Videos of examples from the ESP dataset. The ESP-Dataset with semantic environment information focuses on emergency-event-based challenging scenarios. The collected scenarios encompassed various interactions such as merges, lane changes, ramp out, cone block, and zip lane.
Emergent-scene safety is the key milestone for fully autonomous driving, and reliable on-time prediction is essential to maintain safety in emergency scenarios. However, these emergency scenarios are long-tailed and hard to collect, which restricts the system from getting reliable predictions.
In this paper, we build a new dataset, which aims at the long-term prediction with the inconspicuous state variation in history for the emergency event, named the Extro-Spective Prediction (ESP) problem. Based on the proposed dataset, a flexible feature encoder for ESP is introduced to various prediction methods as a seamless plug-in, and its consistent performance improvement underscores its efficacy. Furthermore, a new metric named clamped temporal error (CTE) is proposed to give a more comprehensive evaluation of prediction performance, especially in time-sensitive emergency events of subseconds. Interestingly, as our ESP features can be described in human-readable language naturally, the application of integrating into ChatGPT also shows huge potential.
@article{dingrui2024esp,
author = {Wang, Dingrui and Lai, Zheyuan and Li, Yuda and Wu, Yi and Ma, Yuexin and Betz, Johannes and Yang, Ruigang and Li, Wei},
title = {ESP: Extro-Spective Prediction for Long-term Behavior Reasoning in Emergency Scenarios},
journal = {ICRA},
year = {2024},
}