MIT technology 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 research and testing for making driverless cars road-ready is still an ongoing process. Multiple carmakers and technology startup including Tesla, GM, Google and Apple are involved in developing futuristic cars. In the development process, algorithms for controlling lane changes are an important topic of study.
Changing lanes whenever necessary is one of the most difficult tasks for autonomous cars. Most existing lane-change algorithms employed by such cars today 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 analyse on the fly; or they’re so simple that they can lead to impractically conservative decisions, such as never changing lanes at all.
The MIT researchers have developed a new algorithm which 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,” says Daniela Rus, the director at Computer Science and Artificial Intelligence Laboratory (CSAIL).
related news
If traffic is fast enough and dense enough, the standard way of calculating the buffer zone to avoid collisions may be too restrictive for autonomous cars. In such scenario, an autonomous vehicle will fail to change lanes at all, whereas a human driver would cheerfully zip around the roadway.
MIT’s algorithm uses a simplistic model 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.
“The autonomous vehicles were not in direct communication but ran the proposed algorithm in parallel without conflict or collisions,” explains Pierson.
“Each car used a different risk threshold that produced a different driving style, allowing us to create conservative and aggressive drivers. Using the static, precomputed buffer zones would only allow for conservative driving, whereas our dynamic algorithm allows for a broader range of driving styles.”