Building Prior Knowledge: A Markov Based Pedestrian Prediction Model Using Urban Environmental Data

Pavan Vasishta 1, 2 Dominique Vaufreydaz 3 Anne Spalanzani 2
2 CHROMA - Robots coopératifs et adaptés à la présence humaine en environnements dynamiques
Inria Grenoble - Rhône-Alpes, CITI - CITI Centre of Innovation in Telecommunications and Integration of services
3 PERVASIVE - Interaction située avec les objets et environnements intelligents
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology, UGA - Université Grenoble Alpes
Abstract : Autonomous Vehicles navigating in urban areas have a need to understand and predict future pedestrian behavior for safer navigation. This high level of situational awareness requires observing pedestrian behavior and extrapolating their positions to know future positions. While some work has been done in this field using Hidden Markov Models (HMMs), one of the few observed drawbacks of the method is the need for informed priors for learning behavior. In this work, an extension to the Growing Hidden Markov Model (GHMM) method is proposed to solve some of these drawbacks. This is achieved by building on existing work using potential cost maps and the principle of Natural Vision. As a consequence, the proposed model is able to predict pedestrian positions more precisely over a longer horizon compared to the state of the art. The method is tested over "legal" and "illegal" behavior of pedestrians, having trained the model with sparse observations and partial trajectories. The method, with no training data, is compared against a trained state of the art model. It is observed that the proposed method is robust even in new, previously unseen areas.
Type de document :
Communication dans un congrès
ICARCV 2018 - 15th International Conference on Control, Automation, Robotics and Vision, Nov 2018, Singapore, Singapore. pp.1-12
Liste complète des métadonnées

https://hal.inria.fr/hal-01875147
Contributeur : Dominique Vaufreydaz <>
Soumis le : lundi 17 septembre 2018 - 08:53:12
Dernière modification le : mercredi 13 février 2019 - 10:00:03
Document(s) archivé(s) le : mardi 18 décembre 2018 - 12:19:22

Fichiers

main_author.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01875147, version 1
  • ARXIV : 1809.06045

Collections

Citation

Pavan Vasishta, Dominique Vaufreydaz, Anne Spalanzani. Building Prior Knowledge: A Markov Based Pedestrian Prediction Model Using Urban Environmental Data. ICARCV 2018 - 15th International Conference on Control, Automation, Robotics and Vision, Nov 2018, Singapore, Singapore. pp.1-12. 〈hal-01875147〉

Partager

Métriques

Consultations de la notice

383

Téléchargements de fichiers

83