Summary of Arrival Time Prediction For Autonomous Shuttle Services in the Real World: Evidence From Five Cities, by Carolin Schmidt et al.
Arrival Time Prediction for Autonomous Shuttle Services in the Real World: Evidence from Five Cities
by Carolin Schmidt, Mathias Tygesen, Filipe Rodrigues
First submitted to arxiv on: 10 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a reliable arrival time (AT) prediction system for autonomous shuttles, which is crucial for customer trust. The model combines separate predictions for dwell and running times using real-world data from five cities. The authors explore the benefits of integrating spatial data using graph neural networks (GNNs), proposing a hierarchical model that handles the case of a shuttle bypassing a stop. They also identify key characteristics of pilot sites that influence model selection. The results show promising low errors, with dwell time prediction being the most important factor in overall AT accuracy, particularly in low-traffic areas or under regulatory speed limits. This research provides insights into current autonomous public transport prediction models and informs data-driven decision-making as the field advances. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Autonomous shuttles are changing how we travel around cities. To make them reliable, scientists need to predict when they will arrive at each stop. This paper shows a new way to do this by combining two predictions: how long it takes for the shuttle to stop and start moving again (dwell time), and how long it takes to drive between stops (running time). The authors tested their method using real data from five cities and found that it works well, even when predicting multiple stops ahead. They also discovered that the way each city is designed affects which prediction method works best. |
