Rheology and Wetting Characterizations of Flux and Solder Paste
BGA Reballing and Influence on Ball Shear Strength
Micro Trace Resistive Technology
Durable Conductive Inks for Robust Printed Electronics
System in Package (SiP) and CSPs Underfilling on Reliability
Nanomaterials Performance Advantages
Cleaning Industrial Parts with Plasma
Thermal Mechanical Fatigue of a 56 I/O Quad-Flat No Lead Package
Latest Industry News
Building A High-performance Data and AI Organization
Mercedes rolls out luxury electric car in duel with Tesla
Tight foundry capacity, component shortages to affect smartphone sales in 2021
U.S. House committee approves blueprint for Big Tech crackdown
How to Prevent Batteries From Exploding? Nanoparticles, Says Startup
What is emotional innovation and how to apply it in your company
China LFP battery makers not hiking prices despite rising material cost
Max Interval Between Reflow for OSP Boards

Autonomous Vehicle Software Analyzes and Predicts Driving Events

Autonomous Vehicle Software Analyzes and Predicts Driving Events
Researchers at the Technical University of Munich have now developed a software module that continuously analyzes and predicts events while driving.
Technology Briefing


The ultimate goal when developing software for Level Five autonomous automobiles is to ensure that they will not cause accidents. New software developed at the Technical University of Munich prevents accidents by predicting different variants of a traffic situation every millisecond.

A car approaches an intersection. Another vehicle pulls out of the cross street, but it is not yet clear whether it will turn right or left. At the same time, a pedestrian step into the lane directly in front of the car, and there is a cyclist on the other side of the street. In these situations, humans with road traffic experience can generally assess the movements of other traffic participants correctly.

However, these kinds of situations present an enormous challenge for autonomous vehicles controlled by computer programs. According to the journal Nature Machine Intelligence, researchers at the Technical University of Munich have now developed a software module that continuously analyzes and predicts events while driving. To do so, vehicle sensor data are recorded and evaluated every millisecond. The software can calculate all possible movements for every traffic participant — provided they adhere to the road traffic regulations; this allows the system to look three to six seconds into the future.

Based on these future scenarios, the system determines a variety of movement options for the vehicle. At the same time, the program calculates potential emergency maneuvers in which the vehicle can be moved out of harm’s way by accelerating or braking without endangering others. The autonomous vehicle may only follow routes that are free of foreseeable collisions and for which an emergency maneuver option has been identified.

This kind of detailed traffic situation forecasting was previously considered too time-consuming and thus impractical. But now, the Munich research team has shown not only the theoretical viability of real-time data analysis with simultaneous simulation of future traffic events; they have also demonstrated that it delivers reliable results.

The quick calculations are made possible by simplified dynamic models. So-called reachability analysis is used to calculate potential future positions a car or a pedestrian might assume. When all characteristics of the road users are taken into account, the calculations become prohibitively time-consuming. That is why the team works with simplified models. These are superior to the real ones in terms of their range of motion — yet, mathematically easier to handle. This enhanced freedom of movement allows the models to depict a larger number of possible positions but includes the subset of positions expected for actual road users.

For their test, the computer scientists created a virtual model based on real data they had collected during test drives with an autonomous vehicle in Munich. This allowed them to craft a test environment that closely reflects everyday traffic scenarios. Using the simulations, they were able to establish that the safety module does not lead to any loss of performance in terms of driving behavior, the predictive calculations are correct, accidents are prevented, and in emergency situations, the vehicle is demonstrably brought to a safe stop.

The computer scientists emphasize that the new software could simplify the development of autonomous vehicles because it can be combined with all of today’s standard motion control programs.


No comments have been submitted to date.

Submit A Comment

Comments are reviewed prior to posting. You must include your full name to have your comments posted. We will not post your email address.

Your Name

Your Company
Your E-mail

Your Country
Your Comments

Board Talk
Max Interval Between Reflow for OSP Boards
Shelf Life Before Conformal Coating
We Bake, But Still Have Delamination, Why?
Cleaning Reballed BGA Components
Solder Paste Volume for BGA Rework
Reflow For Rigid Flex
Delay Before Cleaning Partial Assemblies
Problems With Starved "J" Lead Joints
Ask the Experts
Conformal Coating in Nitrogen Environment
Reflow Profile for Mixed Lead-Free and Leaded
Reliability Concerns When Converting to Lead-free
How Many Fiducials Per Solder Paste Stencil?
Viscosity of Solder Paste Before Printing
Bottom Terminated Components and Vias
Is Solder Mask Considered an Insulator
Reduce Glare During Assembly