TrEP: Transformer-Based Evidential Prediction for Pedestrian Intention with Uncertainty
TrEP: Transformer-Based Evidential Prediction for Pedestrian Intention with Uncertainty
复制标题
DOI：
10.1609/aaai.v37i3.25463
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Zhengming Zhang;Renran Tian;Zhengming Ding
中科院分区：
文献类型：
--
作者：
Zhengming Zhang;Renran Tian;Zhengming Ding
随着硬件(传感器和处理器)和人工智能算法的快速发展，自动驾驶技术已经进入公众的日常生活，并在支持人类驾驶性能方面取得了巨大成功。然而，由于行人行为的高度上下文变异性和时间动力学，自动驾驶汽车与行人之间的相互作用仍然具有挑战性，阻碍了完全自动驾驶系统的发展。提出了一种新的基于变换的证据预测算法(Trep)来预测行人意图。我们开发了行人视频序列中输入特征之间时间相关性的转换模块和深度证据学习模型来捕捉场景复杂情况下的人工智能不确定性。在三个流行的行人意图基准上的实验结果验证了我们提出的模型的有效性。通过控制不确定性水平可以进一步提高算法的性能。我们系统地比较了人类与人工智能不确定性的分歧，以进一步评估人工智能在混乱场景中的表现。该代码在https://github.com/zzmonlyyou/TrEP.git.上发布
With rapid development in hardware (sensors and processors) and AI algorithms, automated driving techniques have entered the public’s daily life and achieved great success in supporting human driving performance. However, due to the high contextual variations and temporal dynamics in pedestrian behaviors, the interaction between autonomous-driving cars and pedestrians remains challenging, impeding the development of fully autonomous driving systems. This paper focuses on predicting pedestrian intention with a novel transformer-based evidential prediction (TrEP) algorithm. We develop a transformer module towards the temporal correlations among the input features within pedestrian video sequences and a deep evidential learning model to capture the AI uncertainty under scene complexities. Experimental results on three popular pedestrian intent benchmarks have verified the effectiveness of our proposed model over the state-of-the-art. The algorithm performance can be further boosted by controlling the uncertainty level. We systematically compare human disagreements with AI uncertainty to further evaluate AI performance in confusing scenes. The code is released at https://github.com/zzmonlyyou/TrEP.git.