ROSYOct 11, 2019

Autonomous Shuttles for Last-Mile Connectivity

arXiv:1910.04971v1
Originality Synthesis-oriented
AI Analysis

This work addresses last-mile connectivity for urban transportation, but it is incremental as it presents an initial implementation for future improvement.

The paper tackled the problem of autonomous last-mile transportation in crowded, unstructured environments by developing a functional shuttle with components for navigation, obstacle avoidance, and pedestrian communication, though no concrete performance numbers were provided.

This paper describes an autonomous shuttle which targets providing last-mile transportation. Often, this involves operation in crowded areas with high levels of pedestrian traffic, and little to no lane markings or traffic control. We aim to create a functional shuttle to be improved upon in the future as new robust solutions are developed to replace the current components. An initial implementation of such a shuttle presented, detailing the overall architecture, controller structure, waypoint following, obstacle detection and avoidance, LiDAR based sign detection, and pedestrian communication. The performance of each component is evaluated, and future improvements are discussed.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes