4 papers
Arrive and Survive: Scaling Safe Goal-Conditioned Policy Learning from One-Bit Failure Signals
Guopeng Li, Yiyang Duan, Yiru Jiao +1
Contrastive reinforcement learning (CRL) scales effectively in goal-conditioned tasks by casting policy learning into a self-supervised contrastive objective. However, in a failure…
Learning collision risk proactively from naturalistic driving data at scale
Yiru Jiao, Simeon C. Calvert, Sander van Cranenburgh +1
Accurately and proactively alerting drivers or automated systems to emerging collisions is crucial for road safety, particularly in highly interactive and complex urban environment…
Structure-preserving contrastive learning for spatial time series
Yiru Jiao, Sander van Cranenburgh, Simeon Calvert +1
The effectiveness of neural network models largely relies on learning meaningful latent patterns from data, where self-supervised learning of informative representations can enhanc…
A Unified Probabilistic Approach to Traffic Conflict Detection
Yiru Jiao, Simeon C. Calvert, Sander van Cranenburgh +1
Traffic conflict detection is essential for proactive road safety by identifying potential collisions before they occur. Existing methods rely on surrogate safety measures tailored…