Traffic jam elimination algorithm for car internet

    Automakers are in full swing testing peer-to-peer WiFi communication systems between vehicles , on which V2V (vehicle-to-vehicle) communication networks will be built. Such networks can dramatically improve the situation on the roads if cars start to transmit information to each other about traffic congestion, traffic jams, traffic signals, etc. At intersections, cars can check their paths by exchanging data in real time. Creating a V2V network is crucial for the normal operation of autopilots, which in the future will replace live drivers and must be coordinated with other cars.

    Technically, the V2V network can be raised now, but the main problem is software. What are the optimal algorithms and the optimal speed of vehicles in the stream? How should robotic cars coordinate their movement if there are a majority of them on the road? Scientists from Seoul University, who published the scientific paper Dissolution of traffic jam via additional local interactions ( PDF ) , are working on one aspect of this problem . They created an algorithm for V2V, which guarantees a very fast elimination of traffic jams due to the exchange of information and instant change of the speed mode of all cars before and after the traffic jam.

    In recent years, many mathematical models have been developed and a lot of experimental data have been collected on the results of measuring traffic patterns. Scientists have come to a consensus that there are three main patterns:
    • free flow, in which the density of vehicles is low enough and each of them can go at the highest possible speed;
    • synchronized flow, in which a high density of vehicles forces drivers to slow down somewhat;
    • traffic jam - the speed drops to zero and the movement occurs by the method of short-term jerks.
    The models of transition from one pattern to another are extremely complex, but some of them, using cellular automata, give useful results in practice. In particular, how does the transition from the third to the second pattern occur, that is, the “resorption” of the cork. Most scientists believe that the best strategy in this case is to increase the speed of vehicles that leave the traffic jam - so that their speed is higher than those of cars that are approaching the traffic jam.

    Hyun Keun Lee and Beom Jun Kim from Seoul University have proposed a simple algorithm to automate this transition. Using cellular automata, they compiled a model of traffic flow and introduced into it a factor for the exchange of information about the current speed between cars. Scientists also took into account the "optimistic" and "protective" strategy of driving a car. In the first case, the driver maintains a distance from the vehicle in front that is shorter than safety standards require, and with a “protective” strategy, on the contrary, the distance is too large.

    Modeling of the situation showed that if, when approaching the traffic jam, all drivers switch to a protective strategy, then the flow rate decreases. At the same time, those cars that leave the traffic jam should do it quickly using an optimistic strategy. Thus, the basic condition for the resolution of the cork is met - and it disappears quite quickly.

    This is an interesting and simple algorithm for eliminating traffic jams using a V2V network. True, for the algorithm to work most efficiently, it is desirable that the cars are controlled in automatic mode and can instantly switch to the required driving mode and change their speed in accordance with the command. Living drivers cannot react so quickly and clearly to incoming information.

    However, one can imagine that partial autopilot and V2V radio communications will appear in the next generation of cars. It is also necessary that these algorithms be adopted as a single standard and be supported by autopilot systems from all manufacturers.

    On the other hand, for efficient resorption of traffic jams, it is not necessary that 100% of the cars act in accordance with the described algorithm, a sufficiently smaller number of them. What proportion of “intelligent” machines is required in the stream remains to be calculated.

    It is hoped that with the automation of traffic in the future, traffic jams will completely disappear from our roads, and driving will bring only pleasure.

    via Technology Review

    Also popular now: