Frédéric Labrosse

Single-track roads are narrow bi-directional roads often found in UK rural areas. They are vital to local communities but pose various challenges to drivers and the simulation of traffic. One key aspect of navigating single-track roads is managing dedicated passing places, short widenings of the road that allow drivers to pass each other. State-of-the-art traffic simulators lack the full functionality to model and resolve passing place scenarios on single-track roads, thus limiting their effectiveness in simulating these environments. This paper contributes to this gap through determining whether the guidance provided in the UK Highway Code is capable of resolving the passing place problem. Using AgentSpeak and a BDI framework, autonomous agents were programmed with the behaviours governed by the Highway Code and evaluated in a number of simulated scenarios. Results show that the Highway Code can improve performance over the state-of-the-art, but struggles to resolve more complex real-world passing place scenarios.

As chairs of the UKRAS 2022 conference, we are happy to welcome you in person after a break from in-person events. The theme of this year’s conference is “Robotics for Unconstrained Environments”, reflecting much of the robotics research that happens at Aberystwyth University. Unconstrained environments include any indoor and outdoor environment that has not been modified specifically for the robot to perform its task. The premise is that the environment must be representative of the task rather than being artificially simplified.

Autonomous following of ill‐defined roads is an important part of visual navigation systems. This paper presents an adaptive method that uses a statistical model of the color of the road surface within a trapezoidal shape that approximately corresponds to the projection of the road on the image plane. The method does not perform an explicit segmentation of the images but instead expands the shape sideways until the match between shape and road worsens, simultaneously computing the color statistics. Results show that the method is capable of reactively following roads, at driving speeds typical of the robots used, in a variety of situations while coping with variable conditions of the road such as surface type, puddles, and shadows. We extensively evaluate the proposed method using a large number of datasets with ground truth (available fromhttp://www.aber.ac.uk/en/cs/research/ir/dss/). We moreover evaluate many color spaces in the context of road following, and we find that the color spaces that separate luminance from color information perform best, especially if the luminance information is discarded.