Interactive simulation platform using processing-based visualization for safe collision-free autonomous driving development

Autonomous driving for maximum throughput of traffic is too complex to cover various cases of exceptions in relation to large-scale cars in city, while still guaranteeing safety of the self-organizing algorithm. In this paper, we present a simulation-integrated interactive visualization platform to enable the fast development of a safe self-organizing driving algorithm. Using the proposed platform, developers describe geographic roads and allocate active cars equipped with specific autonomous algorithms. The cross-coupled simulation result of the self-organized movement of cars is interactively visualized with traffic on roads to show the weakness of the embedded autonomous driving algorithm. We show a demonstration for 1000 cars on 300 junctions of roads and offer a way to accelerate the development of self-organizing control in autonomous cars.

[1]  Aaas News,et al.  Book Reviews , 1893, Buffalo Medical and Surgical Journal.

[2]  Farnoush Banaei-Kashani,et al.  GeoDec: A framework to visualize and query geospatial data for decision-making , 2010, IEEE MultiMedia.

[3]  Qian Wang,et al.  Predictive Guidance and Control Framework for (Semi-)Autonomous Vehicles in Public Traffic , 2017, IEEE Transactions on Control Systems Technology.

[4]  Kyoung-Dae Kim Collision free autonomous ground traffic: A model predictive control approach , 2013, 2013 ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS).

[5]  Mihaela van der Schaar,et al.  Context-Aware Online Spatiotemporal Traffic Prediction , 2014, 2014 IEEE International Conference on Data Mining Workshop.