Autonomous lane changing is a critical feature for advanced autonomous driving systems, that involves several challenges such as uncertainty in other driver's behaviors and the trade-off between safety and agility. In this work, we develop a novel simulation environment that emulates these challenges and train a deep reinforcement learning agent that yields consistent performance in a variety of dynamic and uncertain traffic scenarios. Results show that the proposed data-driven approach performs significantly better in noisy environments compared to methods that rely solely on heuristics. * These authors contributed equally to this work 1 A. Alizadeh is with

MSRox is a wheeled mobile robot with two actuated degrees of freedom which enables it to have smooth motion on flat surfaces. It has the capability of climbing stairs and traversing obstacles, and adaptability toward uphill, downhill and slope surfaces. MSRox with 82 cm in length, 54 cm in width and 29 cm in height has been designed to climb stairs of 10 cm in height and 15 cm in width; nevertheless, it has the capability of climbing stairs up to about 17 cm in height and unlimited widt.In this paper, the motion systems and the capabilities of MSRox are described. Furthermore, experimental results of stair climbing and a comparison of the results with others are presented.

No abstract

No abstract

No abstract