publication . Article . Preprint . 2017

Technical report for real-time certified probabilistic pedestrian forecasting

Ramanarayan Vasudevan;
  • Published: 20 Jun 2017
Abstract
The success of autonomous systems will depend upon their ability to safely navigate human-centric environments. This motivates the need for a real-time, probabilistic forecasting algorithm for pedestrians, cyclists, and other agents since these predictions will form a necessary step in assessing the risk of any action. This paper presents a novel approach to probabilistic forecasting for pedestrians based on weighted sums of ordinary differential equations that are learned from historical trajectory information within a fixed scene. The resulting algorithm is embarrassingly parallel and is able to work at real-time speeds using a naive Python implementation. The...
Subjects
free text keywords: Computer Science - Robotics, Mathematics - Optimization and Control

[1] D. Helbing, “A fluid-dynamic model for the movement of pedestrians,” Complex Systems, vol. 6, pp. 391-415, 1992.

[2] B. D. Ziebart, A. Maas, J. A. Bagnell, and A. K. Dey, “Maximum entropy inverse reinforcement learning,” in Proc. AAAI, 2008, pp. 1433-1438. [OpenAIRE]

[3] B. D. Ziebart, N. Ratliff, G. Gallagher, C. Mertz, K. Peterson, J. A. Bagnell, M. Hebert, A. K. Dey, and S. Srinivasa, “Planning-based prediction for pedestrians,” in IROS, 2009. [OpenAIRE]

[4] K. M. Kitani, B. D. Ziebart, J. A. Bagnell, and M. Hebert, Activity Forecasting. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012, pp. 201-214.

[5] D. Xie, S. Todorovic, and S. Zhu, “Inferring “dark energy” and “dark matter” from image and video,” in Proc. Int'l Conference on Computer Vision, 2013.

[6] V. Karasev, A. Ayvaci, B. Heisele, and S. Soatto, “Intent-aware longterm prediction of pedestrian motion,” Proceedings of the International Conference on Robotics and Automation (ICRA), May 2016. [OpenAIRE]

[7] L. Ballan, F. Castaldo, A. Alahi, F. Palmieri, and S. Savarese, “Knowledge transfer for scene-specific motion prediction,” in Proc. of European Conference on Computer Vision (ECCV), Amsterdam, Netherlands, October 2016. [Online]. Available: http: //arxiv.org/abs/1603.06987 [OpenAIRE]

[8] J. Walker, A. Gupta, and M. Hebert, “Patch to the future: Unsupervised visual prediction,” in Computer Vision and Pattern Recognition, 2014.

[9] D. Helbing and P. Molnar, “Social force model for pedestrian dynamics,” Physical review E, vol. 51, no. 5, p. 4282, 1995. [OpenAIRE]

[10] Y. Xu and H.-J. Huang, “Simulation of exit choosing in pedestrian evacuation with consideration of the direction visual field,” Physica A: Statistical Mechanics and its Applications, vol. 391, no. 4, pp. 991-1000, 2012.

[11] S. Pellegrini, A. Ess, K. Schindler, and L. Van Gool, “You'll never walk alone: Modeling social behavior for multi-target tracking,” in Computer Vision, 2009 IEEE 12th International Conference on. IEEE, 2009, pp. 261-268.

[12] K. Yamaguchi, A. C. Berg, L. E. Ortiz, and T. L. Berg, “Who are you with and where are you going?” in Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE, 2011, pp. 1345-1352.

[13] S. Yi, H. Li, and X. Wang, “Pedestrian behavior modeling from stationary crowds with applications to intelligent surveillance,” IEEE transactions on image processing, vol. 25, no. 9, pp. 4354-4368, 2016.

Abstract
The success of autonomous systems will depend upon their ability to safely navigate human-centric environments. This motivates the need for a real-time, probabilistic forecasting algorithm for pedestrians, cyclists, and other agents since these predictions will form a necessary step in assessing the risk of any action. This paper presents a novel approach to probabilistic forecasting for pedestrians based on weighted sums of ordinary differential equations that are learned from historical trajectory information within a fixed scene. The resulting algorithm is embarrassingly parallel and is able to work at real-time speeds using a naive Python implementation. The...
Subjects
free text keywords: Computer Science - Robotics, Mathematics - Optimization and Control

[1] D. Helbing, “A fluid-dynamic model for the movement of pedestrians,” Complex Systems, vol. 6, pp. 391-415, 1992.

[2] B. D. Ziebart, A. Maas, J. A. Bagnell, and A. K. Dey, “Maximum entropy inverse reinforcement learning,” in Proc. AAAI, 2008, pp. 1433-1438. [OpenAIRE]

[3] B. D. Ziebart, N. Ratliff, G. Gallagher, C. Mertz, K. Peterson, J. A. Bagnell, M. Hebert, A. K. Dey, and S. Srinivasa, “Planning-based prediction for pedestrians,” in IROS, 2009. [OpenAIRE]

[4] K. M. Kitani, B. D. Ziebart, J. A. Bagnell, and M. Hebert, Activity Forecasting. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012, pp. 201-214.

[5] D. Xie, S. Todorovic, and S. Zhu, “Inferring “dark energy” and “dark matter” from image and video,” in Proc. Int'l Conference on Computer Vision, 2013.

[6] V. Karasev, A. Ayvaci, B. Heisele, and S. Soatto, “Intent-aware longterm prediction of pedestrian motion,” Proceedings of the International Conference on Robotics and Automation (ICRA), May 2016. [OpenAIRE]

[7] L. Ballan, F. Castaldo, A. Alahi, F. Palmieri, and S. Savarese, “Knowledge transfer for scene-specific motion prediction,” in Proc. of European Conference on Computer Vision (ECCV), Amsterdam, Netherlands, October 2016. [Online]. Available: http: //arxiv.org/abs/1603.06987 [OpenAIRE]

[8] J. Walker, A. Gupta, and M. Hebert, “Patch to the future: Unsupervised visual prediction,” in Computer Vision and Pattern Recognition, 2014.

[9] D. Helbing and P. Molnar, “Social force model for pedestrian dynamics,” Physical review E, vol. 51, no. 5, p. 4282, 1995. [OpenAIRE]

[10] Y. Xu and H.-J. Huang, “Simulation of exit choosing in pedestrian evacuation with consideration of the direction visual field,” Physica A: Statistical Mechanics and its Applications, vol. 391, no. 4, pp. 991-1000, 2012.

[11] S. Pellegrini, A. Ess, K. Schindler, and L. Van Gool, “You'll never walk alone: Modeling social behavior for multi-target tracking,” in Computer Vision, 2009 IEEE 12th International Conference on. IEEE, 2009, pp. 261-268.

[12] K. Yamaguchi, A. C. Berg, L. E. Ortiz, and T. L. Berg, “Who are you with and where are you going?” in Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE, 2011, pp. 1345-1352.

[13] S. Yi, H. Li, and X. Wang, “Pedestrian behavior modeling from stationary crowds with applications to intelligent surveillance,” IEEE transactions on image processing, vol. 25, no. 9, pp. 4354-4368, 2016.

Powered by OpenAIRE Open Research Graph
Any information missing or wrong?Report an Issue
publication . Article . Preprint . 2017

Technical report for real-time certified probabilistic pedestrian forecasting

Ramanarayan Vasudevan;