MIT Team Develops Lane-Change Algorithm for Autonomous Vehicles


Most existing lane-change algorithms for autonomous cars have one of two drawbacks: Either they rely on detailed statistical models of the driving environment, which are difficult to assemble and too complex to analyze on the fly; or they’re so simple that they can lead to impractically conservative decisions, such as never changing lanes at all.

At the IEEE 2018 International Conference on Robotics and Automation (ICRA), researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) are presenting a new lane-change algorithm that splits the difference. It allows for more aggressive lane changes than the simple models do but relies only on immediate information about other vehicles’ directions and velocities to make decisions.

The optimization solution will ensure navigation with lane changes that can model an entire range of driving styles, from conservative to aggressive, with safety guarantees. Normal “buffer zone” computing is done in advance with the vehicle’s computer comparing situations to those pre-computed scenarios. With fast, dense traffic, however, that can mean the search and comparison is too slow or the scenario does not fit well enough, leading the vehicle to not change lanes at all. A human driver has no such computational shortcomings.

With the MIT researchers’ system, if the default buffer zones are leading to performance that’s far worse than a human driver’s, the system will compute new buffer zones on the fly—complete with proof of collision avoidance. That approach depends on a mathematically efficient method of describing buffer zones, so that the collision-avoidance proof can be executed quickly.

The MIT researchers began with a Gaussian distribution representing the current position of the car, factoring in both its length and the uncertainty of its location estimation. Then, based on estimates of the car’s direction and velocity, the researchers’ system constructs a logistic function. Multiplying the logistic function by the Gaussian distribution skews the distribution in the direction of the car’s movement, with higher speeds increasing the skew.

The skewed distribution defines the vehicle’s new buffer zone. But its mathematical description is so simple—using only a few equation variables—that the system can evaluate it on the fly.

The researchers tested their algorithm in a simulation including up to 16 autonomous cars driving in an environment with several hundred other vehicles.