This paper proposes a Recurrent Neural Network (RNN) for cyclist path prediction to learn the effect of contextual cues on the behavior directly in an end- to-end approach, removing the need for any annotations. The proposed RNN incorporates three distinct contextual cues: one related to actions of the cyclist, one related to the location of the cyclist on the road, and one related to the interaction between the cyclist and the egovehicle. The RNN predicts a Gaussian distribution over the future position of the cyclist one second into the future with a higher accuracy, compared to a current state-of-the-art model that is based on dynamic mode annotations, where our model attains an average prediction error of 33 cm one second into the future.
Context-based cyclist path prediction using Recurrent Neural Networks
2019-06-01
626836 byte
Conference paper
Electronic Resource
English
CONTEXT-BASED CYCLIST PATH PREDICTION USING RECURRENT NEURAL NETWORKS
British Library Conference Proceedings | 2019
|Using Road Topology to Improve Cyclist Path Prediction
British Library Conference Proceedings | 2017
|Using road topology to improve cyclist path prediction
IEEE | 2017
|Model based cyclist energy prediction
IEEE | 2017
|Driver Response Time to Cyclist Path Intrusions
SAE Technical Papers | 2018
|