Motion trajectory prediction based on a CNN-LSTM sequential model
- PDF / 1,219,494 Bytes
- 21 Pages / 595 x 842 pts (A4) Page_size
- 83 Downloads / 238 Views
. RESEARCH PAPER .
November 2020, Vol. 63 212207:1–212207:21 https://doi.org/10.1007/s11432-019-2761-y
Motion trajectory prediction based on a CNN-LSTM sequential model Guo XIE* , Anqi SHANGGUAN, Rong FEI, Wenjiang JI, Weigang MA & Xinhong HEI* School of Automation and Information Engineering, School of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048, China Received 11 September 2019/Accepted 29 November 2019/Published online 15 October 2020
Abstract Accurate monitoring the surrounding environment is an important research direction in the field of unmanned systems such as bio-robotics, and has attracted much research attention in recent years. The trajectories of surrounding vehicles should be predicted accurately in space and time to realize active defense and running safety of an unmanned system. However, there is uncertainty and uncontrollability in the process of trajectory prediction of surrounding obstacles. In this study, we propose a trajectory prediction method based on a sequential model, that fuses two neural networks of a convolutional neural network (CNN) and a long short-term memory network (LSTM). First, a box plot is used to detect and eliminate abnormal values of vehicle trajectories, and valid trajectory data are obtained. Second, the trajectories of surrounding vehicles are predicted by merging the characteristics of CNN space expansion and LSTM time expansion; the hyper-parameters of the model are optimized according to a grid search algorithm, which satisfies the double-precision prediction requirement in space and time. Finally, data from next generation simulation (NGSIM) and Creteil roundabout in France are taken as test cases; the correctness and rationality of the method are verified by prediction error indicators. Experimental results demonstrate that the proposed CNNLSTM method is more accurate and features a shorter time cost, which meets the prediction requirements and provides an effective method for the safe operation of unmanned systems. Keywords
bio-robots, unmanned system, outlier detection, hyper-parameters, trajectory prediction
Citation Xie G, Shangguan A Q, Fei R, et al. Motion trajectory prediction based on a CNN-LSTM sequential model. Sci China Inf Sci, 2020, 63(11): 212207, https://doi.org/10.1007/s11432-019-2761-y
1
Introduction
In the development of bio-robotic systems, the safety and reliability are important but challenging issues [1]. Traffic transportation, as one of the large application fields of bio-robotic systems, is facing increasing safety problem. It can be seen from historical traffic accidents that ensuring operation safety of traffic transportation is extremely important. Currently, there are many transportation safety performance evaluation methods, such as fault diagnosis [2–5], remaining useful life prediction [6, 7], and parameters identification [8]. As for the self-driving vehicles, they can only ensure their safety by judging whether the surrounding environment is safe during driving. Particularly, they can make
Data Loading...
