Robustly-Safe Automated Driving (ROAD) Systems


Automated driving is widely viewed as a promising technology to revolutionize today’s transportation systems, so as to free the human drivers, ease the road congestion and lower the fuel consumption among other benefits.

When the automated vehicles drive on public roads, safety is a big concern. While existing technologies can assure high-fidelity sensing, real-time computation and robust control, the challenges lie in the interactions between the automated vehicle and the environment which includes other manually driven vehicles. For road safety, the driving behavior for the automated vehicles should be carefully designed. In other words, given sensory information from multiple sensors (e.g. cameras and LIDAR), an automated vehicle should be intelligent enough to find a safe and efficient trajectory to its destination, which takes into account of the complex environment with multiple surrounding vehicles.

Conservative strategies such as “braking when collision is anticipated”, known as the Auto Brake function in existing models, are not the best actions in most cases (although they may be necessary in certain cases). Taking into account the dynamics and future course of surrounding vehicles, the automated vehicle has multiple choices for a safe maneuver, i.e. i) slow down to keep a safe headway till the headway reaches the safe limit; ii) steer to the left or right to avoid a collision; iii) even speed up if it can get out a dangerous zone by so doing, etc. The autonomy in driving needs high level machine intelligence.

We propose a framework in designing the driving behavior for automated vehicles to prevent or minimize occurrences of collisions among vehicles and obstacles while maintaining efficiency (e.g. maintaining high speed on freeway). The three-layer Robustly-Safe Automated Driving (ROAD) system is considered, as shown in the following figure.

The ROAD System Architecture

Demo Videos

Maintaining High Speed in Slow Traffic with Active Safety Measure


C. Liu, J. Chen, T. Nguyen, and M. Tomizuka, “The robustly-safe automated driving system for enhanced active safety”, in SAE World Congress, 2017.

C. Liu, and M. Tomizuka, “Enabling Safe Freeway Driving for Automated Vehicles”, in American Control Conference, 2016.


Changliu Liu Graduate Student Email Link Homepage
Jianyu Chen Graduate Student Email Link  
Chen Tang Graduate Student Email Link  
Long Xin Visiting Student Email Link