is provided as an HDF5 file that contains the CIRs and reference positions in a dataset called ds with the following fields:

• rec_time (long): the timestamp in µs at which the CIR was received at the receiver node.
• burst_id (int): the transmitter time index. This can be used for synchronization. At each burst ID, the transmitter (i.e., the mobile node) transmits an impulse that is received by a subset of the receivers (i.e., anchors). The complete set of CIRs from all anchors is not available at all time steps, as at some receivers the detection was not successful due to an insufficient channel and/or data corruption.
• cir_real (int[366]) and cir_imag (int[366]): the real and imaginary parts of the CIR. The CIRs are centered around the peaks and contain 366 samples each.
• anch_id (signed char): the anchor ID of the receiving anchor.
• ref_x, ref_y (double): the positions of the agent (i.e. the mobile tag, the transmitter). The reference positions correspond to the receiver timestamp rec_time.

Download 

If you use our dataset for your research, please consider citing:

@misc{kram2020track7,
  author       = {Kram, Sebastian and Stahlke, Maximilian and Mutschler, Christopher},
  title        = {IPIN2020 Competition Track 7: Channel Impulse Responses},
  year         = {2020},
  howpublished = {\url{https://iis.fraunhofer.de/ipin2020}},
  note         = {Fraunhofer Institute for Integrated Circuits IIS}
}

This work is licensed under a CC BY-SA 4.0 license, see

https://creativecommons.org/licenses/by-sa/4.0/