A survey on data-driven scenario generation for automated vehicle testing
Automated driving is a promising tool for reducing traffic accidents. While some companies
claim that many cutting-edge automated driving functions have been developed, how to …
claim that many cutting-edge automated driving functions have been developed, how to …
Transformers in reinforcement learning: a survey
P Agarwal, AA Rahman, PL St-Charles… - arXiv preprint arXiv …, 2023 - arxiv.org
Transformers have significantly impacted domains like natural language processing,
computer vision, and robotics, where they improve performance compared to other neural …
computer vision, and robotics, where they improve performance compared to other neural …
Conditional predictive behavior planning with inverse reinforcement learning for human-like autonomous driving
Making safe and human-like decisions is an essential capability of autonomous driving
systems, and learning-based behavior planning presents a promising pathway toward …
systems, and learning-based behavior planning presents a promising pathway toward …
Towards knowledge-driven autonomous driving
This paper explores the emerging knowledge-driven autonomous driving technologies. Our
investigation highlights the limitations of current autonomous driving systems, in particular …
investigation highlights the limitations of current autonomous driving systems, in particular …
Identification of high-risk roadway segments for wrong-way driving crash using rare event modeling and data augmentation techniques
Abstract Wrong-Way Driving (WWD) crashes are relatively rare but more likely to produce
fatalities and severe injuries than other crashes. WWD crash segment prediction task is …
fatalities and severe injuries than other crashes. WWD crash segment prediction task is …
[HTML][HTML] Towards robust car-following based on deep reinforcement learning
One of the biggest challenges in the development of learning-driven automated driving
technologies remains the handling of uncommon, rare events that may have not been …
technologies remains the handling of uncommon, rare events that may have not been …
Learning interaction-aware motion prediction model for decision-making in autonomous driving
Predicting the behaviors of other road users is crucial to safe and intelligent decision-making
for autonomous vehicles (AVs). However, most motion prediction models ignore the …
for autonomous vehicles (AVs). However, most motion prediction models ignore the …
Safety-aware causal representation for trustworthy offline reinforcement learning in autonomous driving
In the domain of autonomous driving, the offline Reinforcement Learning (RL) approaches
exhibit notable efficacy in addressing sequential decision-making problems from offline …
exhibit notable efficacy in addressing sequential decision-making problems from offline …
Adaptive safety evaluation for connected and automated vehicles with sparse control variates
Safety performance evaluation is critical for developing and deploying connected and
automated vehicles (CAVs). One prevailing way is to design testing scenarios using prior …
automated vehicles (CAVs). One prevailing way is to design testing scenarios using prior …
Comparative Advantage of Humans versus AI in the Long Tail
N Agarwal, R Huang, A Moehring… - AEA Papers and …, 2024 - pubs.aeaweb.org
Abstract Machine learning algorithms now exceed human performance on several predictive
tasks, generating concerns about widespread job displacement. However, supervised …
tasks, generating concerns about widespread job displacement. However, supervised …