TY - GEN
T1 - Robust modeling and prediction in dynamic environments using recurrent flow networks
AU - Choi, Sungjoon
AU - Lee, Kyungjae
AU - Oh, Songhwai
N1 - Funding Information:
This research was supported by a grant to Bio-Mimetic Robot Research Center funded by Defense Acquisition Program Administration and by Agency for Defense Development (UD130070ID) and Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT and Future Planning (NRF-2015R1A2A1A15052493).
Publisher Copyright:
© 2016 IEEE.
PY - 2016/11/28
Y1 - 2016/11/28
N2 - To enable safe motion planning in a dynamic environment, it is vital to anticipate and predict object movements. In practice, however, an accurate object identification among multiple moving objects is extremely challenging, making it infeasible to accurately track and predict individual objects. Furthermore, even for a single object, its appearance can vary significantly due to external effects, such as occlusions, varying perspectives, or illumination changes. In this paper, we propose a novel recurrent network architecture called a recurrent flow network that can infer the velocity of each cell and the probability of future occupancy from a sequence of occupancy grids which we refer to as an occupancy flow. The parameters of the recurrent flow network are optimized using Bayesian optimization. The proposed method outperforms three baseline optical flow methods, Lucas-Kanade, Lucas-Kanade with Tikhonov regularization, and HornSchunck methods, and a Bayesian occupancy grid filter in terms of both prediction accuracy and robustness to noise.
AB - To enable safe motion planning in a dynamic environment, it is vital to anticipate and predict object movements. In practice, however, an accurate object identification among multiple moving objects is extremely challenging, making it infeasible to accurately track and predict individual objects. Furthermore, even for a single object, its appearance can vary significantly due to external effects, such as occlusions, varying perspectives, or illumination changes. In this paper, we propose a novel recurrent network architecture called a recurrent flow network that can infer the velocity of each cell and the probability of future occupancy from a sequence of occupancy grids which we refer to as an occupancy flow. The parameters of the recurrent flow network are optimized using Bayesian optimization. The proposed method outperforms three baseline optical flow methods, Lucas-Kanade, Lucas-Kanade with Tikhonov regularization, and HornSchunck methods, and a Bayesian occupancy grid filter in terms of both prediction accuracy and robustness to noise.
UR - http://www.scopus.com/inward/record.url?scp=85006508034&partnerID=8YFLogxK
U2 - 10.1109/IROS.2016.7759278
DO - 10.1109/IROS.2016.7759278
M3 - Conference contribution
AN - SCOPUS:85006508034
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 1737
EP - 1742
BT - IROS 2016 - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2016
Y2 - 9 October 2016 through 14 October 2016
ER -