The Implementation of Remote Monitoring for Autonomous Driving

Although autonomous driving offers the possibility of significant benefits to social welfare, fully automated vehicles might not be going to happen in the near further. Currently, the self-driving vehicle, (e.g., shuttle bus) has to be monitored from a remote control center and the large amounts of data, including images, radar and LIDAR (light detection and ranging) data, etc., have to be transmitted from the vehicle to the remote center. Therefore, this paper proposes a compression method for LIDAR data. Firstly, the time-series LIDAR data are rearranged into azimuth-altitude two-dimensional signal spaces. Secondly, the two-dimensional data are transferred into frequency domain by using the discrete cosine transform (DCT). Thirdly, the time-series DCT data are sampled based on differential sampling. Finally, the whole set of data are encoded using Lempel-Ziv-Markov chain-algorithm (LZMA). Meanwhile, this paper also presents the remote control of autonomous vehicles. The videos are streamed from the vehicle while the control commands are issued through a gamepad. Field trials show that the amount of LIDAR data can be reduced dozens of times, while the remote control is feasible at a vehicle speed of 20kph.