Print Email Facebook Twitter Crafted vs. Learned Representations in Predictive Models - A Case Study on Cyclist Path Prediction Title Crafted vs. Learned Representations in Predictive Models - A Case Study on Cyclist Path Prediction Author Pool, E.A.I. (TU Delft Intelligent Vehicles) Kooij, J.F.P. (TU Delft Intelligent Vehicles) Gavrila, D. (TU Delft Intelligent Vehicles) Date 2021 Abstract This paper compares two models for context-based path prediction of objects with switching dynamics: a Dynamic Bayesian Network (DBN) and a Recurrent Neural Network (RNN). These models are instances of two larger model categories, distinguished by whether expert knowledge is explicitly crafted into the state representation (and thus is interpretable) or whether the representation is learned from data, respectively. Both have shown state-of-the-art performance in previous work. In order to provide a fair comparison, we ensure that both models are treated similarly with respect to the use of context cues and parameter estimation. Specifically, we describe (1) how to integrate the context cues (used previously by the DBN) into the RNN, and (2) how to optimize the DBN with back-propagation similar to the RNN, while keeping an interpretable state representation. Experiments are performed on a scenario where a cyclist might turn left at an intersection in front of the ego-vehicle. Results show that the RNN successfully leverages the context cues, and that optimizing the DBN improves its performance with respect to existing work. While the RNN outperforms the optimized DBN in predictive log-likelihood by a significant margin, both models attain similar average Euclidean distance errors (23-39 cm for DBN and 31-34 cm for RNN, predicting 1 s ahead). Subject Active safetyContext modelingDynamicsIntelligent vehiclesmotion predictionPredictive modelsRecurrent neural networksRoadsVehicle dynamicsvulnerable road users (VRUs) To reference this document use: http://resolver.tudelft.nl/uuid:b634c2db-227b-4b29-81ba-84c075a03bf8 DOI https://doi.org/10.1109/TIV.2021.3064253 Embargo date 2021-09-08 ISSN 2379-8858 Source IEEE Transactions on Intelligent Vehicles, 6 (4), 747-759 Bibliographical note Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type journal article Rights © 2021 E.A.I. Pool, J.F.P. Kooij, D. Gavrila Files PDF Crafted_vs_Learned_Repres ... iction.pdf 1.95 MB Close viewer /islandora/object/uuid:b634c2db-227b-4b29-81ba-84c075a03bf8/datastream/OBJ/view