Manufacturing News from the Engineered Designer Perspective

Lane-Changing Algorithm Improves Driverless Vehicle Performance

Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) recently took to the International Conference on Robotics and Automation to present their new algorithm designed to assist driverless vehicles in changing lanes much like humans do.

While existing algorithms aid in controlling driving patterns, they are either too heavily reliant on statistical models of the driving environment or they are overly simple and do not allow for lane changes.

The new algorithm appears to split the difference, allowing for more aggressive lane changes than simpler models while relying only on immediate information regarding vehicle directions and velocities.

According to CSAIL postdoc and the paper’s first author, Alyssa Pierson, the team’s motivation stems from a desire to do the most with the least. “What can we do with as little information as possible?” she asks. “How can we have an autonomous vehicle behave as a human driver might behave? What is the minimum amount of information the car needs to elicit that human-like behavior?”

“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 CSAIL director and Viterbi Professor of Electrical Engineering and Computer Science Daniela Rus.

The standard method for avoiding collisions is to calculate buffer zones around other vehicles in the environment, planning lane changes, and staying out of the pre-determined buffer zones. Algorithm designers must prove that their method guarantees collision avoidance, which can prove difficult. To achieve this, optimal buffer zones are typically computed in advance, and the vehicle acts according to the model that corresponds to its current situation.

However, this becomes problematic when traffic slows and other anomalies cause irregular driving patterns (road construction, accidents, funeral processions, emergency vehicles, etc.). In these instances, precomputed buffer zones may be too restrictive or not restrictive enough, and the vehicle will thus fail to change lanes at all.

The new system developed by the MIT researchers changes that. In instances where precomputed buffer zones lead to poor performance, the system will compute new buffer zones and plan its course to avoid collisions. The method depends primarily on a mathematically efficient method of describing buffer zones so that proof of collision avoidance can be executed quickly.

The team began with a Gaussian, or bell-curve probability, distribution. This represents the current position of the car, factoring in its length and the uncertainty of its location estimation. Estimates of the car’s direction and velocity are used to construct a logistic function. Multiplying the logistic function by the Gaussian distribution skews the distribution in the direction of the car’s movement, and this skewed distribution defines the vehicle’s new buffer zone. The algorithm was tested in a simulation that included up to 16 autonomous vehicles 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,” said 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.”

Latest Stories

Crude Oil Prices Uncertain as OPEC Meets to Discuss Supply

Crude Oil Prices Uncertain as OPEC Meets to Discuss Supply

​Crude oil prices fell in several markets this week pending a June 22nd meeting of the Organization of Petroleum Exporting Countries in Vienna. Prior to the meeting, both OPEC and non-OPEC producers will come together to discuss production levels at seminars scheduled for June 20th and 21st. ​“Last week, we saw some news stories indicating…

Auto Industry Expected to Meet 2025 Standards

Auto Industry Expected to Meet 2025 Standards

​The Union of Concerned Scientists, which meets every few years to discuss the auto industry’s emission reduction progress, released this year’s analysis. The analysis, which was based on model year 2017 vehicles, shows that the industry has reached the lowest levels yet in both smog-forming and global warming emissions from new vehicles. However, that progression…

Unemployment Rate Remains Steady at 5.8 Per Cent

Unemployment Rate Remains Steady at 5.8 Per Cent

According to Statistics Canada, approximately 7,500 jobs were lost in May, with full-time employment only partially offset by an increase in part-time jobs. While part-time employment rose by 23,600 positions, full-time employment fell drastically at an estimated 31,000. This makes the fourth consecutive month that the unemployment rate has remained steady at 5.8 per cent,…

Diesel Outlook Not So Grim, Says GM Executive

Diesel Outlook Not So Grim, Says GM Executive

​General Motors Powertrain Executive Pierpaolo Antonioli remains optimistic about the future of diesel, despite dwindling sales. A key factor in Antonioli’s positive outlook is recent evidence suggesting that nitrogen oxide emissions can be reduced to the bear minimum.According to Robert Bosch, a leading supplier of diesel injection systems, the company has developed a method for…

Audi Recall Announced Due to Emissions

Audi Recall Announced Due to Emissions

​The KBA vehicle licensing authority ordered a recall of approximately 60,000 Volkswagen Audis this week, 33,000 of which are in Germany, due to illegal software designed to conceal emissions. In May, Audi announced that it stopped delivering some A6 and A7 versions after discovering irregularities in their onboard software, as the KBA launched an investigation…

Scientists Use Machine Learning to Automate Atomic-Scale Manufacturing

Scientists Use Machine Learning to Automate Atomic-Scale Manufacturing

​Scientists at the University of Alberta recently unveiled a method wherein they applied a machine learning technique to automate atomic-scale manufacturing for the first time. The green technology used in this process also reduces the impact on the climate while simultaneously meeting the demands of the information age. ​According to Robert Wolkow, Professor of Physics…

Researchers Discover Surprising Role for Water in Energy Storage

Researchers Discover Surprising Role for Water in Energy Storage

​Researchers from North Carolina State University, the Oak Ridge National Laboratory, and Texas A&M University made a surprising discovery while studying crystalline tungsten oxide dihydrate, a material that is comprised of layers separated by atomically thin layers of water. According to the researchers, the material has great potential for energy storage technologies. They also discovered…

Lane-Changing Algorithm Improves Driverless Vehicle Performance

Lane-Changing Algorithm Improves Driverless Vehicle Performance

​Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) recently took to the International Conference on Robotics and Automation to present their new algorithm designed to assist driverless vehicles in changing lanes much like humans do. While existing algorithms aid in controlling driving patterns, they are either too heavily reliant on statistical models of…

Global Warming Cap Could Save Economy Trillions

Global Warming Cap Could Save Economy Trillions

​Researchers studying the effects of global warming recently reported that four-fifths of countries and approximately 90 per cent of the global population could benefit from adherence to the Paris Climate Treaty, which calls for holding the rise in Earth’s surface temperature to well under 2 degrees Celsius and 1.5 degrees Celsius if possible. As reported…

Engineers Design Self-Eating Rocket Engine for Launching Satellites into Orbit

Engineers Design Self-Eating Rocket Engine for Launching Satellites into Orbit

​Engineers from the University of Glasgow and Oles Honchar Dnipro National University in Ukraine recently built an autophage engine designed for launching satellites into space. Unlike standard models, this “self-eating” rocket engine could make the process of sending satellites into orbit easier and more affordably than ever before. ​Rockets typically use tanks, often much heavier…

1 2 3 84Next →

Other Popular News and Stories

  • Japex to buy into west coast LNG development
  • SPPCA's new landing gear facility opening in Mississauga
  • GM investing $250 million at Ingersoll plant
  • RV industry has growing role in Canada's economy: study
  • FTG Aerospace to supply avionics to Rockwell Collins
  • Bombardier nearly ready to flight test CSeries
  • Miners struggling with higher costs, lower prices
  • Bombardier holds update on CSeries aircraft
  • Manufacturing the sole industry showing job losses in February
  • Canadian business, except energy, had profitable Q4: Statistics Canada
  • Canadian oil production up; producers turning to railways for shipment
  • Clean energy expected to surge as pv costs drop
  • Volkswagen to produce super-efficient hybrid
  • Canada keeping up pressure on US for Keystone XL approval
  • Pratt & Whitney Canada announces helicopter engine contracts
  • Skilled labour shortage in world oil industry: report
  • Economy managed slight growth in Q4, but shrank in December
  • BC refinery close to financing deal
  • Russian leasing company orders 42 CSeries jets from Bombardier
  • DART Aerospace re-branding itself to reach wider markets