No abstract

Traffic congestions in urban cities unwantedly form platoons of vehicles running at low speeds. For vehicles operated by human drivers, reaction to speeding up or down requires some time, thus, increasing travel time. In this study, we present an adaptive cruise control for a group of autonomous vehicles that follow each other. We propose a taillight tracking system by utilizing low-cost dashboard cameras for detecting the position of the lead vehicle and then allow autonomous vehicles to correctly accelerate or decelerate depending on the nature of traffic. This is achieved by detecting the leading vehicle's taillight via linear AND-ing of the the RGB and HSV color model representations. We evaluate the proposed system by employing real captured traffic images and tested by utilizing mobile robots for the platoon of vehicles testing.

No abstract

<span lang="EN-US">Traffic congestion is a constant problem for cities worldwide. The human driving inefficiency and poor urban planning and development contribute to traffic buildup and travel discomfort. An example of human inefficiency is the phantom traffic jam, which is caused by unnecessary braking, causing traffic to slow down, and eventually coming to a stop. In this study, a brake and acceleration feature (BAF) for the advanced driver assistance system (ADAS) is proposed to mitigate the effects of the phantom traffic phenomenon. In its initial stage, the BAF provides a heads-up display that gives information on how much braking and acceleration input is needed to maintain smooth driving conditions, i.e., without sudden acceleration or deceleration, while observing a safe distance from the vehicle in front. BAF employs a fuzzy logic controller that takes distance information from a light detection and ranging (LIDAR) sensor and the vehicle’s instantaneous speed from the engine control unit (ECU). It then calculates the corresponding percentage value of needed acceleration and braking in order to maintain travel objectives of smooth and safe-distance travel. Empirical results show that the system suggests acceleration and braking values slightly higher than the driver’s actual inputs and can achieve 90% accuracy overall.</span>

No abstract